WorldWideScience

Sample records for network cnn newsroom

  1. CNN Newsroom Classroom Guides, June 2002.

    Science.gov (United States)

    Cable News Network, Atlanta, GA.

    These classroom guides, designed to accompany the daily CNN (Cable News Network) Newsroom broadcasts for the month of June 2002, provide program rundowns, suggestions for class activities and discussion, student handouts, and a list of related news terms. Major topics covered include: the Kashmir conflict; the Pakistan and the Kazahkstan Summit;…

  2. CNN Newsroom Classroom Guides. April 1-29, 1994.

    Science.gov (United States)

    Cable News Network, Atlanta, GA.

    These classroom guides for the daily CNN (Cable News Network) Newsroom broadcasts for the month of April provide program rundowns, suggestions for class activities and discussion, student handouts, and a list of related news terms. Topics covered by the guides include: (1) peace in the Middle East, Tom Bradley, and minority superheroes (April 1);…

  3. CNN Newsroom Classroom Guides. July 1-31, 1995.

    Science.gov (United States)

    Cable News Network, Atlanta, GA.

    These classroom guides for the daily CNN (Cable News Network) Newsroom broadcasts for the month of July provide program rundowns, suggestions for class activities and discussion, student handouts, and a list of related news terms. Topics covered by the guides include: (1) British Prime Minister John Major, trade and Tijuana, sports physics, and…

  4. BrainNetCNN: Convolutional neural networks for brain networks; towards predicting neurodevelopment.

    Science.gov (United States)

    Kawahara, Jeremy; Brown, Colin J; Miller, Steven P; Booth, Brian G; Chau, Vann; Grunau, Ruth E; Zwicker, Jill G; Hamarneh, Ghassan

    2017-02-01

    We propose BrainNetCNN, a convolutional neural network (CNN) framework to predict clinical neurodevelopmental outcomes from brain networks. In contrast to the spatially local convolutions done in traditional image-based CNNs, our BrainNetCNN is composed of novel edge-to-edge, edge-to-node and node-to-graph convolutional filters that leverage the topological locality of structural brain networks. We apply the BrainNetCNN framework to predict cognitive and motor developmental outcome scores from structural brain networks of infants born preterm. Diffusion tensor images (DTI) of preterm infants, acquired between 27 and 46 weeks gestational age, were used to construct a dataset of structural brain connectivity networks. We first demonstrate the predictive capabilities of BrainNetCNN on synthetic phantom networks with simulated injury patterns and added noise. BrainNetCNN outperforms a fully connected neural-network with the same number of model parameters on both phantoms with focal and diffuse injury patterns. We then apply our method to the task of joint prediction of Bayley-III cognitive and motor scores, assessed at 18 months of age, adjusted for prematurity. We show that our BrainNetCNN framework outperforms a variety of other methods on the same data. Furthermore, BrainNetCNN is able to identify an infant's postmenstrual age to within about 2 weeks. Finally, we explore the high-level features learned by BrainNetCNN by visualizing the importance of each connection in the brain with respect to predicting the outcome scores. These findings are then discussed in the context of the anatomy and function of the developing preterm infant brain. Copyright © 2016 Elsevier Inc. All rights reserved.

  5. S-CNN: Subcategory-aware convolutional networks for object detection.

    Science.gov (United States)

    Chen, Tao; Lu, Shijian; Fan, Jiayuan

    2017-09-26

    The marriage between the deep convolutional neural network (CNN) and region proposals has made breakthroughs for object detection in recent years. While the discriminative object features are learned via a deep CNN for classification, the large intra-class variation and deformation still limit the performance of the CNN based object detection. We propose a subcategory-aware CNN (S-CNN) to solve the object intra-class variation problem. In the proposed technique, the training samples are first grouped into multiple subcategories automatically through a novel instance sharing maximum margin clustering process. A multi-component Aggregated Channel Feature (ACF) detector is then trained to produce more latent training samples, where each ACF component corresponds to one clustered subcategory. The produced latent samples together with their subcategory labels are further fed into a CNN classifier to filter out false proposals for object detection. An iterative learning algorithm is designed for the joint optimization of image subcategorization, multi-component ACF detector, and subcategory-aware CNN classifier. Experiments on INRIA Person dataset, Pascal VOC 2007 dataset and MS COCO dataset show that the proposed technique clearly outperforms the state-of-the-art methods for generic object detection.

  6. Klasifikasi Citra Menggunakan Convolutional Neural Network (CNN pada Caltech 101

    Directory of Open Access Journals (Sweden)

    Wayan Suartika Eka Putra

    2016-04-01

    Full Text Available Deep Learning adalah sebuah bidang keilmuan baru dalam bidang Machine Learning yang akhir-akhir ini berkembang karena perkembangan teknologi GPU accelaration. Deep Learning memiliki kemampuan yang sangat baik dalam visi komputer. Salah satunya adalah pada kasus klasifikasi objek pada citra. Dengan mengimplementasikan salah satu metode machine learning yang dapat digunakan untuk klasifikasi citra objek yaitu CNN. Metode CNN terdiri dari dua tahap. Tahap pertama adalah klasifikasi citra menggunakan feedforward. Tahap kedua merupakan tahap pembelajaran dengan metode backpropagation. Sebelum dilakukan klasifikasi, terlebih dahulu dilakukan praproses dengan metode wrapping dan cropping untuk memfokuskan objek yang akan diklasifikasi. Selanjutnya dilakukan training menggunakan metode feedforward dan backpropagation. Terakhir adalah tahap klasifikasi menggunakan metode feedforward dengan bobot dan bias yang diperbarui. Hasil uji coba dari klasifikasi citra objek dengan tingkat confusion yang berbeda pada basis data Caltech 101 menghasilkan rata-rata nilai akurasi mencapai. Sehingga dapat disimpulkan bahwa metode CNN yang digunakan pada Tugas Akhir ini mampu melakukan klasifikasi dengan baik.

  7. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

    Science.gov (United States)

    Ren, Shaoqing; He, Kaiming; Girshick, Ross; Sun, Jian

    2017-06-01

    State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [1] and Fast R-CNN [2] have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features-using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model [3] , our detection system has a frame rate of 5 fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.

  8. Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

    Science.gov (United States)

    Hoo-Chang, Shin; Roth, Holger R.; Gao, Mingchen; Lu, Le; Xu, Ziyue; Nogues, Isabella; Yao, Jianhua; Mollura, Daniel

    2016-01-01

    Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets (i.e. ImageNet) and the revival of deep convolutional neural networks (CNN). CNNs enable learning data-driven, highly representative, layered hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models (supervised) pre-trained from natural image dataset to medical image tasks (although domain transfer between two medical image datasets is also possible). In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computeraided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, with 85% sensitivity at 3 false positive per patient, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance

  9. Agriculture: Newsroom

    Science.gov (United States)

    Agriculture Newsroom. News releases, reports, and other documents from around EPA that are of interest or direct importance to the environmental management or compliance efforts of the agricultural community.

  10. PARTICLE SWARM OPTIMIZATION (PSO FOR TRAINING OPTIMIZATION ON CONVOLUTIONAL NEURAL NETWORK (CNN

    Directory of Open Access Journals (Sweden)

    Arie Rachmad Syulistyo

    2016-02-01

    Full Text Available Neural network attracts plenty of researchers lately. Substantial number of renowned universities have developed neural network for various both academically and industrially applications. Neural network shows considerable performance on various purposes. Nevertheless, for complex applications, neural network’s accuracy significantly deteriorates. To tackle the aforementioned drawback, lot of researches had been undertaken on the improvement of the standard neural network. One of the most promising modifications on standard neural network for complex applications is deep learning method. In this paper, we proposed the utilization of Particle Swarm Optimization (PSO in Convolutional Neural Networks (CNNs, which is one of the basic methods in deep learning. The use of PSO on the training process aims to optimize the results of the solution vectors on CNN in order to improve the recognition accuracy. The data used in this research is handwritten digit from MNIST. The experiments exhibited that the accuracy can be attained in 4 epoch is 95.08%. This result was better than the conventional CNN and DBN.  The execution time was also almost similar to the conventional CNN. Therefore, the proposed method was a promising method.

  11. Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN).

    Science.gov (United States)

    Chen, Hu; Zhang, Yi; Kalra, Mannudeep K; Lin, Feng; Chen, Yang; Liao, Peixo; Zhou, Jiliu; Wang, Ge

    2017-06-13

    Given the potential risk of X-ray radiation to the patient, low-dose CT has attracted a considerable interest in the medical imaging field. Currently, the main stream low-dose CT methods include vendor-specific sinogram domain filtration and iterative reconstruction algorithms, but they need to access raw data whose formats are not transparent to most users. Due to the difficulty of modeling the statistical characteristics in the image domain, the existing methods for directly processing reconstructed images cannot eliminate image noise very well while keeping structural details. Inspired by the idea of deep learning, here we combine the autoencoder, deconvolution network, and shortcut connections into the residual encoder-decoder convolutional neural network (RED-CNN) for low-dose CT imaging. After patch-based training, the proposed RED-CNN achieves a competitive performance relative to the-state-of-art methods in both simulated and clinical cases. Especially, our method has been favorably evaluated in terms of noise suppression, structural preservation, and lesion detection.

  12. SampleCNN: End-to-End Deep Convolutional Neural Networks Using Very Small Filters for Music Classification

    Directory of Open Access Journals (Sweden)

    Jongpil Lee

    2018-01-01

    Full Text Available Convolutional Neural Networks (CNN have been applied to diverse machine learning tasks for different modalities of raw data in an end-to-end fashion. In the audio domain, a raw waveform-based approach has been explored to directly learn hierarchical characteristics of audio. However, the majority of previous studies have limited their model capacity by taking a frame-level structure similar to short-time Fourier transforms. We previously proposed a CNN architecture which learns representations using sample-level filters beyond typical frame-level input representations. The architecture showed comparable performance to the spectrogram-based CNN model in music auto-tagging. In this paper, we extend the previous work in three ways. First, considering the sample-level model requires much longer training time, we progressively downsample the input signals and examine how it affects the performance. Second, we extend the model using multi-level and multi-scale feature aggregation technique and subsequently conduct transfer learning for several music classification tasks. Finally, we visualize filters learned by the sample-level CNN in each layer to identify hierarchically learned features and show that they are sensitive to log-scaled frequency.

  13. The digital Newsroom

    DEFF Research Database (Denmark)

    Hassall Thomsen, Line Hassall

    2009-01-01

    The aim with this paper is to explore this new newsroom and what it means to the journalists in it. The paper will seek to answer questions such as; How does the physical room affect the social interactions in it? What does the organisation of people and technology in the newsroom do for the jour...

  14. CNN a paradigm for complexity

    CERN Document Server

    Chua, Leon O

    1998-01-01

    Revolutionary and original, this treatise presents a new paradigm of EMERGENCE and COMPLEXITY, with applications drawn from numerous disciplines, including artificial life, biology, chemistry, computation, physics, image processing, information science, etc.CNN is an acronym for Cellular Neural Networks when used in the context of brain science, or Cellular Nonlinear Networks, when used in the context of emergence and complexity. A CNN is modeled by cells and interactions: cells are defined as dynamical systems and interactions are defined via coupling laws. The CNN paradigm is a universal Tur

  15. Nonlinear Circuits and Neural Networks: Chip Implementation and Applications of the TeraOPS CNN Dynamic Array Supercomputer

    National Research Council Canada - National Science Library

    Chua, L

    1998-01-01

    .... Advances in research have been made in the following areas: (1) The design and implementation of the first-ever ARAM in the CNN Chip Set Architecture was successfully competed, and the samples were successfully tested; (2...

  16. Entering The Newsroom

    DEFF Research Database (Denmark)

    Peters, Chris

    2017-01-01

    , from the broader purpose of journalism in society, to its contemporary status and performance, to the politics of the nation. Simply put, the show acts as a catalyst for impassioned discussion and debate. This chapter utilises The Newsroom as a case study to contextualize the struggle over owning...... that evaluating reception to – and the value of – entertainment products in any great depth obliges us to simultaneously consider shifts in perception surrounding what they represent. However, the converse to this claim also holds true. A central claim this chapter makes is that evaluating the interwoven...

  17. CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices

    OpenAIRE

    Ding, Caiwen; Liao, Siyu; Wang, Yanzhi; Li, Zhe; Liu, Ning; Zhuo, Youwei; Wang, Chao; Qian, Xuehai; Bai, Yu; Yuan, Geng; Ma, Xiaolong; Zhang, Yipeng; Tang, Jian; Qiu, Qinru; Lin, Xue

    2017-01-01

    Large-scale deep neural networks (DNNs) are both compute and memory intensive. As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy. For DNNs, the model size is an important factor affecting performance, scalability and energy efficiency. Weight pruning achieves good compression ratios but suffers from three drawbacks: 1) the irregular network structure after pruning; 2) the increased training complexity; and 3) the ...

  18. Evaluation of CNN as anthropomorphic model observer

    Science.gov (United States)

    Massanes, Francesc; Brankov, Jovan G.

    2017-03-01

    Model observers (MO) are widely used in medical imaging to act as surrogates of human observers in task-based image quality evaluation, frequently towards optimization of reconstruction algorithms. In this paper, we explore the use of convolutional neural networks (CNN) to be used as MO. We will compare CNN MO to alternative MO currently being proposed and used such as the relevance vector machine based MO and channelized Hotelling observer (CHO). As the success of the CNN, and other deep learning approaches, is rooted in large data sets availability, which is rarely the case in medical imaging systems task-performance evaluation, we will evaluate CNN performance on both large and small training data sets.

  19. CNN-based ranking for biomedical entity normalization.

    Science.gov (United States)

    Li, Haodi; Chen, Qingcai; Tang, Buzhou; Wang, Xiaolong; Xu, Hua; Wang, Baohua; Huang, Dong

    2017-10-03

    Most state-of-the-art biomedical entity normalization systems, such as rule-based systems, merely rely on morphological information of entity mentions, but rarely consider their semantic information. In this paper, we introduce a novel convolutional neural network (CNN) architecture that regards biomedical entity normalization as a ranking problem and benefits from semantic information of biomedical entities. The CNN-based ranking method first generates candidates using handcrafted rules, and then ranks the candidates according to their semantic information modeled by CNN as well as their morphological information. Experiments on two benchmark datasets for biomedical entity normalization show that our proposed CNN-based ranking method outperforms traditional rule-based method with state-of-the-art performance. We propose a CNN architecture that regards biomedical entity normalization as a ranking problem. Comparison results show that semantic information is beneficial to biomedical entity normalization and can be well combined with morphological information in our CNN architecture for further improvement.

  20. Edge of chaos in reaction diffusion CNN model

    Directory of Open Access Journals (Sweden)

    Slavova Angela

    2017-02-01

    Full Text Available In this paper, we study the dynamics of a reaction-diffusion Cellular Nonlinear Network (RD-CNN nodel in which the reaction term is represented by Brusselator cell. We investigate the RD-CNN dynamics by means of describing function method. Comparison with classical results for Brusselator equation is provided. Then we introduce a new RD-CNN model with memristor coupling, for which the edge of chaos regime in the parameter space is determined. Numerical simulations are presented for obtaining dynamic patterns in the RD-CNN model with memristor coupling.

  1. Improving productivity in the newsroom?

    DEFF Research Database (Denmark)

    Bro, Peter; Reinecke Hansen, Kenneth; Andersson, Ralf

    2016-01-01

    to both the news products, the news processes and the individual news producers. This article is based on newsroom observations, interviews with employees and content analyses, and it shows how the practice of journalism at DR News has been altered in several ways after the implementation of the news...

  2. A CNN-Specific Integrated Processor

    Science.gov (United States)

    Malki, Suleyman; Spaanenburg, Lambert

    2009-12-01

    Integrated Processors (IP) are algorithm-specific cores that either by programming or by configuration can be re-used within many microelectronic systems. This paper looks at Cellular Neural Networks (CNN) to become realized as IP. First current digital implementations are reviewed, and the memoryprocessor bandwidth issues are analyzed. Then a generic view is taken on the structure of the network, and a new intra-communication protocol based on rotating wheels is proposed. It is shown that this provides for guaranteed high-performance with a minimal network interface. The resulting node is small and supports multi-level CNN designs, giving the system a 30-fold increase in capacity compared to classical designs. As it facilitates multiple operations on a single image, and single operations on multiple images, with minimal access to the external image memory, balancing the internal and external data transfer requirements optimizes the system operation. In conventional digital CNN designs, the treatment of boundary nodes requires additional logic to handle the CNN value propagation scheme. In the new architecture, only a slight modification of the existing cells is necessary to model the boundary effect. A typical prototype for visual pattern recognition will house 4096 CNN cells with a 2% overhead for making it an IP.

  3. A CNN-Specific Integrated Processor

    Directory of Open Access Journals (Sweden)

    Suleyman Malki

    2009-01-01

    Full Text Available Integrated Processors (IP are algorithm-specific cores that either by programming or by configuration can be re-used within many microelectronic systems. This paper looks at Cellular Neural Networks (CNN to become realized as IP. First current digital implementations are reviewed, and the memoryprocessor bandwidth issues are analyzed. Then a generic view is taken on the structure of the network, and a new intra-communication protocol based on rotating wheels is proposed. It is shown that this provides for guaranteed high-performance with a minimal network interface. The resulting node is small and supports multi-level CNN designs, giving the system a 30-fold increase in capacity compared to classical designs. As it facilitates multiple operations on a single image, and single operations on multiple images, with minimal access to the external image memory, balancing the internal and external data transfer requirements optimizes the system operation. In conventional digital CNN designs, the treatment of boundary nodes requires additional logic to handle the CNN value propagation scheme. In the new architecture, only a slight modification of the existing cells is necessary to model the boundary effect. A typical prototype for visual pattern recognition will house 4096 CNN cells with a 2% overhead for making it an IP.

  4. The CNN Effect: Stretegic Enabler or Operational Risk?

    National Research Council Canada - National Science Library

    Belknap, Margaret

    2001-01-01

    .... Satellite technology and the proliferation of 2417 news networks have created and increased the so-called 'CNN effect' on strategic level decision-making and how warfighters direct their commands...

  5. Diversity disorders: Ethnicity and newsroom cultures

    Directory of Open Access Journals (Sweden)

    Gunilla Hultén

    2009-10-01

    Full Text Available Sweden, as many other European countries, has been engaged in the debate concerning the relationships between social cohesion and the media. The article examines the tension between officially expressed attitudes and diversity goals of Swedish newsrooms and how journalists who have foreign backgrounds perceive these. Despite the intense discussions in recent years concerning media's role in a multi-ethnic context Swedish media organizations have not yet developed an effective means of promoting and implementing diversity in the newsrooms. The interviewed journalists draw attention to the dilemma of not being accepted in majority dominated newsrooms and stress the need to change editorial organization patterns, newsroom cultures and to re-define journalistic missions regarding ethnic diversity. The article concerns the market focus of news production and argues that the present tendency to mainstream cultural diversity in media content may lead to the exclusion of minority voices and thus undermining diversity efforts.

  6. Newsroom Ethnography in a Field Perspective

    DEFF Research Database (Denmark)

    Willig, Ida

    2012-01-01

    The reflexive sociology of Pierre Bourdieu offers a promising analytical framework for extending the insights offered by the classical tradition of ethnographic newsroom studies. On a methodological level, Bourdieu’s analytical framework has the potential to help us address one of the key questions...... values is used as a vehicle for presenting Bourdieu’s field theory, which is discussed in relation to newsroom studies more generally. It shows how the ‘context’, often missing in ethnographic studies, can be analysed using the framework of reflexive sociology....... in ethnographic research: how should we theorise and empirically investigate context? The question is, not least, practical in nature. When it comes to newsroom ethnography, one of the traditional problems concerns the ‘invisibility’ of certain structures such as the political economy of everyday news work which...

  7. Continuous Chinese sign language recognition with CNN-LSTM

    Science.gov (United States)

    Yang, Su; Zhu, Qing

    2017-07-01

    The goal of sign language recognition (SLR) is to translate the sign language into text, and provide a convenient tool for the communication between the deaf-mute and the ordinary. In this paper, we formulate an appropriate model based on convolutional neural network (CNN) combined with Long Short-Term Memory (LSTM) network, in order to accomplish the continuous recognition work. With the strong ability of CNN, the information of pictures captured from Chinese sign language (CSL) videos can be learned and transformed into vector. Since the video can be regarded as an ordered sequence of frames, LSTM model is employed to connect with the fully-connected layer of CNN. As a recurrent neural network (RNN), it is suitable for sequence learning tasks with the capability of recognizing patterns defined by temporal distance. Compared with traditional RNN, LSTM has performed better on storing and accessing information. We evaluate this method on our self-built dataset including 40 daily vocabularies. The experimental results show that the recognition method with CNN-LSTM can achieve a high recognition rate with small training sets, which will meet the needs of real-time SLR system.

  8. The CNN Paradigm for Complexity

    Science.gov (United States)

    Bucolo, M.; Caponetto, R.; Fortuna, L.; Frasca, M.

    The following sections are included: * Introduction * The 3D-CNN Model * E3: An Universal Emulator for Complex Systems * Emergence of Forms in 3D-CNNs * Initial conditions * 3D waves in homogeneous and unhomogeneous media * Chua's circuit * Lorenz system * Rössler system * FitzHugh-Nagumo neuron model * Hindmarsh-Rose neuron model * Inferior-Olive neuron model * Izhikevich neuron model * Neuron model exhibiting homoclinic chaos * Conclusions * References

  9. Theorems and application of local activity of CNN with five state variables and one port.

    Science.gov (United States)

    Xiong, Gang; Dong, Xisong; Xie, Li; Yang, Thomas

    2012-01-01

    Coupled nonlinear dynamical systems have been widely studied recently. However, the dynamical properties of these systems are difficult to deal with. The local activity of cellular neural network (CNN) has provided a powerful tool for studying the emergence of complex patterns in a homogeneous lattice, which is composed of coupled cells. In this paper, the analytical criteria for the local activity in reaction-diffusion CNN with five state variables and one port are presented, which consists of four theorems, including a serial of inequalities involving CNN parameters. These theorems can be used for calculating the bifurcation diagram to determine or analyze the emergence of complex dynamic patterns, such as chaos. As a case study, a reaction-diffusion CNN of hepatitis B Virus (HBV) mutation-selection model is analyzed and simulated, the bifurcation diagram is calculated. Using the diagram, numerical simulations of this CNN model provide reasonable explanations of complex mutant phenomena during therapy. Therefore, it is demonstrated that the local activity of CNN provides a practical tool for the complex dynamics study of some coupled nonlinear systems.

  10. Theorems and Application of Local Activity of CNN with Five State Variables and One Port

    Directory of Open Access Journals (Sweden)

    Gang Xiong

    2012-01-01

    Full Text Available Coupled nonlinear dynamical systems have been widely studied recently. However, the dynamical properties of these systems are difficult to deal with. The local activity of cellular neural network (CNN has provided a powerful tool for studying the emergence of complex patterns in a homogeneous lattice, which is composed of coupled cells. In this paper, the analytical criteria for the local activity in reaction-diffusion CNN with five state variables and one port are presented, which consists of four theorems, including a serial of inequalities involving CNN parameters. These theorems can be used for calculating the bifurcation diagram to determine or analyze the emergence of complex dynamic patterns, such as chaos. As a case study, a reaction-diffusion CNN of hepatitis B Virus (HBV mutation-selection model is analyzed and simulated, the bifurcation diagram is calculated. Using the diagram, numerical simulations of this CNN model provide reasonable explanations of complex mutant phenomena during therapy. Therefore, it is demonstrated that the local activity of CNN provides a practical tool for the complex dynamics study of some coupled nonlinear systems.

  11. Multi-region two-stream R-CNN for action detection

    OpenAIRE

    Peng, Xiaojiang; Schmid, Cordelia

    2016-01-01

    International audience; We propose a multi-region two-stream R-CNN model for action detection in realistic videos. We start from frame-level action detection based on faster R-CNN [1], and make three contributions: (1) we show that a motion region proposal network generates high-quality proposals , which are complementary to those of an appearance region proposal network; (2) we show that stacking optical flow over several frames significantly improves frame-level action detection; and (3) we...

  12. Effect of Newsroom Management Styles on Journalists: A Case Study.

    Science.gov (United States)

    Gaziano, Cecilie; Coulson, David C.

    1988-01-01

    Determines whether a relationship exists between type of newsroom management style--authoritarian or democratic--and journalists' attitudes toward their newspaper supervisors, jobs, readers, and community. Finds that differences in management style do not appear to influence the relationship with editors or attitudes toward their audience. (RC)

  13. Leadership Development in College Newsroom Labs: It is Transactional

    Science.gov (United States)

    Collins, Janice Marie

    2017-01-01

    While men ease their ways into positions of authority, the number of women holding top-level leadership positions in media is declining. This study sought to explore how the professional socialization process found in college newsroom labs contributes to the effectiveness or ineffectiveness of female leadership development. Mixed methodology…

  14. The digital Newsroom – from Square to Circle

    DEFF Research Database (Denmark)

    Hassall Thomsen, Line Hassall

    At a time where journalistic production is undergoing rapid change and ever growing competition, so is the room from which the news emerges. As broadcasters visit each other in order to mimic each others’ practices, rooms and technology, a new type of newsroom that has moved from the classical sq...... room affect the social interactions in it? What does the organisation of people and technology in the newsroom do for the journalistic working process? And which hierarchal structure does the room feed into? While investigating symbolic and face to face interaction between journalists...... of the space shall bring about an overview of the body of news making, in order to consider it an embodiment of current values and culture of practice within journalism. Thus, I will highlight the advantages of studying the setting, space and place of journalism practice for journalism production studies....

  15. CNN for breaking text-based CAPTCHA with noise

    Science.gov (United States)

    Liu, Kaixuan; Zhang, Rong; Qing, Ke

    2017-07-01

    A CAPTCHA ("Completely Automated Public Turing test to tell Computers and Human Apart") system is a program that most humans can pass but current computer programs could hardly pass. As the most common type of CAPTCHAs , text-based CAPTCHA has been widely used in different websites to defense network bots. In order to breaking textbased CAPTCHA, in this paper, two trained CNN models are connected for the segmentation and classification of CAPTCHA images. Then base on these two models, we apply sliding window segmentation and voting classification methods realize an end-to-end CAPTCHA breaking system with high success rate. The experiment results show that our method is robust and effective in breaking text-based CAPTCHA with noise.

  16. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising.

    Science.gov (United States)

    Zhang, Kai; Zuo, Wangmeng; Chen, Yunjin; Meng, Deyu; Zhang, Lei

    2017-07-01

    The discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In this paper, we take one step forward by investigating the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image denoising. Specifically, residual learning and batch normalization are utilized to speed up the training process as well as boost the denoising performance. Different from the existing discriminative denoising models which usually train a specific model for additive white Gaussian noise at a certain noise level, our DnCNN model is able to handle Gaussian denoising with unknown noise level (i.e., blind Gaussian denoising). With the residual learning strategy, DnCNN implicitly removes the latent clean image in the hidden layers. This property motivates us to train a single DnCNN model to tackle with several general image denoising tasks, such as Gaussian denoising, single image super-resolution, and JPEG image deblocking. Our extensive experiments demonstrate that our DnCNN model can not only exhibit high effectiveness in several general image denoising tasks, but also be efficiently implemented by benefiting from GPU computing.

  17. Mining key elements for severe convection prediction based on CNN

    Science.gov (United States)

    Liu, Ming; Pan, Ning; Zhang, Changan; Sha, Hongzhou; Zhang, Bolei; Liu, Liang; Zhang, Meng

    2017-04-01

    Severe convective weather is a kind of weather disasters accompanied by heavy rainfall, gust wind, hail, etc. Along with recent developments on remote sensing and numerical modeling, there are high-volume and long-term observational and modeling data accumulated to capture massive severe convective events over particular areas and time periods. With those high-volume and high-variety weather data, most of the existing studies and methods carry out the dynamical laws, cause analysis, potential rule study, and prediction enhancement by utilizing the governing equations from fluid dynamics and thermodynamics. In this study, a key-element mining method is proposed for severe convection prediction based on convolution neural network (CNN). It aims to identify the key areas and key elements from huge amounts of historical weather data including conventional measurements, weather radar, satellite, so as numerical modeling and/or reanalysis data. Under this manner, the machine-learning based method could help the human forecasters on their decision-making on operational weather forecasts on severe convective weathers by extracting key information from the real-time and historical weather big data. In this paper, it first utilizes computer vision technology to complete the data preprocessing work of the meteorological variables. Then, it utilizes the information such as radar map and expert knowledge to annotate all images automatically. And finally, by using CNN model, it cloud analyze and evaluate each weather elements (e.g., particular variables, patterns, features, etc.), and identify key areas of those critical weather elements, then help forecasters quickly screen out the key elements from huge amounts of observation data by current weather conditions. Based on the rich weather measurement and model data (up to 10 years) over Fujian province in China, where the severe convective weathers are very active during the summer months, experimental tests are conducted with

  18. IReport for CNN Transmedia Storytelling On The Brazilian Protests in 2013

    Directory of Open Access Journals (Sweden)

    Geane Alzamora

    2015-12-01

    Full Text Available This study discusses the limits and potentials of the concept of transmedia storytelling to describe citizen coverage of the 2013 protests in Brazil in the collaborative section iReport for CNN on CNN.com. The section is characteristically intermedia because it connects to online social networks and doubles as a monthly television program with the same name. But to what extent could it also be characterized as transmedia? Systematic observation of the citizen coverage between June and July 2013 revealed a restructuring of certain editorial spaces on the site aimed at user-proposed perspectives as well as communicational activity across online social networks; both important aspects for its transmedia characterization. Furthermore, the visible hierarchical differentiation of journalistic reporting puts the transmediatic potential of the collaborative experiment into perspective by reducing the importance of expanding the narrative horizontally despite the study showing regular social scheduling for journalistic coverage as evidence of the dynamics of transmedia.

  19. A CNN based neurobiology inspired approach for retinal image quality assessment.

    Science.gov (United States)

    Mahapatra, Dwarikanath; Roy, Pallab K; Sedai, Suman; Garnavi, Rahil

    2016-08-01

    Retinal image quality assessment (IQA) algorithms use different hand crafted features for training classifiers without considering the working of the human visual system (HVS) which plays an important role in IQA. We propose a convolutional neural network (CNN) based approach that determines image quality using the underlying principles behind the working of the HVS. CNNs provide a principled approach to feature learning and hence higher accuracy in decision making. Experimental results demonstrate the superior performance of our proposed algorithm over competing methods.

  20. Comparison of hand-craft feature based SVM and CNN based deep learning framework for automatic polyp classification.

    Science.gov (United States)

    Younghak Shin; Balasingham, Ilangko

    2017-07-01

    Colonoscopy is a standard method for screening polyps by highly trained physicians. Miss-detected polyps in colonoscopy are potential risk factor for colorectal cancer. In this study, we investigate an automatic polyp classification framework. We aim to compare two different approaches named hand-craft feature method and convolutional neural network (CNN) based deep learning method. Combined shape and color features are used for hand craft feature extraction and support vector machine (SVM) method is adopted for classification. For CNN approach, three convolution and pooling based deep learning framework is used for classification purpose. The proposed framework is evaluated using three public polyp databases. From the experimental results, we have shown that the CNN based deep learning framework shows better classification performance than the hand-craft feature based methods. It achieves over 90% of classification accuracy, sensitivity, specificity and precision.

  1. Respiratory motion correction for free-breathing 3D abdominal MRI using CNN based image registration: a feasibility study.

    Science.gov (United States)

    Lv, Jun; Yang, Ming; Zhang, Jue; Wang, Xiaoying

    2017-12-20

    Free-breathing abdomen imaging requires non-rigid motion registration of unavoidable respiratory motion in 3D under-sampled datasets. In this work, we introduce an image registration method based on the convolutional neural network (CNN) to obtain motion-free abdominal images throughout the respiratory cycle. Abdominal data were acquired from 10 volunteers using a 1.5T MRI system. The respiratory signal was extracted from the central-space spokes, and the acquired data were reordered in 3 bins according to the corresponding breathing signal. Retrospective image reconstruction of the 3 near-motion free respiratory phases was performed using non-Cartesian iterative SENSE reconstruction. Then, we trained a CNN to analyse the spatial transform among the different bins. This network could generate the displacement vector field and be applied to perform registration on unseen image pairs. To demonstrate the feasibility of this registration method, we compared the performance of three different registration approaches for accurate image fusion of 3 bins: non-motion corrected (NMC), LREG and CNN. Visualisation of coronal images indicated that LREG had caused broken blood vessels, while the vessels of the CNN were sharper and more consecutive. As shown in the sagittal view, compared to NMC and CNN, distorted and blurred liver contours were caused by LREG. At the same time, zoom-in axial images presented that the vessels were delineated more clearly by CNN than LREG. The statistical results of the signal-to-noise ratio, visual score, vessel sharpness and registration time over all volunteers were compared among the NMC, LREG and CNN approaches. The SNR indicated that the CNN acquired the best image quality (207.42±96.73), which was better than NMC (116.67±44.70) and LREG (187.93±96.68). The image visual score agreed with SNR, marking CNN (3.85±0.12) as the best, followed by LREG (3.43±0.13) and NMC (2.55±0.09). A vessel sharpness assessment yielded similar values

  2. Low-Grade Glioma Segmentation Based on CNN with Fully Connected CRF

    Directory of Open Access Journals (Sweden)

    Zeju Li

    2017-01-01

    Full Text Available This work proposed a novel automatic three-dimensional (3D magnetic resonance imaging (MRI segmentation method which would be widely used in the clinical diagnosis of the most common and aggressive brain tumor, namely, glioma. The method combined a multipathway convolutional neural network (CNN and fully connected conditional random field (CRF. Firstly, 3D information was introduced into the CNN which makes more accurate recognition of glioma with low contrast. Then, fully connected CRF was added as a postprocessing step which purposed more delicate delineation of glioma boundary. The method was applied to T2flair MRI images of 160 low-grade glioma patients. With 59 cases of data training and manual segmentation as the ground truth, the Dice similarity coefficient (DSC of our method was 0.85 for the test set of 101 MRI images. The results of our method were better than those of another state-of-the-art CNN method, which gained the DSC of 0.76 for the same dataset. It proved that our method could produce better results for the segmentation of low-grade gliomas.

  3. Using CNN Features to Better Understand What Makes Visual Artworks Special

    Science.gov (United States)

    Brachmann, Anselm; Barth, Erhardt; Redies, Christoph

    2017-01-01

    One of the goal of computational aesthetics is to understand what is special about visual artworks. By analyzing image statistics, contemporary methods in computer vision enable researchers to identify properties that distinguish artworks from other (non-art) types of images. Such knowledge will eventually allow inferences with regard to the possible neural mechanisms that underlie aesthetic perception in the human visual system. In the present study, we define measures that capture variances of features of a well-established Convolutional Neural Network (CNN), which was trained on millions of images to recognize objects. Using an image dataset that represents traditional Western, Islamic and Chinese art, as well as various types of non-art images, we show that we need only two variance measures to distinguish between the artworks and non-art images with a high classification accuracy of 93.0%. Results for the first variance measure imply that, in the artworks, the subregions of an image tend to be filled with pictorial elements, to which many diverse CNN features respond (richness of feature responses). Results for the second measure imply that this diversity is tied to a relatively large variability of the responses of individual CNN feature across the subregions of an image. We hypothesize that this combination of richness and variability of CNN feature responses is one of properties that makes traditional visual artworks special. We discuss the possible neural underpinnings of this perceptual quality of artworks and propose to study the same quality also in other types of aesthetic stimuli, such as music and literature. PMID:28588537

  4. Using CNN Features to Better Understand What Makes Visual Artworks Special

    Directory of Open Access Journals (Sweden)

    Anselm Brachmann

    2017-05-01

    Full Text Available One of the goal of computational aesthetics is to understand what is special about visual artworks. By analyzing image statistics, contemporary methods in computer vision enable researchers to identify properties that distinguish artworks from other (non-art types of images. Such knowledge will eventually allow inferences with regard to the possible neural mechanisms that underlie aesthetic perception in the human visual system. In the present study, we define measures that capture variances of features of a well-established Convolutional Neural Network (CNN, which was trained on millions of images to recognize objects. Using an image dataset that represents traditional Western, Islamic and Chinese art, as well as various types of non-art images, we show that we need only two variance measures to distinguish between the artworks and non-art images with a high classification accuracy of 93.0%. Results for the first variance measure imply that, in the artworks, the subregions of an image tend to be filled with pictorial elements, to which many diverse CNN features respond (richness of feature responses. Results for the second measure imply that this diversity is tied to a relatively large variability of the responses of individual CNN feature across the subregions of an image. We hypothesize that this combination of richness and variability of CNN feature responses is one of properties that makes traditional visual artworks special. We discuss the possible neural underpinnings of this perceptual quality of artworks and propose to study the same quality also in other types of aesthetic stimuli, such as music and literature.

  5. Effect of Newsroom Management Styles on Journalists: A Case Study of Two Newspapers.

    Science.gov (United States)

    Gaziano, Cecilie; Coulson, David C.

    A case study of two metropolitan newspapers examined whether there was a relationship between type of newsroom management style--"authoritarian" or "democratic"--and journalists' perceptions of management style and leadership, editors' roles, career goals and job satisfaction, readers' news source contact, and community…

  6. Coorientation in the Newsroom: An Analysis of the News Preferences of Reporters, Editors, and Publishers.

    Science.gov (United States)

    Popovich, Mark

    The question of whether publishers' news preferences affect the performances of editors and reporters is examined in this paper. The first section reviews studies of ways the newsroom environment has affected reporters' role assumptions; it then notes that previous studies have generally been monadic (focusing on only one person) and have provided…

  7. Examining Education and Newsroom Work Experience as Predictors of Communication Students' Perceptions of Journalism Ethics

    Science.gov (United States)

    Detenber, Benjamin H.; Cenite, Mark; Malik, Shelly; Neo, Rachel L.

    2012-01-01

    This study examines education and work experience in newsrooms as predictors of ethical perceptions among communication undergraduates at a large Singaporean university (N = 826). Results indicate that education is associated with ethical ideologies, perceived importance of journalism ethics codes, justifiability of using contentious news…

  8. SAR target recognition and posture estimation using spatial pyramid pooling within CNN

    Science.gov (United States)

    Peng, Lijiang; Liu, Xiaohua; Liu, Ming; Dong, Liquan; Hui, Mei; Zhao, Yuejin

    2018-01-01

    Many convolution neural networks(CNN) architectures have been proposed to strengthen the performance on synthetic aperture radar automatic target recognition (SAR-ATR) and obtained state-of-art results on targets classification on MSTAR database, but few methods concern about the estimation of depression angle and azimuth angle of targets. To get better effect on learning representation of hierarchies of features on both 10-class target classification task and target posture estimation tasks, we propose a new CNN architecture with spatial pyramid pooling(SPP) which can build high hierarchy of features map by dividing the convolved feature maps from finer to coarser levels to aggregate local features of SAR images. Experimental results on MSTAR database show that the proposed architecture can get high recognition accuracy as 99.57% on 10-class target classification task as the most current state-of-art methods, and also get excellent performance on target posture estimation tasks which pays attention to depression angle variety and azimuth angle variety. What's more, the results inspire us the application of deep learning on SAR target posture description.

  9. S-CNN-BASED SHIP DETECTION FROM HIGH-RESOLUTION REMOTE SENSING IMAGES

    Directory of Open Access Journals (Sweden)

    R. Zhang

    2016-06-01

    Full Text Available Reliable ship detection plays an important role in both military and civil fields. However, it makes the task difficult with high-resolution remote sensing images with complex background and various types of ships with different poses, shapes and scales. Related works mostly used gray and shape features to detect ships, which obtain results with poor robustness and efficiency. To detect ships more automatically and robustly, we propose a novel ship detection method based on the convolutional neural networks (CNNs, called SCNN, fed with specifically designed proposals extracted from the ship model combined with an improved saliency detection method. Firstly we creatively propose two ship models, the “V” ship head model and the “||” ship body one, to localize the ship proposals from the line segments extracted from a test image. Next, for offshore ships with relatively small sizes, which cannot be efficiently picked out by the ship models due to the lack of reliable line segments, we propose an improved saliency detection method to find these proposals. Therefore, these two kinds of ship proposals are fed to the trained CNN for robust and efficient detection. Experimental results on a large amount of representative remote sensing images with different kinds of ships with varied poses, shapes and scales demonstrate the efficiency and robustness of our proposed S-CNN-Based ship detector.

  10. A 2D-View Depth Image- and CNN-Based 3D Model Identification Method

    Directory of Open Access Journals (Sweden)

    Yiyu Hong

    2017-09-01

    Full Text Available With the rapid development of three-dimensional (3D technology and an increase in the number of available models, issues with copyright protection of 3D models are inevitable. In this paper, we propose a 2D-view depth image- and convolutional neural network (CNN-based 3D model identification method. To identify a 3D model, we first need an adequate number of the modified versions that could be made by copyright infringers. Then, they can be represented by a number of 2D-view depth images that are captured from evenly distributed vertices on a regular convex polyhedron. Finally, a CNN is trained by these depth images to acquire the capability of identifying the 3D model. The experiment carried out with the dataset of Shape Retrieval Contest 2015 (SHREC’15: Non-Rigid 3D Shape Retrieval shows the practicability of our method, which yields 93.5% accuracy. The effectiveness of the proposed method is demonstrated via evaluation in the latest standard benchmark SHREC’17 Deformable Shape Retrieval with Missing Parts. It clearly shows superior or comparable performance to state-of-the-art methods, shown by the fact that it is in the top three of the 11 participating methods (without counting different runs.

  11. A CNN-Based Method of Vehicle Detection from Aerial Images Using Hard Example Mining

    Directory of Open Access Journals (Sweden)

    Yohei Koga

    2018-01-01

    Full Text Available Recently, deep learning techniques have had a practical role in vehicle detection. While much effort has been spent on applying deep learning to vehicle detection, the effective use of training data has not been thoroughly studied, although it has great potential for improving training results, especially in cases where the training data are sparse. In this paper, we proposed using hard example mining (HEM in the training process of a convolutional neural network (CNN for vehicle detection in aerial images. We applied HEM to stochastic gradient descent (SGD to choose the most informative training data by calculating the loss values in each batch and employing the examples with the largest losses. We picked 100 out of both 500 and 1000 examples for training in one iteration, and we tested different ratios of positive to negative examples in the training data to evaluate how the balance of positive and negative examples would affect the performance. In any case, our method always outperformed the plain SGD. The experimental results for images from New York showed improved performance over a CNN trained in plain SGD where the F1 score of our method was 0.02 higher.

  12. Temporal Classification Error Compensation of Convolutional Neural Network for Traffic Sign Recognition

    Science.gov (United States)

    Yoon, Seungjong; Kim, Eungtae

    2017-02-01

    In this paper, we propose the method that classifies the traffic signs by using Convolutional Neural Network(CNN) and compensates the error rate of CNN using the temporal correlation between adjacent successive frames. Instead of applying a conventional CNN architecture with more layers, Temporal Classification Error Compensation(TCEC) is proposed to improve the error rate in the architecture which has less nodes and layers than a conventional CNN. Experimental results show that the complexity of the proposed method could be reduced by 50% compared with that of the conventional CNN with same layers, and the error rate could be improved by about 3%.

  13. Low-Resource Cross-Domain Product Review Sentiment Classification Based on a CNN with an Auxiliary Large-Scale Corpus

    Directory of Open Access Journals (Sweden)

    Xiaocong Wei

    2017-07-01

    Full Text Available The literature [-5]contains several reports evaluating the abilities of deep neural networks in text transfer learning. To our knowledge, however, there have been few efforts to fully realize the potential of deep neural networks in cross-domain product review sentiment classification. In this paper, we propose a two-layer convolutional neural network (CNN for cross-domain product review sentiment classification (LM-CNN-LB. Transfer learning research into product review sentiment classification based on deep neural networks has been limited by the lack of a large-scale corpus; we sought to remedy this problem using a large-scale auxiliary cross-domain dataset collected from Amazon product reviews. Our proposed framework exhibits the dramatic transferability of deep neural networks for cross-domain product review sentiment classification and achieves state-of-the-art performance. The framework also outperforms complex engineered features used with a non-deep neural network method. The experiments demonstrate that introducing large-scale data from similar domains is an effective way to resolve the lack of training data. The LM-CNN-LB trained on the multi-source related domain dataset outperformed the one trained on a single similar domain.

  14. Anomaly Detection in Nanofibrous Materials by CNN-Based Self-Similarity

    Directory of Open Access Journals (Sweden)

    Paolo Napoletano

    2018-01-01

    Full Text Available Automatic detection and localization of anomalies in nanofibrous materials help to reduce the cost of the production process and the time of the post-production visual inspection process. Amongst all the monitoring methods, those exploiting Scanning Electron Microscope (SEM imaging are the most effective. In this paper, we propose a region-based method for the detection and localization of anomalies in SEM images, based on Convolutional Neural Networks (CNNs and self-similarity. The method evaluates the degree of abnormality of each subregion of an image under consideration by computing a CNN-based visual similarity with respect to a dictionary of anomaly-free subregions belonging to a training set. The proposed method outperforms the state of the art.

  15. Anomaly Detection in Nanofibrous Materials by CNN-Based Self-Similarity.

    Science.gov (United States)

    Napoletano, Paolo; Piccoli, Flavio; Schettini, Raimondo

    2018-01-12

    Automatic detection and localization of anomalies in nanofibrous materials help to reduce the cost of the production process and the time of the post-production visual inspection process. Amongst all the monitoring methods, those exploiting Scanning Electron Microscope (SEM) imaging are the most effective. In this paper, we propose a region-based method for the detection and localization of anomalies in SEM images, based on Convolutional Neural Networks (CNNs) and self-similarity. The method evaluates the degree of abnormality of each subregion of an image under consideration by computing a CNN-based visual similarity with respect to a dictionary of anomaly-free subregions belonging to a training set. The proposed method outperforms the state of the art.

  16. Pairwise domain adaptation module for CNN-based 2-D/3-D registration.

    Science.gov (United States)

    Zheng, Jiannan; Miao, Shun; Jane Wang, Z; Liao, Rui

    2018-04-01

    Accurate two-dimensional to three-dimensional (2-D/3-D) registration of preoperative 3-D data and intraoperative 2-D x-ray images is a key enabler for image-guided therapy. Recent advances in 2-D/3-D registration formulate the problem as a learning-based approach and exploit the modeling power of convolutional neural networks (CNN) to significantly improve the accuracy and efficiency of 2-D/3-D registration. However, for surgery-related applications, collecting a large clinical dataset with accurate annotations for training can be very challenging or impractical. Therefore, deep learning-based 2-D/3-D registration methods are often trained with synthetically generated data, and a performance gap is often observed when testing the trained model on clinical data. We propose a pairwise domain adaptation (PDA) module to adapt the model trained on source domain (i.e., synthetic data) to target domain (i.e., clinical data) by learning domain invariant features with only a few paired real and synthetic data. The PDA module is designed to be flexible for different deep learning-based 2-D/3-D registration frameworks, and it can be plugged into any pretrained CNN model such as a simple Batch-Norm layer. The proposed PDA module has been quantitatively evaluated on two clinical applications using different frameworks of deep networks, demonstrating its significant advantages of generalizability and flexibility for 2-D/3-D medical image registration when a small number of paired real-synthetic data can be obtained.

  17. Can a CNN recognize Catalan diet?

    Science.gov (United States)

    Herruzo, P.; Bolaños, M.; Radeva, P.

    2016-10-01

    Nowadays, we can find several diseases related to the unhealthy diet habits of the population, such as diabetes, obesity, anemia, bulimia and anorexia. In many cases, these diseases are related to the food consumption of people. Mediterranean diet is scientifically known as a healthy diet that helps to prevent many metabolic diseases. In particular, our work focuses on the recognition of Mediterranean food and dishes. The development of this methodology would allow to analise the daily habits of users with wearable cameras, within the topic of lifelogging. By using automatic mechanisms we could build an objective tool for the analysis of the patient's behavior, allowing specialists to discover unhealthy food patterns and understand the user's lifestyle. With the aim to automatically recognize a complete diet, we introduce a challenging multi-labeled dataset related to Mediter-ranean diet called FoodCAT. The first type of label provided consists of 115 food classes with an average of 400 images per dish, and the second one consists of 12 food categories with an average of 3800 pictures per class. This dataset will serve as a basis for the development of automatic diet recognition. In this context, deep learning and more specifically, Convolutional Neural Networks (CNNs), currently are state-of-the-art methods for automatic food recognition. In our work, we compare several architectures for image classification, with the purpose of diet recognition. Applying the best model for recognising food categories, we achieve a top-1 accuracy of 72.29%, and top-5 of 97.07%. In a complete diet recognition of dishes from Mediterranean diet, enlarged with the Food-101 dataset for international dishes recognition, we achieve a top-1 accuracy of 68.07%, and top-5 of 89.53%, for a total of 115+101 food classes.

  18. Detection of Phase Transition via Convolutional Neural Networks

    Science.gov (United States)

    Tanaka, Akinori; Tomiya, Akio

    2017-06-01

    A convolutional neural network (CNN) is designed to study correlation between the temperature and the spin configuration of the two-dimensional Ising model. Our CNN is able to find the characteristic feature of the phase transition without prior knowledge. Also a novel order parameter on the basis of the CNN is introduced to identify the location of the critical temperature; the result is found to be consistent with the exact value.

  19. Is There a Nordic Way? A Swedish Perspective on Achievements and Problems with Gender Equality in Newsrooms

    Directory of Open Access Journals (Sweden)

    Maria Edström

    2011-12-01

    Full Text Available Over the last decades several achievements have emerged in Nordic state societies concerning gender equality, particularly with regard to political representation, salaries, and shared parental leave.In most newsrooms one may find a near equal distribution of women and men working alongside one another. Additionally, in the larger newsrooms of Sweden, there is a gender balance at the manageriallevel. Yet in terms of news content, women remain a minority. By using qualitative and quantitative data from two projects, The Global Media Monitoring Project and The Global Status of Women in the News Media, this article assesses some of the challenges and best practice solutions for gender equality in Scandinavian newsrooms. The major gender discrepancies between newsrooms can often be explained by the level of gender awareness at the societal-level. Further, capable leadership, policies, and gender monitoring seem to benefit a gender balance in the news. National legislation on parental leave and discrimination, additionally, appear to play a key role in creating gender equality in the newsroom.

  20. Evaluation of the traffic parameters in a metropolitan area by fusing visual perceptions and CNN processing of webcam images.

    Science.gov (United States)

    Faro, Alberto; Giordano, Daniela; Spampinato, Concetto

    2008-06-01

    This paper proposes a traffic monitoring architecture based on a high-speed communication network whose nodes are equipped with fuzzy processors and cellular neural network (CNN) embedded systems. It implements a real-time mobility information system where visual human perceptions sent by people working on the territory and video-sequences of traffic taken from webcams are jointly processed to evaluate the fundamental traffic parameters for every street of a metropolitan area. This paper presents the whole methodology for data collection and analysis and compares the accuracy and the processing time of the proposed soft computing techniques with other existing algorithms. Moreover, this paper discusses when and why it is recommended to fuse the visual perceptions of the traffic with the automated measurements taken from the webcams to compute the maximum traveling time that is likely needed to reach any destination in the traffic network.

  1. Lane marking detection based on waveform analysis and CNN

    Science.gov (United States)

    Ye, Yang Yang; Chen, Hou Jin; Hao, Xiao Li

    2017-06-01

    Lane markings detection is a very important part of the ADAS to avoid traffic accidents. In order to obtain accurate lane markings, in this work, a novel and efficient algorithm is proposed, which analyses the waveform generated from the road image after inverse perspective mapping (IPM). The algorithm includes two main stages: the first stage uses an image preprocessing including a CNN to reduce the background and enhance the lane markings. The second stage obtains the waveform of the road image and analyzes the waveform to get lanes. The contribution of this work is that we introduce local and global features of the waveform to detect the lane markings. The results indicate the proposed method is robust in detecting and fitting the lane markings.

  2. CNN-Based Vision Model for Obstacle Avoidance of Mobile Robot

    Directory of Open Access Journals (Sweden)

    Liu Canglong

    2017-01-01

    Full Text Available Exploration in a known or unknown environment for a mobile robot is an essential application. In the paper, we study the mobile robot obstacle avoidance problem in an indoor environment. We present an end-to-end learning model based Convolutional Neural Network (CNN, which takes the raw image obtained from camera as only input. And the method converts directly the raw pixels to steering commands including turn left, turn right and go straight. Training data was collected by a human remotely controlled mobile robot which was manipulated to explore in a structure environment without colliding into obstacles. Our neural network was trained under caffe framework and specific instructions are executed by the Robot Operating System (ROS. We analysis the effect of the datasets from different environments with some marks on training process and several real-time detect experiments were designed. The final test result shows that the accuracy can be improved by increase the marks in a structured environment and our model can get high accuracy on obstacle avoidance for mobile robots.

  3. The Drosophila Pericentrin-like-protein (PLP cooperates with Cnn to maintain the integrity of the outer PCM

    Directory of Open Access Journals (Sweden)

    Jennifer H. Richens

    2015-08-01

    Full Text Available Centrosomes comprise a pair of centrioles surrounded by a matrix of pericentriolar material (PCM. In vertebrate cells, Pericentrin plays an important part in mitotic PCM assembly, but the Drosophila Pericentrin-like protein (PLP appears to have a more minor role in mitotic fly cells. Here we investigate the function of PLP during the rapid mitotic cycles of the early Drosophila embryo. Unexpectedly, we find that PLP is specifically enriched in the outer-most regions of the PCM, where it largely co-localizes with the PCM scaffold protein Cnn. In the absence of PLP the outer PCM appears to be structurally weakened, and it rapidly disperses along the centrosomal microtubules (MTs. As a result, centrosomal MTs are subtly disorganized in embryos lacking PLP, although mitosis is largely unperturbed and these embryos develop and hatch at near-normal rates. Y2H analysis reveals that PLP can potentially form multiple interactions with itself and with the PCM recruiting proteins Asl, Spd-2 and Cnn. A deletion analysis suggests that PLP participates in a complex network of interactions that ultimately help to strengthen the PCM.

  4. Fuzzy-C-Means Clustering Based Segmentation and CNN-Classification for Accurate Segmentation of Lung Nodules

    Science.gov (United States)

    K, Jalal Deen; R, Ganesan; A, Merline

    2017-07-27

    Objective: Accurate segmentation of abnormal and healthy lungs is very crucial for a steadfast computer-aided disease diagnostics. Methods: For this purpose a stack of chest CT scans are processed. In this paper, novel methods are proposed for segmentation of the multimodal grayscale lung CT scan. In the conventional methods using Markov–Gibbs Random Field (MGRF) model the required regions of interest (ROI) are identified. Result: The results of proposed FCM and CNN based process are compared with the results obtained from the conventional method using MGRF model. The results illustrate that the proposed method can able to segment the various kinds of complex multimodal medical images precisely. Conclusion: However, in this paper, to obtain an exact boundary of the regions, every empirical dispersion of the image is computed by Fuzzy C-Means Clustering segmentation. A classification process based on the Convolutional Neural Network (CNN) classifier is accomplished to distinguish the normal tissue and the abnormal tissue. The experimental evaluation is done using the Interstitial Lung Disease (ILD) database. Creative Commons Attribution License

  5. Between Ideals and Practice: Journalism Students Facing Ethical Dilemmas in Online Newsroom Teaching--Lessons From Denmark

    Science.gov (United States)

    Eberholst, Mads Kaemsgaard; Hartley, Jannie Møller; Olsen, Maria Bendix

    2016-01-01

    This article looks at journalism students' experiences in a course that simulates an online newsroom. On the basis of a quantitative survey and more qualitative reflections from the students, we explore the dilemmas that students experience "working" as online journalists and how these are related to broader issues of journalistic…

  6. Evaluating journalism through popular culture : HBO’s The Newsroom and public reflections on the state of the news media

    NARCIS (Netherlands)

    Peters, Chris

    2015-01-01

    While HBO’s The Newsroom presents itself as fictional television, its narrative is driven by critiquing American cable news culture and contemporary journalism ethics. This article analyses popular reflections on the programme to identify what these discourses reveal about public evaluations of the

  7. Evaluating journalism through popular culture : HBO's The Newsroom and public reflections on the state of the news media

    NARCIS (Netherlands)

    Peters, Chris

    While HBO's The Newsroom presents itself as fictional television, its narrative is driven by critiquing American cable news culture and contemporary journalism ethics. This article analyses popular reflections on the programme to identify what these discourses reveal about public evaluations of the

  8. The Use of Negative Reinforcement in the Management of Television Newsrooms in the Southwestern U.S.

    Science.gov (United States)

    Swanson, Douglas J.

    A study highlighted the extent to which TV news directors and subordinates perceived negative reinforcement to be used to help establish working climate in their newsrooms, and examined the differences in their perceptions that working climate affects personal ability to do "best" work on the job. Twenty news directors and 40…

  9. Symbol detection in online handwritten graphics using Faster R-CNN

    OpenAIRE

    Julca-Aguilar, Frank D.; Hirata, Nina S. T.

    2017-01-01

    Symbol detection techniques in online handwritten graphics (e.g. diagrams and mathematical expressions) consist of methods specifically designed for a single graphic type. In this work, we evaluate the Faster R-CNN object detection algorithm as a general method for detection of symbols in handwritten graphics. We evaluate different configurations of the Faster R-CNN method, and point out issues relative to the handwritten nature of the data. Considering the online recognition context, we eval...

  10. Statistical Hypothesis Testing using CNN Features for Synthesis of Adversarial Counterexamples to Human and Object Detection Vision Systems

    Energy Technology Data Exchange (ETDEWEB)

    Raj, Sunny [Univ. of Central Florida, Orlando, FL (United States); Jha, Sumit Kumar [Univ. of Central Florida, Orlando, FL (United States); Pullum, Laura L. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Ramanathan, Arvind [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

    2017-05-01

    Validating the correctness of human detection vision systems is crucial for safety applications such as pedestrian collision avoidance in autonomous vehicles. The enormous space of possible inputs to such an intelligent system makes it difficult to design test cases for such systems. In this report, we present our tool MAYA that uses an error model derived from a convolutional neural network (CNN) to explore the space of images similar to a given input image, and then tests the correctness of a given human or object detection system on such perturbed images. We demonstrate the capability of our tool on the pre-trained Histogram-of-Oriented-Gradients (HOG) human detection algorithm implemented in the popular OpenCV toolset and the Caffe object detection system pre-trained on the ImageNet benchmark. Our tool may serve as a testing resource for the designers of intelligent human and object detection systems.

  11. Synthesis and reactivity of tantalum alkylidene complexes containing the C,N,N'-chelating aryldiamine ligand [C6H4(CH2N(Me)CH2CH2NMe2)-2- (CNN). X-ray structurs of [TaCl2(=CH-t-Bu) (CNN)], [Ta{CH2)3-1,3}(CNN)(O-t-Bu)2], and [Ta(CNN)(O-t-Bu)2(H2C=CH2)

    NARCIS (Netherlands)

    Koten, G. van; Rietveld, M.H.P.; Teunissen, Wendy; Hagen, H.; Water, L. van de; Grove, D.M.; Veldman, N.; Spek, A.L.

    1997-01-01

    The potentially C,N,N'-chelating anionic aryldiamine ligand [C6H4(CH2N(Me)CH2CH2NMe2)-2]- (CNN) has been employed in the preparation of six-coordinate Ta(V) alkylidene complexes. The new dichloro alkylidene complex [TaCl2(=CH-t-Bu)(CNN)], 2, prepared from [TaCl3(=CH-t-Bu)(THF)2] and [Li(CNN)]2, 1,

  12. Cellular Neural Networks: A genetic algorithm for parameters optimization in artificial vision applications

    Energy Technology Data Exchange (ETDEWEB)

    Taraglio, S. [ENEA, Centro Ricerche Casaccia, Rome (Italy). Dipt. Innovazione; Zanela, A. [Rome Univ. `La Sapienza` (Italy). Dipt. di Fisica

    1997-03-01

    An optimization method for some of the CNN`s (Cellular Neural Network) parameters, based on evolutionary strategies, is proposed. The new class of feedback template found is more effective in extracting features from the images that an autonomous vehicle acquires, than in the previous CNN`s literature.

  13. Witnessing images of extreme violence: a psychological study of journalists in the newsroom.

    Science.gov (United States)

    Feinstein, Anthony; Audet, Blair; Waknine, Elizabeth

    2014-08-01

    User Generated Content - photos and videos submitted to newsrooms by the public - has become a prominent source of information for news organisations. Journalists working with uncensored material can frequently witness disturbing images for prolonged periods. How this might affect their psychological health is not known and it is the focus of this study. Descriptive, exploratory. The newsrooms of three international news organisations. One hundred and sixteen journalists working with User Generated Content material. Psychometric data included the re-experiencing, avoidance and autonomic arousal indices of posttraumatic stress disorder (Impact of Event Scale-revised), depression (Beck Depression Inventory-II; BDI-II), a measure of psychological distress (GHQ-28), the latter comprising four subscales measuring somatisation, anxiety, social dysfunction and depression, and mean weekly alcohol consumption divided according to gender. Regression analyses revealed that frequent (i.e. daily) exposure to violent images independently predicted higher scores on all indices of the Impact of Event Scale-revised, the BDI-II and the somatic and anxiety subscales of the GHQ-28. Exposure per shift only predicted scores on the intrusion subscale of the Impact of Event Scale-revised. The present study, the first of its kind, suggests that frequency rather than duration of exposure to images of graphic violence is more emotionally distressing to journalists working with User Generated Content material. Given that good journalism depends on healthy journalists, news organisations will need to look anew at what can be done to offset the risks inherent in viewing User Generated Content material. Our findings, in need of replication, suggest that reducing the frequency of exposure may be one way to go.

  14. Drug-Drug Interaction Extraction via Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Shengyu Liu

    2016-01-01

    Full Text Available Drug-drug interaction (DDI extraction as a typical relation extraction task in natural language processing (NLP has always attracted great attention. Most state-of-the-art DDI extraction systems are based on support vector machines (SVM with a large number of manually defined features. Recently, convolutional neural networks (CNN, a robust machine learning method which almost does not need manually defined features, has exhibited great potential for many NLP tasks. It is worth employing CNN for DDI extraction, which has never been investigated. We proposed a CNN-based method for DDI extraction. Experiments conducted on the 2013 DDIExtraction challenge corpus demonstrate that CNN is a good choice for DDI extraction. The CNN-based DDI extraction method achieves an F-score of 69.75%, which outperforms the existing best performing method by 2.75%.

  15. Cellular Neural Networks for NP-Hard Optimization

    Directory of Open Access Journals (Sweden)

    Mária Ercsey-Ravasz

    2009-02-01

    Full Text Available A cellular neural/nonlinear network (CNN is used for NP-hard optimization. We prove that a CNN in which the parameters of all cells can be separately controlled is the analog correspondent of a two-dimensional Ising-type (Edwards-Anderson spin-glass system. Using the properties of CNN, we show that one single operation (template always yields a local minimum of the spin-glass energy function. This way, a very fast optimization method, similar to simulated annealing, can be built. Estimating the simulation time needed on CNN-based computers, and comparing it with the time needed on normal digital computers using the simulated annealing algorithm, the results are astonishing. CNN computers could be faster than digital computers already at 10×10 lattice sizes. The local control of the template parameters was already partially realized on some of the hardwares, we think this study could further motivate their development in this direction.

  16. Car Detection from Low-Altitude UAV Imagery with the Faster R-CNN

    Directory of Open Access Journals (Sweden)

    Yongzheng Xu

    2017-01-01

    Full Text Available UAV based traffic monitoring holds distinct advantages over traditional traffic sensors, such as loop detectors, as UAVs have higher mobility, wider field of view, and less impact on the observed traffic. For traffic monitoring from UAV images, the essential but challenging task is vehicle detection. This paper extends the framework of Faster R-CNN for car detection from low-altitude UAV imagery captured over signalized intersections. Experimental results show that Faster R-CNN can achieve promising car detection results compared with other methods. Our tests further demonstrate that Faster R-CNN is robust to illumination changes and cars’ in-plane rotation. Besides, the detection speed of Faster R-CNN is insensitive to the detection load, that is, the number of detected cars in a frame; therefore, the detection speed is almost constant for each frame. In addition, our tests show that Faster R-CNN holds great potential for parking lot car detection. This paper tries to guide the readers to choose the best vehicle detection framework according to their applications. Future research will be focusing on expanding the current framework to detect other transportation modes such as buses, trucks, motorcycles, and bicycles.

  17. Learning Oriented Region-based Convolutional Neural Networks for Building Detection in Satellite Remote Sensing Images

    Directory of Open Access Journals (Sweden)

    C. Chen

    2017-05-01

    Full Text Available The automated building detection in aerial images is a fundamental problem encountered in aerial and satellite images analysis. Recently, thanks to the advances in feature descriptions, Region-based CNN model (R-CNN for object detection is receiving an increasing attention. Despite the excellent performance in object detection, it is problematic to directly leverage the features of R-CNN model for building detection in single aerial image. As we know, the single aerial image is in vertical view and the buildings possess significant directional feature. However, in R-CNN model, direction of the building is ignored and the detection results are represented by horizontal rectangles. For this reason, the detection results with horizontal rectangle cannot describe the building precisely. To address this problem, in this paper, we proposed a novel model with a key feature related to orientation, namely, Oriented R-CNN (OR-CNN. Our contributions are mainly in the following two aspects: 1 Introducing a new oriented layer network for detecting the rotation angle of building on the basis of the successful VGG-net R-CNN model; 2 the oriented rectangle is proposed to leverage the powerful R-CNN for remote-sensing building detection. In experiments, we establish a complete and bran-new data set for training our oriented R-CNN model and comprehensively evaluate the proposed method on a publicly available building detection data set. We demonstrate State-of-the-art results compared with the previous baseline methods.

  18. A method for medulloblastoma tumor differentiation based on convolutional neural networks and transfer learning

    Science.gov (United States)

    Cruz-Roa, Angel; Arévalo, John; Judkins, Alexander; Madabhushi, Anant; González, Fabio

    2015-12-01

    Convolutional neural networks (CNN) have been very successful at addressing different computer vision tasks thanks to their ability to learn image representations directly from large amounts of labeled data. Features learned from a dataset can be used to represent images from a different dataset via an approach called transfer learning. In this paper we apply transfer learning to the challenging task of medulloblastoma tumor differentiation. We compare two different CNN models which were previously trained in two different domains (natural and histopathology images). The first CNN is a state-of-the-art approach in computer vision, a large and deep CNN with 16-layers, Visual Geometry Group (VGG) CNN. The second (IBCa-CNN) is a 2-layer CNN trained for invasive breast cancer tumor classification. Both CNNs are used as visual feature extractors of histopathology image regions of anaplastic and non-anaplastic medulloblastoma tumor from digitized whole-slide images. The features from the two models are used, separately, to train a softmax classifier to discriminate between anaplastic and non-anaplastic medulloblastoma image regions. Experimental results show that the transfer learning approach produce competitive results in comparison with the state of the art approaches for IBCa detection. Results also show that features extracted from the IBCa-CNN have better performance in comparison with features extracted from the VGG-CNN. The former obtains 89.8% while the latter obtains 76.6% in terms of average accuracy.

  19. Learning Oriented Region-based Convolutional Neural Networks for Building Detection in Satellite Remote Sensing Images

    Science.gov (United States)

    Chen, C.; Gong, W.; Hu, Y.; Chen, Y.; Ding, Y.

    2017-05-01

    The automated building detection in aerial images is a fundamental problem encountered in aerial and satellite images analysis. Recently, thanks to the advances in feature descriptions, Region-based CNN model (R-CNN) for object detection is receiving an increasing attention. Despite the excellent performance in object detection, it is problematic to directly leverage the features of R-CNN model for building detection in single aerial image. As we know, the single aerial image is in vertical view and the buildings possess significant directional feature. However, in R-CNN model, direction of the building is ignored and the detection results are represented by horizontal rectangles. For this reason, the detection results with horizontal rectangle cannot describe the building precisely. To address this problem, in this paper, we proposed a novel model with a key feature related to orientation, namely, Oriented R-CNN (OR-CNN). Our contributions are mainly in the following two aspects: 1) Introducing a new oriented layer network for detecting the rotation angle of building on the basis of the successful VGG-net R-CNN model; 2) the oriented rectangle is proposed to leverage the powerful R-CNN for remote-sensing building detection. In experiments, we establish a complete and bran-new data set for training our oriented R-CNN model and comprehensively evaluate the proposed method on a publicly available building detection data set. We demonstrate State-of-the-art results compared with the previous baseline methods.

  20. Convolutional Neural Networks for Font Classification

    OpenAIRE

    Tensmeyer, Chris; Saunders, Daniel; Martinez, Tony

    2017-01-01

    Classifying pages or text lines into font categories aids transcription because single font Optical Character Recognition (OCR) is generally more accurate than omni-font OCR. We present a simple framework based on Convolutional Neural Networks (CNNs), where a CNN is trained to classify small patches of text into predefined font classes. To classify page or line images, we average the CNN predictions over densely extracted patches. We show that this method achieves state-of-the-art performance...

  1. Cost-Effective Class-Imbalance Aware CNN for Vehicle Localization and Categorization in High Resolution Aerial Images

    Directory of Open Access Journals (Sweden)

    Feimo Li

    2017-05-01

    Full Text Available Joint vehicle localization and categorization in high resolution aerial images can provide useful information for applications such as traffic flow structure analysis. To maintain sufficient features to recognize small-scaled vehicles, a regions with convolutional neural network features (R-CNN -like detection structure is employed. In this setting, cascaded localization error can be averted by equally treating the negatives and differently typed positives as a multi-class classification task, but the problem of class-imbalance remains. To address this issue, a cost-effective network extension scheme is proposed. In it, the correlated convolution and connection costs during extension are reduced by feature map selection and bi-partite main-side network construction, which are realized with the assistance of a novel feature map class-importance measurement and a new class-imbalance sensitive main-side loss function. By using an image classification dataset established from a set of traditional real-colored aerial images with 0.13 m ground sampling distance which are taken from the height of 1000 m by an imaging system composed of non-metric cameras, the effectiveness of the proposed network extension is verified by comparing with its similarly shaped strong counter-parts. Experiments show an equivalent or better performance, while requiring the least parameter and memory overheads are required.

  2. Cellular neural networks for the stereo matching problem

    Energy Technology Data Exchange (ETDEWEB)

    Taraglio, S. [ENEA, Centro Ricerche Casaccia, Rome (Italy). Dipt. Innovazione; Zanela, A. [Rome Univ. `La Sapienza` (Italy). Dipt. di Fisica

    1997-03-01

    The applicability of the Cellular Neural Network (CNN) paradigm to the problem of recovering information on the tridimensional structure of the environment is investigated. The approach proposed is the stereo matching of video images. The starting point of this work is the Zhou-Chellappa neural network implementation for the same problem. The CNN based system we present here yields the same results as the previous approach, but without the many existing drawbacks.

  3. Automated assessment of breast tissue density in non-contrast 3D CT images without image segmentation based on a deep CNN

    Science.gov (United States)

    Zhou, Xiangrong; Kano, Takuya; Koyasu, Hiromi; Li, Shuo; Zhou, Xinxin; Hara, Takeshi; Matsuo, Masayuki; Fujita, Hiroshi

    2017-03-01

    This paper describes a novel approach for the automatic assessment of breast density in non-contrast three-dimensional computed tomography (3D CT) images. The proposed approach trains and uses a deep convolutional neural network (CNN) from scratch to classify breast tissue density directly from CT images without segmenting the anatomical structures, which creates a bottleneck in conventional approaches. Our scheme determines breast density in a 3D breast region by decomposing the 3D region into several radial 2D-sections from the nipple, and measuring the distribution of breast tissue densities on each 2D section from different orientations. The whole scheme is designed as a compact network without the need for post-processing and provides high robustness and computational efficiency in clinical settings. We applied this scheme to a dataset of 463 non-contrast CT scans obtained from 30- to 45-year-old-women in Japan. The density of breast tissue in each CT scan was assigned to one of four categories (glandular tissue within the breast 75%) by a radiologist as ground truth. We used 405 CT scans for training a deep CNN and the remaining 58 CT scans for testing the performance. The experimental results demonstrated that the findings of the proposed approach and those of the radiologist were the same in 72% of the CT scans among the training samples and 76% among the testing samples. These results demonstrate the potential use of deep CNN for assessing breast tissue density in non-contrast 3D CT images.

  4. Vehicle Color Recognition with Vehicle-Color Saliency Detection and Dual-Orientational Dimensionality Reduction of CNN Deep Features

    Science.gov (United States)

    Zhang, Qiang; Li, Jiafeng; Zhuo, Li; Zhang, Hui; Li, Xiaoguang

    2017-12-01

    Color is one of the most stable attributes of vehicles and often used as a valuable cue in some important applications. Various complex environmental factors, such as illumination, weather, noise and etc., result in the visual characteristics of the vehicle color being obvious diversity. Vehicle color recognition in complex environments has been a challenging task. The state-of-the-arts methods roughly take the whole image for color recognition, but many parts of the images such as car windows; wheels and background contain no color information, which will have negative impact on the recognition accuracy. In this paper, a novel vehicle color recognition method using local vehicle-color saliency detection and dual-orientational dimensionality reduction of convolutional neural network (CNN) deep features has been proposed. The novelty of the proposed method includes two parts: (1) a local vehicle-color saliency detection method has been proposed to determine the vehicle color region of the vehicle image and exclude the influence of non-color regions on the recognition accuracy; (2) dual-orientational dimensionality reduction strategy has been designed to greatly reduce the dimensionality of deep features that are learnt from CNN, which will greatly mitigate the storage and computational burden of the subsequent processing, while improving the recognition accuracy. Furthermore, linear support vector machine is adopted as the classifier to train the dimensionality reduced features to obtain the recognition model. The experimental results on public dataset demonstrate that the proposed method can achieve superior recognition performance over the state-of-the-arts methods.

  5. Video-based convolutional neural networks for activity recognition from robot-centric videos

    Science.gov (United States)

    Ryoo, M. S.; Matthies, Larry

    2016-05-01

    In this evaluation paper, we discuss convolutional neural network (CNN)-based approaches for human activity recognition. In particular, we investigate CNN architectures designed to capture temporal information in videos and their applications to the human activity recognition problem. There have been multiple previous works to use CNN-features for videos. These include CNNs using 3-D XYT convolutional filters, CNNs using pooling operations on top of per-frame image-based CNN descriptors, and recurrent neural networks to learn temporal changes in per-frame CNN descriptors. We experimentally compare some of these different representatives CNNs while using first-person human activity videos. We especially focus on videos from a robots viewpoint, captured during its operations and human-robot interactions.

  6. Convolutional Neural Networks with Batch Normalization for Classifying Hi-hat, Snare, and Bass Percussion Sound Samples

    DEFF Research Database (Denmark)

    Gajhede, Nicolai; Beck, Oliver; Purwins, Hendrik

    2016-01-01

    After having revolutionized image and speech processing, convolu- tional neural networks (CNN) are now starting to become more and more successful in music information retrieval as well. We compare four CNN types for classifying a dataset of more than 3000 acoustic and synthesized samples...

  7. Combining high-speed SVM learning with CNN feature encoding for real-time target recognition in high-definition video for ISR missions

    Science.gov (United States)

    Kroll, Christine; von der Werth, Monika; Leuck, Holger; Stahl, Christoph; Schertler, Klaus

    2017-05-01

    For Intelligence, Surveillance, Reconnaissance (ISR) missions of manned and unmanned air systems typical electrooptical payloads provide high-definition video data which has to be exploited with respect to relevant ground targets in real-time by automatic/assisted target recognition software. Airbus Defence and Space is developing required technologies for real-time sensor exploitation since years and has combined the latest advances of Deep Convolutional Neural Networks (CNN) with a proprietary high-speed Support Vector Machine (SVM) learning method into a powerful object recognition system with impressive results on relevant high-definition video scenes compared to conventional target recognition approaches. This paper describes the principal requirements for real-time target recognition in high-definition video for ISR missions and the Airbus approach of combining an invariant feature extraction using pre-trained CNNs and the high-speed training and classification ability of a novel frequency-domain SVM training method. The frequency-domain approach allows for a highly optimized implementation for General Purpose Computation on a Graphics Processing Unit (GPGPU) and also an efficient training of large training samples. The selected CNN which is pre-trained only once on domain-extrinsic data reveals a highly invariant feature extraction. This allows for a significantly reduced adaptation and training of the target recognition method for new target classes and mission scenarios. A comprehensive training and test dataset was defined and prepared using relevant high-definition airborne video sequences. The assessment concept is explained and performance results are given using the established precision-recall diagrams, average precision and runtime figures on representative test data. A comparison to legacy target recognition approaches shows the impressive performance increase by the proposed CNN+SVM machine-learning approach and the capability of real-time high

  8. Human Parsing with Contextualized Convolutional Neural Network.

    Science.gov (United States)

    Liang, Xiaodan; Xu, Chunyan; Shen, Xiaohui; Yang, Jianchao; Tang, Jinhui; Lin, Liang; Yan, Shuicheng

    2016-03-02

    In this work, we address the human parsing task with a novel Contextualized Convolutional Neural Network (Co-CNN) architecture, which well integrates the cross-layer context, global image-level context, semantic edge context, within-super-pixel context and cross-super-pixel neighborhood context into a unified network. Given an input human image, Co-CNN produces the pixel-wise categorization in an end-to-end way. First, the cross-layer context is captured by our basic local-to-global-to-local structure, which hierarchically combines the global semantic information and the local fine details across different convolutional layers. Second, the global image-level label prediction is used as an auxiliary objective in the intermediate layer of the Co-CNN, and its outputs are further used for guiding the feature learning in subsequent convolutional layers to leverage the global imagelevel context. Third, semantic edge context is further incorporated into Co-CNN, where the high-level semantic boundaries are leveraged to guide pixel-wise labeling. Finally, to further utilize the local super-pixel contexts, the within-super-pixel smoothing and cross-super-pixel neighbourhood voting are formulated as natural sub-components of the Co-CNN to achieve the local label consistency in both training and testing process. Comprehensive evaluations on two public datasets well demonstrate the significant superiority of our Co-CNN over other state-of-the-arts for human parsing. In particular, the F-1 score on the large dataset [1] reaches 81:72% by Co-CNN, significantly higher than 62:81% and 64:38% by the state-of-the-art algorithms, MCNN [2] and ATR [1], respectively. By utilizing our newly collected large dataset for training, our Co-CNN can achieve 85:36% in F-1 score.

  9. A novel memristive cellular neural network with time-variant templates

    Directory of Open Access Journals (Sweden)

    Xiaofang Hu

    2016-03-01

    Full Text Available A cellular neural network (CNN is a massively parallel analog array processor capable of solving various complex processing problems by using specific templates that characterize the synaptic connections. The hardware implementation and applications of CNN have attracted a great deal of attention. Recently, memristors with nanometer-scale and variable gradual conductance have been exploited to make compact and programmable electric synapses. This paper proposes and studies a novel memristive CNN (Mt-CNN with time-variant templates realized by memristor crossbar synaptic circuits. The template parameters are estimated analytically. The Mt-CNN provides a promising solution to hardware realization of real-time template updating processes, which can be used to effectively deal with various complicated problems of cascaded processing. Its effectiveness and advantages are demonstrated by practical examples of edge detection on noisy images.

  10. The global village in a local context. Implementing global awareness as a managerial competency within South Africa's multicultural mainstream media newsrooms

    Directory of Open Access Journals (Sweden)

    E. Steyn

    2006-12-01

    Full Text Available Purpose: As part of a national research survey into the importance and implementation of six managerial competencies, this article aims to investigate the importance a national sample of reporters and first-line newsroom managers in South Africa's mainstream media attach to global awareness as a managerial competency. It also aims to establish gaps between the importance attached to and current implementation thereof by the latter. Design/Methodology/Approach: Qualitative and quantitative research designs were combined to obtain the most comprehensive view on the research problem. Quantitative data was compiled through self-administered questionnaires among first-line newsroom managers and reporters employed by the country's mainstream media. Qualitative data was obtained through semi-structured interviews and observational research. These sets of data were combined triangularly to improve validity and reliability. Quantitative data was analysed through factor analysis and effect size analysis, while qualitative data was analysed through qualitative content analysis. Findings: It was found that both respondent groups perceive first-line newsroom managers unable to implement the skills associated with the global awareness competency (given the importance they attach to it. While in some cases first-line newsroom managers themselves were more aware of their shortcomings, reporters highlighted other instances where they perceive their superiors unable to perform as expected. Implications: Given the challenges associated with globalisation, media managers need skills to identify and realise the impact of national and international changes on their business activities. South African media managers must also identify and address the challenges associated with the multilingual and multicultural backgrounds of their newsroom staff. Originality/Value: The dimensions of global awareness as a managerial competency are rooted in general management theory

  11. The global village in a local context. Implementing global awareness as a managerial competency within South Africa's multicultural mainstream media newsrooms

    Directory of Open Access Journals (Sweden)

    E. Steyn

    2006-12-01

    Full Text Available Purpose: As part of a national research survey into the importance and implementation of six managerial competencies, this article aims to investigate the importance a national sample of reporters and first-line newsroom managers in South Africa's mainstream media attach to global awareness as a managerial competency. It also aims to establish gaps between the importance attached to and current implementation thereof by the latter. Design/Methodology/Approach: Qualitative and quantitative research designs were combined to obtain the most comprehensive view on the research problem. Quantitative data was compiled through self-administered questionnaires among first-line newsroom managers and reporters employed by the country's mainstream media. Qualitative data was obtained through semi-structured interviews and observational research. These sets of data were combined triangularly to improve validity and reliability. Quantitative data was analysed through factor analysis and effect size analysis, while qualitative data was analysed through qualitative content analysis.Findings: It was found that both respondent groups perceive first-line newsroom managers unable to implement the skills associated with the global awareness competency (given the importance they attach to it. While in some cases first-line newsroom managers themselves were more aware of their shortcomings, reporters highlighted other instances where they perceive their superiors unable to perform as expected. Implications: Given the challenges associated with globalisation, media managers need skills to identify and realise the impact of national and international changes on their business activities. South African media managers must also identify and address the challenges associated with the multilingual and multicultural backgrounds of their newsroom staff. Originality/Value: The dimensions of global awareness as a managerial competency are rooted in general management theory. In

  12. Effective Use of Word Order for Text Categorization with Convolutional Neural Networks

    OpenAIRE

    Johnson, Rie; Zhang, Tong

    2014-01-01

    Convolutional neural network (CNN) is a neural network that can make use of the internal structure of data such as the 2D structure of image data. This paper studies CNN on text categorization to exploit the 1D structure (namely, word order) of text data for accurate prediction. Instead of using low-dimensional word vectors as input as is often done, we directly apply CNN to high-dimensional text data, which leads to directly learning embedding of small text regions for use in classification....

  13. Convolutional neural network architectures for predicting DNA–protein binding

    Science.gov (United States)

    Zeng, Haoyang; Edwards, Matthew D.; Liu, Ge; Gifford, David K.

    2016-01-01

    Motivation: Convolutional neural networks (CNN) have outperformed conventional methods in modeling the sequence specificity of DNA–protein binding. Yet inappropriate CNN architectures can yield poorer performance than simpler models. Thus an in-depth understanding of how to match CNN architecture to a given task is needed to fully harness the power of CNNs for computational biology applications. Results: We present a systematic exploration of CNN architectures for predicting DNA sequence binding using a large compendium of transcription factor datasets. We identify the best-performing architectures by varying CNN width, depth and pooling designs. We find that adding convolutional kernels to a network is important for motif-based tasks. We show the benefits of CNNs in learning rich higher-order sequence features, such as secondary motifs and local sequence context, by comparing network performance on multiple modeling tasks ranging in difficulty. We also demonstrate how careful construction of sequence benchmark datasets, using approaches that control potentially confounding effects like positional or motif strength bias, is critical in making fair comparisons between competing methods. We explore how to establish the sufficiency of training data for these learning tasks, and we have created a flexible cloud-based framework that permits the rapid exploration of alternative neural network architectures for problems in computational biology. Availability and Implementation: All the models analyzed are available at http://cnn.csail.mit.edu. Contact: gifford@mit.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27307608

  14. Convolutional neural network architectures for predicting DNA-protein binding.

    Science.gov (United States)

    Zeng, Haoyang; Edwards, Matthew D; Liu, Ge; Gifford, David K

    2016-06-15

    Convolutional neural networks (CNN) have outperformed conventional methods in modeling the sequence specificity of DNA-protein binding. Yet inappropriate CNN architectures can yield poorer performance than simpler models. Thus an in-depth understanding of how to match CNN architecture to a given task is needed to fully harness the power of CNNs for computational biology applications. We present a systematic exploration of CNN architectures for predicting DNA sequence binding using a large compendium of transcription factor datasets. We identify the best-performing architectures by varying CNN width, depth and pooling designs. We find that adding convolutional kernels to a network is important for motif-based tasks. We show the benefits of CNNs in learning rich higher-order sequence features, such as secondary motifs and local sequence context, by comparing network performance on multiple modeling tasks ranging in difficulty. We also demonstrate how careful construction of sequence benchmark datasets, using approaches that control potentially confounding effects like positional or motif strength bias, is critical in making fair comparisons between competing methods. We explore how to establish the sufficiency of training data for these learning tasks, and we have created a flexible cloud-based framework that permits the rapid exploration of alternative neural network architectures for problems in computational biology. All the models analyzed are available at http://cnn.csail.mit.edu gifford@mit.edu Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press.

  15. Classification of Microcalcifications for the Diagnosis of Breast Cancer Using Artificial Neural Networks

    National Research Council Canada - National Science Library

    Wu, Yuzheng

    1997-01-01

    .... A convolution neural network (CNN) was employed to classify benign and malignant microcalcifications in the radiographs of pathological specimen that were digitized at a high resolution of 21 microns x 21 microns...

  16. Feature Acquisition and Analysis for Facial Expression Recognition Using Convolutional Neural Networks

    National Research Council Canada - National Science Library

    Taiki Nishime; Satoshi Endo; Naruaki Toma; Koji Yamada; Yuhei Akamine

    2017-01-01

    .... Therefore, it is difficult to evaluate the reliability of the result from recognition accuracy alone, and the analysis for explaining the result and feature learned by Convolutional Neural Networks (CNN...

  17. Explaining Deep Convolutional Neural Networks on Music Classification

    OpenAIRE

    Choi, Keunwoo; Fazekas, George; Sandler, Mark

    2016-01-01

    Deep convolutional neural networks (CNNs) have been actively adopted in the field of music information retrieval, e.g. genre classification, mood detection, and chord recognition. However, the process of learning and prediction is little understood, particularly when it is applied to spectrograms. We introduce auralisation of a CNN to understand its underlying mechanism, which is based on a deconvolution procedure introduced in [2]. Auralisation of a CNN is converting the learned convolutiona...

  18. Histopathological Breast-Image Classification Using Local and Frequency Domains by Convolutional Neural Network

    Directory of Open Access Journals (Sweden)

    Abdullah-Al Nahid

    2018-01-01

    Full Text Available Identification of the malignancy of tissues from Histopathological images has always been an issue of concern to doctors and radiologists. This task is time-consuming, tedious and moreover very challenging. Success in finding malignancy from Histopathological images primarily depends on long-term experience, though sometimes experts disagree on their decisions. However, Computer Aided Diagnosis (CAD techniques help the radiologist to give a second opinion that can increase the reliability of the radiologist’s decision. Among the different image analysis techniques, classification of the images has always been a challenging task. Due to the intense complexity of biomedical images, it is always very challenging to provide a reliable decision about an image. The state-of-the-art Convolutional Neural Network (CNN technique has had great success in natural image classification. Utilizing advanced engineering techniques along with the CNN, in this paper, we have classified a set of Histopathological Breast-Cancer (BC images utilizing a state-of-the-art CNN model containing a residual block. Conventional CNN operation takes raw images as input and extracts the global features; however, the object oriented local features also contain significant information—for example, the Local Binary Pattern (LBP represents the effective textural information, Histogram represent the pixel strength distribution, Contourlet Transform (CT gives much detailed information about the smoothness about the edges, and Discrete Fourier Transform (DFT derives frequency-domain information from the image. Utilizing these advantages, along with our proposed novel CNN model, we have examined the performance of the novel CNN model as Histopathological image classifier. To do so, we have introduced five cases: (a Convolutional Neural Network Raw Image (CNN-I; (b Convolutional Neural Network CT Histogram (CNN-CH; (c Convolutional Neural Network CT LBP (CNN-CL; (d Convolutional

  19. Mobile robots exploration through cnn-based reinforcement learning.

    Science.gov (United States)

    Tai, Lei; Liu, Ming

    2016-01-01

    Exploration in an unknown environment is an elemental application for mobile robots. In this paper, we outlined a reinforcement learning method aiming for solving the exploration problem in a corridor environment. The learning model took the depth image from an RGB-D sensor as the only input. The feature representation of the depth image was extracted through a pre-trained convolutional-neural-networks model. Based on the recent success of deep Q-network on artificial intelligence, the robot controller achieved the exploration and obstacle avoidance abilities in several different simulated environments. It is the first time that the reinforcement learning is used to build an exploration strategy for mobile robots through raw sensor information.

  20. R-PHOC: Segmentation-Free Word Spotting using CNN

    OpenAIRE

    Ghosh, Suman; Valveny, Ernest

    2017-01-01

    This paper proposes a region based convolutional neural network for segmentation-free word spotting. Our net- work takes as input an image and a set of word candidate bound- ing boxes and embeds all bounding boxes into an embedding space, where word spotting can be casted as a simple nearest neighbour search between the query representation and each of the candidate bounding boxes. We make use of PHOC embedding as it has previously achieved significant success in segmentation- based word spot...

  1. a Rough Set Decision Tree Based Mlp-Cnn for Very High Resolution Remotely Sensed Image Classification

    Science.gov (United States)

    Zhang, C.; Pan, X.; Zhang, S. Q.; Li, H. P.; Atkinson, P. M.

    2017-09-01

    Recent advances in remote sensing have witnessed a great amount of very high resolution (VHR) images acquired at sub-metre spatial resolution. These VHR remotely sensed data has post enormous challenges in processing, analysing and classifying them effectively due to the high spatial complexity and heterogeneity. Although many computer-aid classification methods that based on machine learning approaches have been developed over the past decades, most of them are developed toward pixel level spectral differentiation, e.g. Multi-Layer Perceptron (MLP), which are unable to exploit abundant spatial details within VHR images. This paper introduced a rough set model as a general framework to objectively characterize the uncertainty in CNN classification results, and further partition them into correctness and incorrectness on the map. The correct classification regions of CNN were trusted and maintained, whereas the misclassification areas were reclassified using a decision tree with both CNN and MLP. The effectiveness of the proposed rough set decision tree based MLP-CNN was tested using an urban area at Bournemouth, United Kingdom. The MLP-CNN, well capturing the complementarity between CNN and MLP through the rough set based decision tree, achieved the best classification performance both visually and numerically. Therefore, this research paves the way to achieve fully automatic and effective VHR image classification.

  2. A ROUGH SET DECISION TREE BASED MLP-CNN FOR VERY HIGH RESOLUTION REMOTELY SENSED IMAGE CLASSIFICATION

    Directory of Open Access Journals (Sweden)

    C. Zhang

    2017-09-01

    Full Text Available Recent advances in remote sensing have witnessed a great amount of very high resolution (VHR images acquired at sub-metre spatial resolution. These VHR remotely sensed data has post enormous challenges in processing, analysing and classifying them effectively due to the high spatial complexity and heterogeneity. Although many computer-aid classification methods that based on machine learning approaches have been developed over the past decades, most of them are developed toward pixel level spectral differentiation, e.g. Multi-Layer Perceptron (MLP, which are unable to exploit abundant spatial details within VHR images. This paper introduced a rough set model as a general framework to objectively characterize the uncertainty in CNN classification results, and further partition them into correctness and incorrectness on the map. The correct classification regions of CNN were trusted and maintained, whereas the misclassification areas were reclassified using a decision tree with both CNN and MLP. The effectiveness of the proposed rough set decision tree based MLP-CNN was tested using an urban area at Bournemouth, United Kingdom. The MLP-CNN, well capturing the complementarity between CNN and MLP through the rough set based decision tree, achieved the best classification performance both visually and numerically. Therefore, this research paves the way to achieve fully automatic and effective VHR image classification.

  3. A Smartphone Camera-Based Indoor Positioning Algorithm of Crowded Scenarios with the Assistance of Deep CNN.

    Science.gov (United States)

    Jiao, Jichao; Li, Fei; Deng, Zhongliang; Ma, Wenjing

    2017-03-28

    Considering the installation cost and coverage, the received signal strength indicator (RSSI)-based indoor positioning system is widely used across the world. However, the indoor positioning performance, due to the interference of wireless signals that are caused by the complex indoor environment that includes a crowded population, cannot achieve the demands of indoor location-based services. In this paper, we focus on increasing the signal strength estimation accuracy considering the population density, which is different to the other RSSI-based indoor positioning methods. Therefore, we propose a new wireless signal compensation model considering the population density, distance, and frequency. First of all, the number of individuals in an indoor crowded scenario can be calculated by our convolutional neural network (CNN)-based human detection approach. Then, the relationship between the population density and the signal attenuation is described in our model. Finally, we use the trilateral positioning principle to realize the pedestrian location. According to the simulation and tests in the crowded scenarios, the proposed model increases the accuracy of the signal strength estimation by 1.53 times compared to that without considering the human body. Therefore, the localization accuracy is less than 1.37 m, which indicates that our algorithm can improve the indoor positioning performance and is superior to other RSSI models.

  4. Deep convolutional neural network for prostate MR segmentation

    Science.gov (United States)

    Tian, Zhiqiang; Liu, Lizhi; Fei, Baowei

    2017-03-01

    Automatic segmentation of the prostate in magnetic resonance imaging (MRI) has many applications in prostate cancer diagnosis and therapy. We propose a deep fully convolutional neural network (CNN) to segment the prostate automatically. Our deep CNN model is trained end-to-end in a single learning stage based on prostate MR images and the corresponding ground truths, and learns to make inference for pixel-wise segmentation. Experiments were performed on our in-house data set, which contains prostate MR images of 20 patients. The proposed CNN model obtained a mean Dice similarity coefficient of 85.3%+/-3.2% as compared to the manual segmentation. Experimental results show that our deep CNN model could yield satisfactory segmentation of the prostate.

  5. Using convolutional neural networks to explore the microbiome.

    Science.gov (United States)

    Reiman, Derek; Metwally, Ahmed; Yang Dai

    2017-07-01

    The microbiome has been shown to have an impact on the development of various diseases in the host. Being able to make an accurate prediction of the phenotype of a genomic sample based on its microbial taxonomic abundance profile is an important problem for personalized medicine. In this paper, we examine the potential of using a deep learning framework, a convolutional neural network (CNN), for such a prediction. To facilitate the CNN learning, we explore the structure of abundance profiles by creating the phylogenetic tree and by designing a scheme to embed the tree to a matrix that retains the spatial relationship of nodes in the tree and their quantitative characteristics. The proposed CNN framework is highly accurate, achieving a 99.47% of accuracy based on the evaluation on a dataset 1967 samples of three phenotypes. Our result demonstrated the feasibility and promising aspect of CNN in the classification of sample phenotype.

  6. A-Lamp: Adaptive Layout-Aware Multi-Patch Deep Convolutional Neural Network for Photo Aesthetic Assessment

    OpenAIRE

    Ma, Shuang; Liu, Jing; Chen, Chang Wen

    2017-01-01

    Deep convolutional neural networks (CNN) have recently been shown to generate promising results for aesthetics assessment. However, the performance of these deep CNN methods is often compromised by the constraint that the neural network only takes the fixed-size input. To accommodate this requirement, input images need to be transformed via cropping, warping, or padding, which often alter image composition, reduce image resolution, or cause image distortion. Thus the aesthetics of the origina...

  7. Cnn Based Retinal Image Upscaling Using Zero Component Analysis

    Science.gov (United States)

    Nasonov, A.; Chesnakov, K.; Krylov, A.

    2017-05-01

    The aim of the paper is to obtain high quality of image upscaling for noisy images that are typical in medical image processing. A new training scenario for convolutional neural network based image upscaling method is proposed. Its main idea is a novel dataset preparation method for deep learning. The dataset contains pairs of noisy low-resolution images and corresponding noiseless highresolution images. To achieve better results at edges and textured areas, Zero Component Analysis is applied to these images. The upscaling results are compared with other state-of-the-art methods like DCCI, SI-3 and SRCNN on noisy medical ophthalmological images. Objective evaluation of the results confirms high quality of the proposed method. Visual analysis shows that fine details and structures like blood vessels are preserved, noise level is reduced and no artifacts or non-existing details are added. These properties are essential in retinal diagnosis establishment, so the proposed algorithm is recommended to be used in real medical applications.

  8. A comparison study between MLP and convolutional neural network models for character recognition

    Science.gov (United States)

    Ben Driss, S.; Soua, M.; Kachouri, R.; Akil, M.

    2017-05-01

    Optical Character Recognition (OCR) systems have been designed to operate on text contained in scanned documents and images. They include text detection and character recognition in which characters are described then classified. In the classification step, characters are identified according to their features or template descriptions. Then, a given classifier is employed to identify characters. In this context, we have proposed the unified character descriptor (UCD) to represent characters based on their features. Then, matching was employed to ensure the classification. This recognition scheme performs a good OCR Accuracy on homogeneous scanned documents, however it cannot discriminate characters with high font variation and distortion.3 To improve recognition, classifiers based on neural networks can be used. The multilayer perceptron (MLP) ensures high recognition accuracy when performing a robust training. Moreover, the convolutional neural network (CNN), is gaining nowadays a lot of popularity for its high performance. Furthermore, both CNN and MLP may suffer from the large amount of computation in the training phase. In this paper, we establish a comparison between MLP and CNN. We provide MLP with the UCD descriptor and the appropriate network configuration. For CNN, we employ the convolutional network designed for handwritten and machine-printed character recognition (Lenet-5) and we adapt it to support 62 classes, including both digits and characters. In addition, GPU parallelization is studied to speed up both of MLP and CNN classifiers. Based on our experimentations, we demonstrate that the used real-time CNN is 2x more relevant than MLP when classifying characters.

  9. Fast Convolutional Neural Network Training Using Selective Data Sampling: Application to Hemorrhage Detection in Color Fundus Images.

    Science.gov (United States)

    van Grinsven, Mark J J P; van Ginneken, Bram; Hoyng, Carel B; Theelen, Thomas; Sanchez, Clara I

    2016-05-01

    Convolutional neural networks (CNNs) are deep learning network architectures that have pushed forward the state-of-the-art in a range of computer vision applications and are increasingly popular in medical image analysis. However, training of CNNs is time-consuming and challenging. In medical image analysis tasks, the majority of training examples are easy to classify and therefore contribute little to the CNN learning process. In this paper, we propose a method to improve and speed-up the CNN training for medical image analysis tasks by dynamically selecting misclassified negative samples during training. Training samples are heuristically sampled based on classification by the current status of the CNN. Weights are assigned to the training samples and informative samples are more likely to be included in the next CNN training iteration. We evaluated and compared our proposed method by training a CNN with (SeS) and without (NSeS) the selective sampling method. We focus on the detection of hemorrhages in color fundus images. A decreased training time from 170 epochs to 60 epochs with an increased performance-on par with two human experts-was achieved with areas under the receiver operating characteristics curve of 0.894 and 0.972 on two data sets. The SeS CNN statistically outperformed the NSeS CNN on an independent test set.

  10. How Deep Neural Networks Can Improve Emotion Recognition on Video Data

    Science.gov (United States)

    2016-09-25

    available, we evaluate all of our ex- periments on the development set. We evaluate our tech- niques by computing three metrics: (i) Root Mean Square...feature extractor by fixing all of the parameters and removing the top regression layer. We then pass each frame within the window to the CNN and extract a...recurrent neural network (RNN) to propagate infor- mation from one time point to next. We first model the CNN as a feature extractor by fixing all of

  11. Classification of crystal structure using a convolutional neural network.

    Science.gov (United States)

    Park, Woon Bae; Chung, Jiyong; Jung, Jaeyoung; Sohn, Keemin; Singh, Satendra Pal; Pyo, Myoungho; Shin, Namsoo; Sohn, Kee-Sun

    2017-07-01

    A deep machine-learning technique based on a convolutional neural network (CNN) is introduced. It has been used for the classification of powder X-ray diffraction (XRD) patterns in terms of crystal system, extinction group and space group. About 150 000 powder XRD patterns were collected and used as input for the CNN with no handcrafted engineering involved, and thereby an appropriate CNN architecture was obtained that allowed determination of the crystal system, extinction group and space group. In sharp contrast with the traditional use of powder XRD pattern analysis, the CNN never treats powder XRD patterns as a deconvoluted and discrete peak position or as intensity data, but instead the XRD patterns are regarded as nothing but a pattern similar to a picture. The CNN interprets features that humans cannot recognize in a powder XRD pattern. As a result, accuracy levels of 81.14, 83.83 and 94.99% were achieved for the space-group, extinction-group and crystal-system classifications, respectively. The well trained CNN was then used for symmetry identification of unknown novel inorganic compounds.

  12. Joint multiple fully connected convolutional neural network with extreme learning machine for hepatocellular carcinoma nuclei grading.

    Science.gov (United States)

    Li, Siqi; Jiang, Huiyan; Pang, Wenbo

    2017-05-01

    Accurate cell grading of cancerous tissue pathological image is of great importance in medical diagnosis and treatment. This paper proposes a joint multiple fully connected convolutional neural network with extreme learning machine (MFC-CNN-ELM) architecture for hepatocellular carcinoma (HCC) nuclei grading. First, in preprocessing stage, each grayscale image patch with the fixed size is obtained using center-proliferation segmentation (CPS) method and the corresponding labels are marked under the guidance of three pathologists. Next, a multiple fully connected convolutional neural network (MFC-CNN) is designed to extract the multi-form feature vectors of each input image automatically, which considers multi-scale contextual information of deep layer maps sufficiently. After that, a convolutional neural network extreme learning machine (CNN-ELM) model is proposed to grade HCC nuclei. Finally, a back propagation (BP) algorithm, which contains a new up-sample method, is utilized to train MFC-CNN-ELM architecture. The experiment comparison results demonstrate that our proposed MFC-CNN-ELM has superior performance compared with related works for HCC nuclei grading. Meanwhile, external validation using ICPR 2014 HEp-2 cell dataset shows the good generalization of our MFC-CNN-ELM architecture. Copyright © 2017 Elsevier Ltd. All rights reserved.

  13. A shallow convolutional neural network for blind image sharpness assessment.

    Science.gov (United States)

    Yu, Shaode; Wu, Shibin; Wang, Lei; Jiang, Fan; Xie, Yaoqin; Li, Leida

    2017-01-01

    Blind image quality assessment can be modeled as feature extraction followed by score prediction. It necessitates considerable expertise and efforts to handcraft features for optimal representation of perceptual image quality. This paper addresses blind image sharpness assessment by using a shallow convolutional neural network (CNN). The network takes single feature layer to unearth intrinsic features for image sharpness representation and utilizes multilayer perceptron (MLP) to rate image quality. Different from traditional methods, CNN integrates feature extraction and score prediction into an optimization procedure and retrieves features automatically from raw images. Moreover, its prediction performance can be enhanced by replacing MLP with general regression neural network (GRNN) and support vector regression (SVR). Experiments on Gaussian blur images from LIVE-II, CSIQ, TID2008 and TID2013 demonstrate that CNN features with SVR achieves the best overall performance, indicating high correlation with human subjective judgment.

  14. Epileptiform spike detection via convolutional neural networks

    DEFF Research Database (Denmark)

    Johansen, Alexander Rosenberg; Jin, Jing; Maszczyk, Tomasz

    2016-01-01

    The EEG of epileptic patients often contains sharp waveforms called "spikes", occurring between seizures. Detecting such spikes is crucial for diagnosing epilepsy. In this paper, we develop a convolutional neural network (CNN) for detecting spikes in EEG of epileptic patients in an automated...

  15. Enhancing deep convolutional neural network scheme for breast cancer diagnosis with unlabeled data.

    Science.gov (United States)

    Sun, Wenqing; Tseng, Tzu-Liang Bill; Zhang, Jianying; Qian, Wei

    2017-04-01

    In this study we developed a graph based semi-supervised learning (SSL) scheme using deep convolutional neural network (CNN) for breast cancer diagnosis. CNN usually needs a large amount of labeled data for training and fine tuning the parameters, and our proposed scheme only requires a small portion of labeled data in training set. Four modules were included in the diagnosis system: data weighing, feature selection, dividing co-training data labeling, and CNN. 3158 region of interests (ROIs) with each containing a mass extracted from 1874 pairs of mammogram images were used for this study. Among them 100 ROIs were treated as labeled data while the rest were treated as unlabeled. The area under the curve (AUC) observed in our study was 0.8818, and the accuracy of CNN is 0.8243 using the mixed labeled and unlabeled data. Copyright © 2016. Published by Elsevier Ltd.

  16. Quaternion-based adaptive output feedback attitude control of spacecraft using Chebyshev neural networks.

    Science.gov (United States)

    Zou, An-Min; Dev Kumar, Krishna; Hou, Zeng-Guang

    2010-09-01

    This paper investigates the problem of output feedback attitude control of an uncertain spacecraft. Two robust adaptive output feedback controllers based on Chebyshev neural networks (CNN) termed adaptive neural networks (NN) controller-I and adaptive NN controller-II are proposed for the attitude tracking control of spacecraft. The four-parameter representations (quaternion) are employed to describe the spacecraft attitude for global representation without singularities. The nonlinear reduced-order observer is used to estimate the derivative of the spacecraft output, and the CNN is introduced to further improve the control performance through approximating the spacecraft attitude motion. The implementation of the basis functions of the CNN used in the proposed controllers depends only on the desired signals, and the smooth robust compensator using the hyperbolic tangent function is employed to counteract the CNN approximation errors and external disturbances. The adaptive NN controller-II can efficiently avoid the over-estimation problem (i.e., the bound of the CNNs output is much larger than that of the approximated unknown function, and hence, the control input may be very large) existing in the adaptive NN controller-I. Both adaptive output feedback controllers using CNN can guarantee that all signals in the resulting closed-loop system are uniformly ultimately bounded. For performance comparisons, the standard adaptive controller using the linear parameterization of spacecraft attitude motion is also developed. Simulation studies are presented to show the advantages of the proposed CNN-based output feedback approach over the standard adaptive output feedback approach.

  17. A convolutional neural network for steady state visual evoked potential classification under ambulatory environment.

    Science.gov (United States)

    Kwak, No-Sang; Müller, Klaus-Robert; Lee, Seong-Whan

    2017-01-01

    The robust analysis of neural signals is a challenging problem. Here, we contribute a convolutional neural network (CNN) for the robust classification of a steady-state visual evoked potentials (SSVEPs) paradigm. We measure electroencephalogram (EEG)-based SSVEPs for a brain-controlled exoskeleton under ambulatory conditions in which numerous artifacts may deteriorate decoding. The proposed CNN is shown to achieve reliable performance under these challenging conditions. To validate the proposed method, we have acquired an SSVEP dataset under two conditions: 1) a static environment, in a standing position while fixated into a lower-limb exoskeleton and 2) an ambulatory environment, walking along a test course wearing the exoskeleton (here, artifacts are most challenging). The proposed CNN is compared to a standard neural network and other state-of-the-art methods for SSVEP decoding (i.e., a canonical correlation analysis (CCA)-based classifier, a multivariate synchronization index (MSI), a CCA combined with k-nearest neighbors (CCA-KNN) classifier) in an offline analysis. We found highly encouraging SSVEP decoding results for the CNN architecture, surpassing those of other methods with classification rates of 99.28% and 94.03% in the static and ambulatory conditions, respectively. A subsequent analysis inspects the representation found by the CNN at each layer and can thus contribute to a better understanding of the CNN's robust, accurate decoding abilities.

  18. Cellular Neural Network-Based Methods for Distributed Network Intrusion Detection

    Directory of Open Access Journals (Sweden)

    Kang Xie

    2015-01-01

    Full Text Available According to the problems of current distributed architecture intrusion detection systems (DIDS, a new online distributed intrusion detection model based on cellular neural network (CNN was proposed, in which discrete-time CNN (DTCNN was used as weak classifier in each local node and state-controlled CNN (SCCNN was used as global detection method, respectively. We further proposed a new method for design template parameters of SCCNN via solving Linear Matrix Inequality. Experimental results based on KDD CUP 99 dataset show its feasibility and effectiveness. Emerging evidence has indicated that this new approach is affordable to parallelism and analog very large scale integration (VLSI implementation which allows the distributed intrusion detection to be performed better.

  19. Classification of CT brain images based on deep learning networks.

    Science.gov (United States)

    Gao, Xiaohong W; Hui, Rui; Tian, Zengmin

    2017-01-01

    While computerised tomography (CT) may have been the first imaging tool to study human brain, it has not yet been implemented into clinical decision making process for diagnosis of Alzheimer's disease (AD). On the other hand, with the nature of being prevalent, inexpensive and non-invasive, CT does present diagnostic features of AD to a great extent. This study explores the significance and impact on the application of the burgeoning deep learning techniques to the task of classification of CT brain images, in particular utilising convolutional neural network (CNN), aiming at providing supplementary information for the early diagnosis of Alzheimer's disease. Towards this end, three categories of CT images (N = 285) are clustered into three groups, which are AD, lesion (e.g. tumour) and normal ageing. In addition, considering the characteristics of this collection with larger thickness along the direction of depth (z) (~3-5 mm), an advanced CNN architecture is established integrating both 2D and 3D CNN networks. The fusion of the two CNN networks is subsequently coordinated based on the average of Softmax scores obtained from both networks consolidating 2D images along spatial axial directions and 3D segmented blocks respectively. As a result, the classification accuracy rates rendered by this elaborated CNN architecture are 85.2%, 80% and 95.3% for classes of AD, lesion and normal respectively with an average of 87.6%. Additionally, this improved CNN network appears to outperform the others when in comparison with 2D version only of CNN network as well as a number of state of the art hand-crafted approaches. As a result, these approaches deliver accuracy rates in percentage of 86.3, 85.6 ± 1.10, 86.3 ± 1.04, 85.2 ± 1.60, 83.1 ± 0.35 for 2D CNN, 2D SIFT, 2D KAZE, 3D SIFT and 3D KAZE respectively. The two major contributions of the paper constitute a new 3-D approach while applying deep learning technique to extract signature information

  20. One-Dimensional Convolutional Neural Network Land-Cover Classification of Multi-Seasonal Hyperspectral Imagery in the San Francisco Bay Area, California

    Directory of Open Access Journals (Sweden)

    Daniel Guidici

    2017-06-01

    Full Text Available In this study, a 1-D Convolutional Neural Network (CNN architecture was developed, trained and utilized to classify single (summer and three seasons (spring, summer, fall of hyperspectral imagery over the San Francisco Bay Area, California for the year 2015. For comparison, the Random Forests (RF and Support Vector Machine (SVM classifiers were trained and tested with the same data. In order to support space-based hyperspectral applications, all analyses were performed with simulated Hyperspectral Infrared Imager (HyspIRI imagery. Three-season data improved classifier overall accuracy by 2.0% (SVM, 1.9% (CNN to 3.5% (RF over single-season data. The three-season CNN provided an overall classification accuracy of 89.9%, which was comparable to overall accuracy of 89.5% for SVM. Both three-season CNN and SVM outperformed RF by over 7% overall accuracy. Analysis and visualization of the inner products for the CNN provided insight to distinctive features within the spectral-temporal domain. A method for CNN kernel tuning was presented to assess the importance of learned features. We concluded that CNN is a promising candidate for hyperspectral remote sensing applications because of the high classification accuracy and interpretability of its inner products.

  1. Brain tumor segmentation with Deep Neural Networks.

    Science.gov (United States)

    Havaei, Mohammad; Davy, Axel; Warde-Farley, David; Biard, Antoine; Courville, Aaron; Bengio, Yoshua; Pal, Chris; Jodoin, Pierre-Marc; Larochelle, Hugo

    2017-01-01

    In this paper, we present a fully automatic brain tumor segmentation method based on Deep Neural Networks (DNNs). The proposed networks are tailored to glioblastomas (both low and high grade) pictured in MR images. By their very nature, these tumors can appear anywhere in the brain and have almost any kind of shape, size, and contrast. These reasons motivate our exploration of a machine learning solution that exploits a flexible, high capacity DNN while being extremely efficient. Here, we give a description of different model choices that we've found to be necessary for obtaining competitive performance. We explore in particular different architectures based on Convolutional Neural Networks (CNN), i.e. DNNs specifically adapted to image data. We present a novel CNN architecture which differs from those traditionally used in computer vision. Our CNN exploits both local features as well as more global contextual features simultaneously. Also, different from most traditional uses of CNNs, our networks use a final layer that is a convolutional implementation of a fully connected layer which allows a 40 fold speed up. We also describe a 2-phase training procedure that allows us to tackle difficulties related to the imbalance of tumor labels. Finally, we explore a cascade architecture in which the output of a basic CNN is treated as an additional source of information for a subsequent CNN. Results reported on the 2013 BRATS test data-set reveal that our architecture improves over the currently published state-of-the-art while being over 30 times faster. Copyright © 2016 Elsevier B.V. All rights reserved.

  2. Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval

    Directory of Open Access Journals (Sweden)

    Weixun Zhou

    2017-05-01

    Full Text Available Learning powerful feature representations for image retrieval has always been a challenging task in the field of remote sensing. Traditional methods focus on extracting low-level hand-crafted features which are not only time-consuming but also tend to achieve unsatisfactory performance due to the complexity of remote sensing images. In this paper, we investigate how to extract deep feature representations based on convolutional neural networks (CNNs for high-resolution remote sensing image retrieval (HRRSIR. To this end, several effective schemes are proposed to generate powerful feature representations for HRRSIR. In the first scheme, a CNN pre-trained on a different problem is treated as a feature extractor since there are no sufficiently-sized remote sensing datasets to train a CNN from scratch. In the second scheme, we investigate learning features that are specific to our problem by first fine-tuning the pre-trained CNN on a remote sensing dataset and then proposing a novel CNN architecture based on convolutional layers and a three-layer perceptron. The novel CNN has fewer parameters than the pre-trained and fine-tuned CNNs and can learn low dimensional features from limited labelled images. The schemes are evaluated on several challenging, publicly available datasets. The results indicate that the proposed schemes, particularly the novel CNN, achieve state-of-the-art performance.

  3. Image-based quantitative analysis of gold immunochromatographic strip via cellular neural network approach.

    Science.gov (United States)

    Zeng, Nianyin; Wang, Zidong; Zineddin, Bachar; Li, Yurong; Du, Min; Xiao, Liang; Liu, Xiaohui; Young, Terry

    2014-05-01

    Gold immunochromatographic strip assay provides a rapid, simple, single-copy and on-site way to detect the presence or absence of the target analyte. This paper aims to develop a method for accurately segmenting the test line and control line of the gold immunochromatographic strip (GICS) image for quantitatively determining the trace concentrations in the specimen, which can lead to more functional information than the traditional qualitative or semi-quantitative strip assay. The canny operator as well as the mathematical morphology method is used to detect and extract the GICS reading-window. Then, the test line and control line of the GICS reading-window are segmented by the cellular neural network (CNN) algorithm, where the template parameters of the CNN are designed by the switching particle swarm optimization (SPSO) algorithm for improving the performance of the CNN. It is shown that the SPSO-based CNN offers a robust method for accurately segmenting the test and control lines, and therefore serves as a novel image methodology for the interpretation of GICS. Furthermore, quantitative comparison is carried out among four algorithms in terms of the peak signal-to-noise ratio. It is concluded that the proposed CNN algorithm gives higher accuracy and the CNN is capable of parallelism and analog very-large-scale integration implementation within a remarkably efficient time.

  4. Adaptive Steganalysis Based on Selection Region and Combined Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Donghui Hu

    2017-01-01

    Full Text Available Digital image steganalysis is the art of detecting the presence of information hiding in carrier images. When detecting recently developed adaptive image steganography methods, state-of-art steganalysis methods cannot achieve satisfactory detection accuracy, because the adaptive steganography methods can adaptively embed information into regions with rich textures via the guidance of distortion function and thus make the effective steganalysis features hard to be extracted. Inspired by the promising success which convolutional neural network (CNN has achieved in the fields of digital image analysis, increasing researchers are devoted to designing CNN based steganalysis methods. But as for detecting adaptive steganography methods, the results achieved by CNN based methods are still far from expected. In this paper, we propose a hybrid approach by designing a region selection method and a new CNN framework. In order to make the CNN focus on the regions with complex textures, we design a region selection method by finding a region with the maximal sum of the embedding probabilities. To evolve more diverse and effective steganalysis features, we design a new CNN framework consisting of three separate subnets with independent structure and configuration parameters and then merge and split the three subnets repeatedly. Experimental results indicate that our approach can lead to performance improvement in detecting adaptive steganography.

  5. Convolutional Neural Network-based SAR Image Classification with Noisy Labels

    Directory of Open Access Journals (Sweden)

    Zhao Juanping

    2017-10-01

    Full Text Available SAR image classification is an important task in SAR image interpretation. Supervised learning methods, such as the Convolutional Neural Network (CNN, demand samples that are accurately labeled. However, this presents a major challenge in SAR image labeling. Due to their unique imaging mechanism, SAR images are seriously affected by speckle, geometric distortion, and incomplete structural information. Thus, SAR images have a strong non-intuitive property, which causes difficulties in SAR image labeling, and which results in the weakened learning and generalization performance of many classifiers (including CNN. In this paper, we propose a Probability Transition CNN (PTCNN for patch-level SAR image classification with noisy labels. Based on the classical CNN, PTCNN builds a bridge between noise-free labels and their noisy versions via a noisy-label transition layer. As such, we derive a new CNN model trained with a noisily labeled training dataset that can potentially revise noisy labels and improve learning capacity with noisily labeled data. We use a 16-class land cover dataset and the MSTAR dataset to demonstrate the effectiveness of our model. Our experimental results show the PTCNN model to be robust with respect to label noise and demonstrate its promising classification performance compared with the classical CNN model. Therefore, the proposed PTCNN model could lower the standards required regarding the quality of image labels and have a variety of practical applications.

  6. Tweaked residual convolutional network for face alignment

    Science.gov (United States)

    Du, Wenchao; Li, Ke; Zhao, Qijun; Zhang, Yi; Chen, Hu

    2017-08-01

    We propose a novel Tweaked Residual Convolutional Network approach for face alignment with two-level convolutional networks architecture. Specifically, the first-level Tweaked Convolutional Network (TCN) module predicts the landmark quickly but accurately enough as a preliminary, by taking low-resolution version of the detected face holistically as the input. The following Residual Convolutional Networks (RCN) module progressively refines the landmark by taking as input the local patch extracted around the predicted landmark, particularly, which allows the Convolutional Neural Network (CNN) to extract local shape-indexed features to fine tune landmark position. Extensive evaluations show that the proposed Tweaked Residual Convolutional Network approach outperforms existing methods.

  7. Three-dimensional fingerprint recognition by using convolution neural network

    Science.gov (United States)

    Tian, Qianyu; Gao, Nan; Zhang, Zonghua

    2018-01-01

    With the development of science and technology and the improvement of social information, fingerprint recognition technology has become a hot research direction and been widely applied in many actual fields because of its feasibility and reliability. The traditional two-dimensional (2D) fingerprint recognition method relies on matching feature points. This method is not only time-consuming, but also lost three-dimensional (3D) information of fingerprint, with the fingerprint rotation, scaling, damage and other issues, a serious decline in robustness. To solve these problems, 3D fingerprint has been used to recognize human being. Because it is a new research field, there are still lots of challenging problems in 3D fingerprint recognition. This paper presents a new 3D fingerprint recognition method by using a convolution neural network (CNN). By combining 2D fingerprint and fingerprint depth map into CNN, and then through another CNN feature fusion, the characteristics of the fusion complete 3D fingerprint recognition after classification. This method not only can preserve 3D information of fingerprints, but also solves the problem of CNN input. Moreover, the recognition process is simpler than traditional feature point matching algorithm. 3D fingerprint recognition rate by using CNN is compared with other fingerprint recognition algorithms. The experimental results show that the proposed 3D fingerprint recognition method has good recognition rate and robustness.

  8. The Global Discourse on Human Trafficking and the Construction of a Standard of Civilization: Explored through The CNN Freedom Project

    OpenAIRE

    Larsen, Line Liblik

    2014-01-01

    This thesis is an integrated research study in two study programs cultural encounters and global studies. The thesis performs a critical discourse analysis of a mass media humanitarian campaign called The CNN Freedom Project and the broader global discourse on human trafficking in which the campaign is situated. The complexity of the issue of human trafficking is owed to the plethora of competing and influential elements, where various definitions, understandings, statistics, and ideologies e...

  9. Age estimation of facial image based on convolution neural network

    Science.gov (United States)

    Meng, Xiaodong; Wang, Yifeng; Zheng, Haihong

    2017-07-01

    Age is an inherent biological characteristic of human and is reflected in facial images to a certain extent. A method for estimating age from a facial image by combining CNN (Convolution Neural Network) with SVR (Support Vector Regression) is proposed. First, a deep CNN is trained to automatically extract age features from facial images and classify them into variant age groups. Then different SVRs are trained for each age group to estimate the age of a facial image. The experimental results show that a lower MAE (Mean Absolute Error) of age estimation on MORPH database is obtained.

  10. Detection of phase transition via convolutional neural network

    CERN Document Server

    Tanaka, Akinori

    2016-01-01

    We design a Convolutional Neural Network (CNN) which studies correlation between discretized inverse temperature and spin configuration of 2D Ising model and show that it can find a feature of the phase transition without teaching any a priori information for it. We also define a new order parameter via the CNN and show that it provides well approximated critical inverse temperature. In addition, we compare the activation functions for convolution layer and find that the Rectified Linear Unit (ReLU) is important to detect the phase transition of 2D Ising model.

  11. Classifying Symmetrical Differences and Temporal Change in Mammography Using Deep Neural Networks

    NARCIS (Netherlands)

    Kooi, T.; Karssemeijer, N.

    2017-01-01

    Neural networks, in particular deep Convolutional Neural Networks (CNN), have recently gone through a renaissance sparked by the introduction of more efficient training procedures and massive amounts of raw annotated data. Barring a handful of modalities, medical images are typically too large to

  12. Robust Total Retina Thickness Segmentation in Optical Coherence Tomography Images using Convolutional Neural Networks

    NARCIS (Netherlands)

    Venhuizen, F.G.; Ginneken, B. van; Liefers, B.J.; Grinsven, M.J.J.P. van; Fauser, S.; Hoyng, C.B.; Theelen, T.; Sanchez, C.I.

    2017-01-01

    We developed a fully automated system using a convolutional neural network (CNN) for total retina segmentation in optical coherence tomography (OCT) that is robust to the presence of severe retinal pathology. A generalized U-net network architecture was introduced to include the large context needed

  13. Robust total retina thickness segmentation in optical coherence tomography images using convolutional neural networks

    NARCIS (Netherlands)

    Venhuizen, F.G.; Ginneken, B. van; Liefers, B.J.; Grinsven, M.J.J.P. van; Fauser, S.; Hoyng, C.B.; Theelen, T.; Sanchez, C.I.

    2017-01-01

    We developed a fully automated system using a convolutional neural network (CNN) for total retina segmentation in optical coherence tomography (OCT) that is robust to the presence of severe retinal pathology. A generalized U-net network architecture was introduced to include the large context needed

  14. Convolutional neural networks with balanced batches for facial expressions recognition

    Science.gov (United States)

    Battini Sönmez, Elena; Cangelosi, Angelo

    2017-03-01

    This paper considers the issue of fully automatic emotion classification on 2D faces. In spite of the great effort done in recent years, traditional machine learning approaches based on hand-crafted feature extraction followed by the classification stage failed to develop a real-time automatic facial expression recognition system. The proposed architecture uses Convolutional Neural Networks (CNN), which are built as a collection of interconnected processing elements to simulate the brain of human beings. The basic idea of CNNs is to learn a hierarchical representation of the input data, which results in a better classification performance. In this work we present a block-based CNN algorithm, which uses noise, as data augmentation technique, and builds batches with a balanced number of samples per class. The proposed architecture is a very simple yet powerful CNN, which can yield state-of-the-art accuracy on the very competitive benchmark algorithm of the Extended Cohn Kanade database.

  15. Multi-robot Coordination by using Cellular Neural Networks

    Directory of Open Access Journals (Sweden)

    A. Gacsadi

    2008-05-01

    Full Text Available Vision-based algorithms for multi-robot coordination,are presented in this paper. Cellular Neural Networks (CNNsprocessing techniques are used for real time motion planning ofthe robots. The CNN methods are considered an advantageoussolution for image processing in autonomous mobile robotsguidance.

  16. Training Convolutional Neural Networks for Translational Invariance on SAR ATR

    DEFF Research Database (Denmark)

    Malmgren-Hansen, David; Engholm, Rasmus; Østergaard Pedersen, Morten

    2016-01-01

    In this paper we present a comparison of the robustness of Convolutional Neural Networks (CNN) to other classifiers in the presence of uncertainty of the objects localization in SAR image. We present a framework for simulating simple SAR images, translating the object of interest systematically...

  17. Dangerous noncompliance: a narrative analysis of a CNN special investigation of mental illness.

    Science.gov (United States)

    Glick, Douglas; Applbaum, Kalman

    2010-08-01

    Prevention of illness has become a central theme in debates over strategies to reduce healthcare costs. Severe mental illness poses a special challenge to the paradigm of rational prevention, the principal strategy of which is adherence to pharmacological therapies. With the contraction in the US of in-patient psychiatric care from the 1960s onwards, the mentally ill have become more visible among the homeless and among those caught up in the penal system. Their characteristic visibility contributes to their image as threatening. The perceived dangerousness and the combined societal and economic costs associated with the illness have generated a heightened, and in some venues even a sensationalized rhetoric surrounding the questions of responsibility and control, which we consider in terms of compliance. Using the linguistic method of discourse analysis, we analyze one high profile instance - an episode of CNN's 'Special Investigations Unit', which aired several times in the summer of 2007 - to demonstrate a narrative linking of the high social costs and failures associated with noncompliance and, therefore, the imperative of enforcing it for the safety of society. Through the semiotic reduction of a 'poetic parallelism', the episode reflects and reinforces existing cultural models for mental illness, including its status as straightforward biological disease amenable to pharmacological therapy but which remains uncontrolled due to widespread noncompliance.

  18. Bent CNN bond of diazo compounds, RR'(Cdbnd N+dbnd N-)

    Science.gov (United States)

    Akita, Motoko; Takahashi, Mai; Kobayashi, Keiji; Hayashi, Naoto; Tukada, Hideyuki

    2013-02-01

    The reaction of ninhydrin with benzophenone hydrazone afforded 2-diazo-3-diphenylmethylenehydrazono-1-indanone 1 and 2-diazo-1,3-bis(diphenylmethylenehydrazono)indan 2. X-ray crystal structure analyses of these products showed that the diazo functional group Cdbnd N+dbnd N- of 1 is bent by 172.9°, while that of 2 has a linear geometry. The crystal structure data of diazo compounds have been retrieved from the Cambridge Structural Database (CSD), which hit 177 entries to indicate that the angle of 172.9° in 1 lies in one of the most bent structures. The CSD search also indicated that diazo compounds consisting of a distorted diazo carbon tend to bend the Cdbnd N+dbnd N- bond. On the basis of DFT calculations (B3LYP/6-311++G(d,p)) of model compounds, it was revealed that the bending of the CNN bond is principally induced by steric factors and that the neighboring carbonyl group also plays a role in bending toward the carbonyl side owing to an electrostatic attractive interaction. The potential surface along the path of Cdbnd N+dbnd N- bending in 2-diazopropane shows a significantly shallow profile with only 4 kcal/mol needed to bend the Cdbnd N+dbnd N- bond from 180° to 160°. Thus, the bending of the diazo group in 1 is reasonable as it is provided with all of the factors for facile bending disclosed in this investigation.

  19. The Types of Argument Structure Used by Hillary Clinton in the CNN Democratic Presidential Debate

    Directory of Open Access Journals (Sweden)

    Anggie Angeline

    2009-01-01

    Full Text Available This qualitative research was conducted to examine the types of argument structure by Hillary Clinton in part one of the CNN Democratic Presidential Debate since Hillary, who had a great deal of experiences in political parties, was supposed to be able to construct convincing arguments that had good argument structures. The theories used to analyze were Bierman and Assali’s (1996, King’s (n.d. and Stanlick’s (2003. The findings showed that there were five types of argument structure used: serial, linked, convergent, divergent, and hybrid argument structures. The linked argument structure was the argument structure used the most frequently in Hillary’s utterances in the debate, while the divergent was the least one. Thus, it could be concluded that Hillary’s speech in the Presidential Debate was quite interesting since she could combine all the five types of argument structure, though the frequency of using them was not the same and it seems that linked argument structure was the most effective strategy for her in arguing about the politic, economy, and social issues.

  20. Towards completing the cyclopropenylidene cycle: rovibrational analysis of cyclic N3(+), CNN, HCNN(+), and CNC().

    Science.gov (United States)

    Fortenberry, Ryan C; Lee, Timothy J; Huang, Xinchuan

    2017-08-30

    The simple aromatic hydrocarbon, cyclopropenylidene (c-C3H2), is a known, naturally-occurring molecule. The question remains as to whether its isoelectronic, cyclic, fellow aromatics of c-N3(+), c-CNN, HCNN(+), and c-CNC(-) are as well. Each of these are exciting objects for observation of Titan, and the rotational constants and vibrational frequencies produced here will allow for remote sensing of Titan's atmosphere or other astrophysical or terrestrial sources. None of these four aromatic species are vibrationally strong absorbers/emitters, but the two ions, HCNN(+) and c-CNC(-), have dipole moments of greater than 3 D and 1 D, respectively, making them good targets for rotational spectroscopic observation. Each of these molecules is shown here to exhibit its own, unique vibrational properties, but the general trends put the vibrational behavior for corresponding fundamental modes within close ranges of one another, even producing nearly the same heavy atom, symmetric stretching frequencies for HCNN(+) and c-C3H2 at 1600 cm(-1). The c-N3(+) cation is confirmed to be fairly unstable and has almost no intensity in its ν2 fundamental. Hence, it will likely remain difficult to characterize experimentally.

  1. Convolutional neural networks for segmentation and object detection of human semen

    DEFF Research Database (Denmark)

    Nissen, Malte Stær; Krause, Oswin; Almstrup, Kristian

    2017-01-01

    We compare a set of convolutional neural network (CNN) architectures for the task of segmenting and detecting human sperm cells in an image taken from a semen sample. In contrast to previous work, samples are not stained or washed to allow for full sperm quality analysis, making analysis harder due...... are found by using connected components on the CNN predictions. We investigate optimization of a threshold parameter on the size of detected components. Our best network achieves 93.87% precision and 91.89% recall on our test dataset after thresholding outperforming a classical image analysis approach....

  2. Remote Sensing Scene Classification Based on Convolutional Neural Networks Pre-Trained Using Attention-Guided Sparse Filters

    Directory of Open Access Journals (Sweden)

    Jingbo Chen

    2018-02-01

    Full Text Available Semantic-level land-use scene classification is a challenging problem, in which deep learning methods, e.g., convolutional neural networks (CNNs, have shown remarkable capacity. However, a lack of sufficient labeled images has proved a hindrance to increasing the land-use scene classification accuracy of CNNs. Aiming at this problem, this paper proposes a CNN pre-training method under the guidance of a human visual attention mechanism. Specifically, a computational visual attention model is used to automatically extract salient regions in unlabeled images. Then, sparse filters are adopted to learn features from these salient regions, with the learnt parameters used to initialize the convolutional layers of the CNN. Finally, the CNN is further fine-tuned on labeled images. Experiments are performed on the UCMerced and AID datasets, which show that when combined with a demonstrative CNN, our method can achieve 2.24% higher accuracy than a plain CNN and can obtain an overall accuracy of 92.43% when combined with AlexNet. The results indicate that the proposed method can effectively improve CNN performance using easy-to-access unlabeled images and thus will enhance the performance of land-use scene classification especially when a large-scale labeled dataset is unavailable.

  3. Metaheuristic Algorithms for Convolution Neural Network.

    Science.gov (United States)

    Rere, L M Rasdi; Fanany, Mohamad Ivan; Arymurthy, Aniati Murni

    2016-01-01

    A typical modern optimization technique is usually either heuristic or metaheuristic. This technique has managed to solve some optimization problems in the research area of science, engineering, and industry. However, implementation strategy of metaheuristic for accuracy improvement on convolution neural networks (CNN), a famous deep learning method, is still rarely investigated. Deep learning relates to a type of machine learning technique, where its aim is to move closer to the goal of artificial intelligence of creating a machine that could successfully perform any intellectual tasks that can be carried out by a human. In this paper, we propose the implementation strategy of three popular metaheuristic approaches, that is, simulated annealing, differential evolution, and harmony search, to optimize CNN. The performances of these metaheuristic methods in optimizing CNN on classifying MNIST and CIFAR dataset were evaluated and compared. Furthermore, the proposed methods are also compared with the original CNN. Although the proposed methods show an increase in the computation time, their accuracy has also been improved (up to 7.14 percent).

  4. Metaheuristic Algorithms for Convolution Neural Network

    Directory of Open Access Journals (Sweden)

    L. M. Rasdi Rere

    2016-01-01

    Full Text Available A typical modern optimization technique is usually either heuristic or metaheuristic. This technique has managed to solve some optimization problems in the research area of science, engineering, and industry. However, implementation strategy of metaheuristic for accuracy improvement on convolution neural networks (CNN, a famous deep learning method, is still rarely investigated. Deep learning relates to a type of machine learning technique, where its aim is to move closer to the goal of artificial intelligence of creating a machine that could successfully perform any intellectual tasks that can be carried out by a human. In this paper, we propose the implementation strategy of three popular metaheuristic approaches, that is, simulated annealing, differential evolution, and harmony search, to optimize CNN. The performances of these metaheuristic methods in optimizing CNN on classifying MNIST and CIFAR dataset were evaluated and compared. Furthermore, the proposed methods are also compared with the original CNN. Although the proposed methods show an increase in the computation time, their accuracy has also been improved (up to 7.14 percent.

  5. Community structure of complex networks based on continuous neural network

    Science.gov (United States)

    Dai, Ting-ting; Shan, Chang-ji; Dong, Yan-shou

    2017-09-01

    As a new subject, the research of complex networks has attracted the attention of researchers from different disciplines. Community structure is one of the key structures of complex networks, so it is a very important task to analyze the community structure of complex networks accurately. In this paper, we study the problem of extracting the community structure of complex networks, and propose a continuous neural network (CNN) algorithm. It is proved that for any given initial value, the continuous neural network algorithm converges to the eigenvector of the maximum eigenvalue of the network modularity matrix. Therefore, according to the stability of the evolution of the network symbol will be able to get two community structure.

  6. Deep Convolutional Neural Network for Inverse Problems in Imaging.

    Science.gov (United States)

    Jin, Kyong Hwan; McCann, Michael T; Froustey, Emmanuel; Unser, Michael

    2017-06-15

    In this paper, we propose a novel deep convolutional neural network (CNN)-based algorithm for solving ill-posed inverse problems. Regularized iterative algorithms have emerged as the standard approach to ill-posed inverse problems in the past few decades. These methods produce excellent results, but can be challenging to deploy in practice due to factors including the high computational cost of the forward and adjoint operators and the difficulty of hyper parameter selection. The starting point of our work is the observation that unrolled iterative methods have the form of a CNN (filtering followed by point-wise nonlinearity) when the normal operator ( H*H where H* is the adjoint of the forward imaging operator, H ) of the forward model is a convolution. Based on this observation, we propose using direct inversion followed by a CNN to solve normal-convolutional inverse problems. The direct inversion encapsulates the physical model of the system, but leads to artifacts when the problem is ill-posed; the CNN combines multiresolution decomposition and residual learning in order to learn to remove these artifacts while preserving image structure. We demonstrate the performance of the proposed network in sparse-view reconstruction (down to 50 views) on parallel beam X-ray computed tomography in synthetic phantoms as well as in real experimental sinograms. The proposed network outperforms total variation-regularized iterative reconstruction for the more realistic phantoms and requires less than a second to reconstruct a 512 x 512 image on the GPU.

  7. Deep Convolutional Neural Network for Inverse Problems in Imaging

    Science.gov (United States)

    Jin, Kyong Hwan; McCann, Michael T.; Froustey, Emmanuel; Unser, Michael

    2017-09-01

    In this paper, we propose a novel deep convolutional neural network (CNN)-based algorithm for solving ill-posed inverse problems. Regularized iterative algorithms have emerged as the standard approach to ill-posed inverse problems in the past few decades. These methods produce excellent results, but can be challenging to deploy in practice due to factors including the high computational cost of the forward and adjoint operators and the difficulty of hyper parameter selection. The starting point of our work is the observation that unrolled iterative methods have the form of a CNN (filtering followed by point-wise non-linearity) when the normal operator (H*H, the adjoint of H times H) of the forward model is a convolution. Based on this observation, we propose using direct inversion followed by a CNN to solve normal-convolutional inverse problems. The direct inversion encapsulates the physical model of the system, but leads to artifacts when the problem is ill-posed; the CNN combines multiresolution decomposition and residual learning in order to learn to remove these artifacts while preserving image structure. We demonstrate the performance of the proposed network in sparse-view reconstruction (down to 50 views) on parallel beam X-ray computed tomography in synthetic phantoms as well as in real experimental sinograms. The proposed network outperforms total variation-regularized iterative reconstruction for the more realistic phantoms and requires less than a second to reconstruct a 512 x 512 image on GPU.

  8. Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction.

    Science.gov (United States)

    Ma, Xiaolei; Dai, Zhuang; He, Zhengbing; Ma, Jihui; Wang, Yong; Wang, Yunpeng

    2017-04-10

    This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.

  9. A cellular neural network based method for classification of magnetic resonance images: towards an automated detection of hippocampal sclerosis.

    Science.gov (United States)

    Döhler, Florian; Mormann, Florian; Weber, Bernd; Elger, Christian E; Lehnertz, Klaus

    2008-05-30

    We present a cellular neuronal network (CNN) based approach to classify magnetic resonance images with and without hippocampal or Ammon's horn sclerosis (AHS) in the medial temporal lobe. A CNN combines the architecture of cellular automata and artificial neural networks and is an array of locally coupled nonlinear electrical circuits or cells, which is capable of processing a large amount of information in parallel and in real time. Using an exemplary database that consists of a large number of volumes of interest extracted from T1-weighted magnetic resonance images from 144 subjects we here demonstrate that the network allows to classify brain tissue with respect to the presence or absence of mesial temporal sclerosis. Results indicate the general feasibility of CNN-based computer-aided systems for diagnosis and classification of images generated by medical imaging systems.

  10. Design of deep convolutional networks for prediction of image rapid serial visual presentation events.

    Science.gov (United States)

    Zijing Mao; Wan Xiang Yao; Yufe Huang

    2017-07-01

    We report in this paper an investigation of convolutional neural network (CNN) models for target prediction in time-locked image rapid serial visual presentation (RSVP) experiment. We investigated CNN models with 11 different designs of convolution filters in capturing spatial and temporal correlations in EEG data. We showed that for both within-subject and cross-subject predictions, the CNN models outperform the state-of-the-art algorithms: Bayesian linear discriminant analysis (BLDA) and xDAWN spatial filtering and achieved >6% improvement. Among the 11 different CNN models, the global spatial filter and our proposed region of interest (ROI) achieved best performance. We also implemented the deconvolution network to show how we can visualize from activated hidden units for target/nontarget events learned by the ROI-CNN. Our study suggests that deep learning is a powerful tool for RSVP target prediction and the proposed model is applicable for general EEG-based classifications in brain computer interaction research. The code of this project is available at https://github.com/ZijingMao/ROICNN.

  11. A convolutional neural network for steady state visual evoked potential classification under ambulatory environment

    Science.gov (United States)

    Kwak, No-Sang; Müller, Klaus-Robert

    2017-01-01

    The robust analysis of neural signals is a challenging problem. Here, we contribute a convolutional neural network (CNN) for the robust classification of a steady-state visual evoked potentials (SSVEPs) paradigm. We measure electroencephalogram (EEG)-based SSVEPs for a brain-controlled exoskeleton under ambulatory conditions in which numerous artifacts may deteriorate decoding. The proposed CNN is shown to achieve reliable performance under these challenging conditions. To validate the proposed method, we have acquired an SSVEP dataset under two conditions: 1) a static environment, in a standing position while fixated into a lower-limb exoskeleton and 2) an ambulatory environment, walking along a test course wearing the exoskeleton (here, artifacts are most challenging). The proposed CNN is compared to a standard neural network and other state-of-the-art methods for SSVEP decoding (i.e., a canonical correlation analysis (CCA)-based classifier, a multivariate synchronization index (MSI), a CCA combined with k-nearest neighbors (CCA-KNN) classifier) in an offline analysis. We found highly encouraging SSVEP decoding results for the CNN architecture, surpassing those of other methods with classification rates of 99.28% and 94.03% in the static and ambulatory conditions, respectively. A subsequent analysis inspects the representation found by the CNN at each layer and can thus contribute to a better understanding of the CNN’s robust, accurate decoding abilities. PMID:28225827

  12. 3D Convolutional Neural Network for Automatic Detection of Lung Nodules in Chest CT.

    Science.gov (United States)

    Hamidian, Sardar; Sahiner, Berkman; Petrick, Nicholas; Pezeshk, Aria

    2017-01-01

    Deep convolutional neural networks (CNNs) form the backbone of many state-of-the-art computer vision systems for classification and segmentation of 2D images. The same principles and architectures can be extended to three dimensions to obtain 3D CNNs that are suitable for volumetric data such as CT scans. In this work, we train a 3D CNN for automatic detection of pulmonary nodules in chest CT images using volumes of interest extracted from the LIDC dataset. We then convert the 3D CNN which has a fixed field of view to a 3D fully convolutional network (FCN) which can generate the score map for the entire volume efficiently in a single pass. Compared to the sliding window approach for applying a CNN across the entire input volume, the FCN leads to a nearly 800-fold speed-up, and thereby fast generation of output scores for a single case. This screening FCN is used to generate difficult negative examples that are used to train a new discriminant CNN. The overall system consists of the screening FCN for fast generation of candidate regions of interest, followed by the discrimination CNN.

  13. 3D convolutional neural network for automatic detection of lung nodules in chest CT

    Science.gov (United States)

    Hamidian, Sardar; Sahiner, Berkman; Petrick, Nicholas; Pezeshk, Aria

    2017-03-01

    Deep convolutional neural networks (CNNs) form the backbone of many state-of-the-art computer vision systems for classification and segmentation of 2D images. The same principles and architectures can be extended to three dimensions to obtain 3D CNNs that are suitable for volumetric data such as CT scans. In this work, we train a 3D CNN for automatic detection of pulmonary nodules in chest CT images using volumes of interest extracted from the LIDC dataset. We then convert the 3D CNN which has a fixed field of view to a 3D fully convolutional network (FCN) which can generate the score map for the entire volume efficiently in a single pass. Compared to the sliding window approach for applying a CNN across the entire input volume, the FCN leads to a nearly 800-fold speed-up, and thereby fast generation of output scores for a single case. This screening FCN is used to generate difficult negative examples that are used to train a new discriminant CNN. The overall system consists of the screening FCN for fast generation of candidate regions of interest, followed by the discrimination CNN.

  14. Computer-Aided Diagnosis Based on Convolutional Neural Network System for Colorectal Polyp Classification: Preliminary Experience.

    Science.gov (United States)

    Komeda, Yoriaki; Handa, Hisashi; Watanabe, Tomohiro; Nomura, Takanobu; Kitahashi, Misaki; Sakurai, Toshiharu; Okamoto, Ayana; Minami, Tomohiro; Kono, Masashi; Arizumi, Tadaaki; Takenaka, Mamoru; Hagiwara, Satoru; Matsui, Shigenaga; Nishida, Naoshi; Kashida, Hiroshi; Kudo, Masatoshi

    2017-01-01

    Computer-aided diagnosis (CAD) is becoming a next-generation tool for the diagnosis of human disease. CAD for colon polyps has been suggested as a particularly useful tool for trainee colonoscopists, as the use of a CAD system avoids the complications associated with endoscopic resections. In addition to conventional CAD, a convolutional neural network (CNN) system utilizing artificial intelligence (AI) has been developing rapidly over the past 5 years. We attempted to generate a unique CNN-CAD system with an AI function that studied endoscopic images extracted from movies obtained with colonoscopes used in routine examinations. Here, we report our preliminary results of this novel CNN-CAD system for the diagnosis of colon polyps. A total of 1,200 images from cases of colonoscopy performed between January 2010 and December 2016 at Kindai University Hospital were used. These images were extracted from the video of actual endoscopic examinations. Additional video images from 10 cases of unlearned processes were retrospectively assessed in a pilot study. They were simply diagnosed as either an adenomatous or nonadenomatous polyp. The number of images used by AI to learn to distinguish adenomatous from nonadenomatous was 1,200:600. These images were extracted from the videos of actual endoscopic examinations. The size of each image was adjusted to 256 × 256 pixels. A 10-hold cross-validation was carried out. The accuracy of the 10-hold cross-validation is 0.751, where the accuracy is the ratio of the number of correct answers over the number of all the answers produced by the CNN. The decisions by the CNN were correct in 7 of 10 cases. A CNN-CAD system using routine colonoscopy might be useful for the rapid diagnosis of colorectal polyp classification. Further prospective studies in an in vivo setting are required to confirm the effectiveness of a CNN-CAD system in routine colonoscopy. © 2017 S. Karger AG, Basel.

  15. A Convolutional Neural Network Neutrino Event Classifier

    CERN Document Server

    Aurisano, A; Rocco, D; Himmel, A; Messier, M D; Niner, E; Pawloski, G; Psihas, F; Sousa, A; Vahle, P

    2016-01-01

    Convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.

  16. Digital Neural Networks for New Media

    Science.gov (United States)

    Spaanenburg, Lambert; Malki, Suleyman

    Neural Networks perform computationally intensive tasks offering smart solutions for many new media applications. A number of analog and mixed digital/analog implementations have been proposed to smooth the algorithmic gap. But gradually, the digital implementation has become feasible, and the dedicated neural processor is on the horizon. A notable example is the Cellular Neural Network (CNN). The analog direction has matured for low-power, smart vision sensors; the digital direction is gradually being shaped into an IP-core for algorithm acceleration, especially for use in FPGA-based high-performance systems. The chapter discusses the next step towards a flexible and scalable multi-core engine using Application-Specific Integrated Processors (ASIP). This topographic engine can serve many new media tasks, as illustrated by novel applications in Homeland Security. We conclude with a view on the CNN kaleidoscope for the year 2020.

  17. Automatic Categorization and Scoring of Solid, Part-Solid and Non-Solid Pulmonary Nodules in CT Images with Convolutional Neural Network.

    Science.gov (United States)

    Tu, Xiaoguang; Xie, Mei; Gao, Jingjing; Ma, Zheng; Chen, Daiqiang; Wang, Qingfeng; Finlayson, Samuel G; Ou, Yangming; Cheng, Jie-Zhi

    2017-09-01

    We present a computer-aided diagnosis system (CADx) for the automatic categorization of solid, part-solid and non-solid nodules in pulmonary computerized tomography images using a Convolutional Neural Network (CNN). Provided with only a two-dimensional region of interest (ROI) surrounding each nodule, our CNN automatically reasons from image context to discover informative computational features. As a result, no image segmentation processing is needed for further analysis of nodule attenuation, allowing our system to avoid potential errors caused by inaccurate image processing. We implemented two computerized texture analysis schemes, classification and regression, to automatically categorize solid, part-solid and non-solid nodules in CT scans, with hierarchical features in each case learned directly by the CNN model. To show the effectiveness of our CNN-based CADx, an established method based on histogram analysis (HIST) was implemented for comparison. The experimental results show significant performance improvement by the CNN model over HIST in both classification and regression tasks, yielding nodule classification and rating performance concordant with those of practicing radiologists. Adoption of CNN-based CADx systems may reduce the inter-observer variation among screening radiologists and provide a quantitative reference for further nodule analysis.

  18. Sigma-delta cellular neural network for 2D modulation.

    Science.gov (United States)

    Aomori, Hisashi; Otake, Tsuyoshi; Takahashi, Nobuaki; Tanaka, Mamoru

    2008-01-01

    Although sigma-delta modulation is widely used for analog-to-digital (A/D) converters, sigma-delta concepts are only for 1D signals. Signal processing in the digital domain is extremely useful for 2D signals such as used in image processing, medical imaging, ultrasound imaging, and so on. The intricate task that provides true 2D sigma-delta modulation is feasible in the spatial domain sigma-delta modulation using the discrete-time cellular neural network (DT-CNN) with a C-template. In the proposed architecture, the A-template is used for a digital-to-analog converter (DAC), the C-template works as an integrator, and the nonlinear output function is used for the bilevel output. In addition, due to the cellular neural network (CNN) characteristics, each pixel of an image corresponds to a cell of a CNN, and each cell is connected spatially by the A-template. Therefore, the proposed system can be thought of as a very large-scale and super-parallel sigma-delta modulator. Moreover, the spatio-temporal dynamics is designed to obtain an optimal reconstruction signal. The experimental results show the excellent reconstruction performance and capabilities of the CNN as a sigma-delta modulator.

  19. Pattern Recognition of Momentary Mental Workload Based on Multi-Channel Electrophysiological Data and Ensemble Convolutional Neural Networks.

    Science.gov (United States)

    Zhang, Jianhua; Li, Sunan; Wang, Rubin

    2017-01-01

    In this paper, we deal with the Mental Workload (MWL) classification problem based on the measured physiological data. First we discussed the optimal depth (i.e., the number of hidden layers) and parameter optimization algorithms for the Convolutional Neural Networks (CNN). The base CNNs designed were tested according to five classification performance indices, namely Accuracy, Precision, F-measure, G-mean, and required training time. Then we developed an Ensemble Convolutional Neural Network (ECNN) to enhance the accuracy and robustness of the individual CNN model. For the ECNN design, three model aggregation approaches (weighted averaging, majority voting and stacking) were examined and a resampling strategy was used to enhance the diversity of individual CNN models. The results of MWL classification performance comparison indicated that the proposed ECNN framework can effectively improve MWL classification performance and is featured by entirely automatic feature extraction and MWL classification, when compared with traditional machine learning methods.

  20. Pattern Recognition of Momentary Mental Workload Based on Multi-Channel Electrophysiological Data and Ensemble Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Jianhua Zhang

    2017-05-01

    Full Text Available In this paper, we deal with the Mental Workload (MWL classification problem based on the measured physiological data. First we discussed the optimal depth (i.e., the number of hidden layers and parameter optimization algorithms for the Convolutional Neural Networks (CNN. The base CNNs designed were tested according to five classification performance indices, namely Accuracy, Precision, F-measure, G-mean, and required training time. Then we developed an Ensemble Convolutional Neural Network (ECNN to enhance the accuracy and robustness of the individual CNN model. For the ECNN design, three model aggregation approaches (weighted averaging, majority voting and stacking were examined and a resampling strategy was used to enhance the diversity of individual CNN models. The results of MWL classification performance comparison indicated that the proposed ECNN framework can effectively improve MWL classification performance and is featured by entirely automatic feature extraction and MWL classification, when compared with traditional machine learning methods.

  1. Building a Social Newsroom

    DEFF Research Database (Denmark)

    Zimmerman, Chris; Wessels, Henricus T. W. J.; Vatrapu, Ravi

    2015-01-01

    Insufficient data visualization in current social media tools is hampering opportunities to make effective meaning and take decisive action from social data. This paper presents the technical architecture of a prototype tool for Social Business Intelligence (SBI) under development. Adopting...

  2. The Social Newsroom

    DEFF Research Database (Denmark)

    Zimmerman, Chris; Vatrapu, Ravi

    reflection of consumers and brand advocates. Social media thus takes on a new relevance in forging relationships of brand co-creation. This research project, in its entirety, seeks to derive business value from social data by designing and developing a series of dashboards for those who struggle to interpret...

  3. The Social Newsroom

    DEFF Research Database (Denmark)

    Zimmerman, Christopher; Vatrapu, Ravi

    2015-01-01

    relevance in forging relationships of brand co-creation. The research project, in its entirety, seeks to derive business value from social data by designing and developing a series of dashboards for those who struggle to interpret and keep up with the social data created around a brand and marketing...

  4. Building a Social Newsroom

    OpenAIRE

    Zimmerman, Christopher J.; Wessels, Henricus T.W.J.; Vatrapu, Ravi

    2015-01-01

    Insufficient data visualization in current social media tools is hampering opportunities to make effective meaning and take decisive action from social data. This paper presents the technical architecture of a prototype tool for Social Business Intelligence (SBI) under development. Adopting an Action Design Research approach, the goal of the ‘Social Newsroom’ is to provide practitioners with user interfaces for leveraging such affordances. The construction of specific interfaces is detailed i...

  5. The Social Newsroom

    OpenAIRE

    Zimmerman, Chris; Vatrapu, Ravi

    2015-01-01

    Today, social media is widely adopted across personal and professional spheres. Increasingly businesses are utilizing social media as part of their strategy for communicating with and understanding the behaviors of their clients. The widespread public use of social media is a relatively new phenomenon that presents an ongoing, ever-changing challenge to companies and creates a unique set of risks as well as advantages to decision-makers. At the same time expansion into the online social sp...

  6. National Kidney Foundation Newsroom

    Science.gov (United States)

    ... Kidney Foundation - 04/10/2017 National University of Malaysia Researcher Honored by National Kidney Foundation - 04/10/ ... Organizations”, a special report in The New England Journal of Medicine - 03/01/2017 Industry News New ...

  7. Image quality assessment using deep convolutional networks

    Science.gov (United States)

    Li, Yezhou; Ye, Xiang; Li, Yong

    2017-12-01

    This paper proposes a method of accurately assessing image quality without a reference image by using a deep convolutional neural network. Existing training based methods usually utilize a compact set of linear filters for learning features of images captured by different sensors to assess their quality. These methods may not be able to learn the semantic features that are intimately related with the features used in human subject assessment. Observing this drawback, this work proposes training a deep convolutional neural network (CNN) with labelled images for image quality assessment. The ReLU in the CNN allows non-linear transformations for extracting high-level image features, providing a more reliable assessment of image quality than linear filters. To enable the neural network to take images of any arbitrary size as input, the spatial pyramid pooling (SPP) is introduced connecting the top convolutional layer and the fully-connected layer. In addition, the SPP makes the CNN robust to object deformations to a certain extent. The proposed method taking an image as input carries out an end-to-end learning process, and outputs the quality of the image. It is tested on public datasets. Experimental results show that it outperforms existing methods by a large margin and can accurately assess the image quality on images taken by different sensors of varying sizes.

  8. Traffic Command Gesture Recognition for Virtual Urban Scenes Based on a Spatiotemporal Convolution Neural Network

    Directory of Open Access Journals (Sweden)

    Chunyong Ma

    2018-01-01

    Full Text Available Intelligent recognition of traffic police command gestures increases authenticity and interactivity in virtual urban scenes. To actualize real-time traffic gesture recognition, a novel spatiotemporal convolution neural network (ST-CNN model is presented. We utilized Kinect 2.0 to construct a traffic police command gesture skeleton (TPCGS dataset collected from 10 volunteers. Subsequently, convolution operations on the locational change of each skeletal point were performed to extract temporal features, analyze the relative positions of skeletal points, and extract spatial features. After temporal and spatial features based on the three-dimensional positional information of traffic police skeleton points were extracted, the ST-CNN model classified positional information into eight types of Chinese traffic police gestures. The test accuracy of the ST-CNN model was 96.67%. In addition, a virtual urban traffic scene in which real-time command tests were carried out was set up, and a real-time test accuracy rate of 93.0% was achieved. The proposed ST-CNN model ensured a high level of accuracy and robustness. The ST-CNN model recognized traffic command gestures, and such recognition was found to control vehicles in virtual traffic environments, which enriches the interactive mode of the virtual city scene. Traffic command gesture recognition contributes to smart city construction.

  9. Standard Plane Localization in Fetal Ultrasound via Domain Transferred Deep Neural Networks.

    Science.gov (United States)

    Chen, Hao; Ni, Dong; Qin, Jing; Li, Shengli; Yang, Xin; Wang, Tianfu; Heng, Pheng Ann

    2015-09-01

    Automatic localization of the standard plane containing complicated anatomical structures in ultrasound (US) videos remains a challenging problem. In this paper, we present a learning-based approach to locate the fetal abdominal standard plane (FASP) in US videos by constructing a domain transferred deep convolutional neural network (CNN). Compared with previous works based on low-level features, our approach is able to represent the complicated appearance of the FASP and hence achieve better classification performance. More importantly, in order to reduce the overfitting problem caused by the small amount of training samples, we propose a transfer learning strategy, which transfers the knowledge in the low layers of a base CNN trained from a large database of natural images to our task-specific CNN. Extensive experiments demonstrate that our approach outperforms the state-of-the-art method for the FASP localization as well as the CNN only trained on the limited US training samples. The proposed approach can be easily extended to other similar medical image computing problems, which often suffer from the insufficient training samples when exploiting the deep CNN to represent high-level features.

  10. Contextual convolutional neural networks for lung nodule classification using Gaussian-weighted average image patches

    Science.gov (United States)

    Lee, Haeil; Lee, Hansang; Park, Minseok; Kim, Junmo

    2017-03-01

    Lung cancer is the most common cause of cancer-related death. To diagnose lung cancers in early stages, numerous studies and approaches have been developed for cancer screening with computed tomography (CT) imaging. In recent years, convolutional neural networks (CNN) have become one of the most common and reliable techniques in computer aided detection (CADe) and diagnosis (CADx) by achieving state-of-the-art-level performances for various tasks. In this study, we propose a CNN classification system for false positive reduction of initially detected lung nodule candidates. First, image patches of lung nodule candidates are extracted from CT scans to train a CNN classifier. To reflect the volumetric contextual information of lung nodules to 2D image patch, we propose a weighted average image patch (WAIP) generation by averaging multiple slice images of lung nodule candidates. Moreover, to emphasize central slices of lung nodules, slice images are locally weighted according to Gaussian distribution and averaged to generate the 2D WAIP. With these extracted patches, 2D CNN is trained to achieve the classification of WAIPs of lung nodule candidates into positive and negative labels. We used LUNA 2016 public challenge database to validate the performance of our approach for false positive reduction in lung CT nodule classification. Experiments show our approach improves the classification accuracy of lung nodules compared to the baseline 2D CNN with patches from single slice image.

  11. Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval

    Science.gov (United States)

    Zhou, Weixun; Newsam, Shawn; Li, Congmin; Shao, Zhenfeng

    2017-05-01

    Learning powerful feature representations for image retrieval has always been a challenging task in the field of remote sensing. Traditional methods focus on extracting low-level hand-crafted features which are not only time-consuming but also tend to achieve unsatisfactory performance due to the content complexity of remote sensing images. In this paper, we investigate how to extract deep feature representations based on convolutional neural networks (CNN) for high-resolution remote sensing image retrieval (HRRSIR). To this end, two effective schemes are proposed to generate powerful feature representations for HRRSIR. In the first scheme, the deep features are extracted from the fully-connected and convolutional layers of the pre-trained CNN models, respectively; in the second scheme, we propose a novel CNN architecture based on conventional convolution layers and a three-layer perceptron. The novel CNN model is then trained on a large remote sensing dataset to learn low dimensional features. The two schemes are evaluated on several public and challenging datasets, and the results indicate that the proposed schemes and in particular the novel CNN are able to achieve state-of-the-art performance.

  12. Cephalometric landmark detection in dental x-ray images using convolutional neural networks

    Science.gov (United States)

    Lee, Hansang; Park, Minseok; Kim, Junmo

    2017-03-01

    In dental X-ray images, an accurate detection of cephalometric landmarks plays an important role in clinical diagnosis, treatment and surgical decisions for dental problems. In this work, we propose an end-to-end deep learning system for cephalometric landmark detection in dental X-ray images, using convolutional neural networks (CNN). For detecting 19 cephalometric landmarks in dental X-ray images, we develop a detection system using CNN-based coordinate-wise regression systems. By viewing x- and y-coordinates of all landmarks as 38 independent variables, multiple CNN-based regression systems are constructed to predict the coordinate variables from input X-ray images. First, each coordinate variable is normalized by the length of either height or width of an image. For each normalized coordinate variable, a CNN-based regression system is trained on training images and corresponding coordinate variable, which is a variable to be regressed. We train 38 regression systems with the same CNN structure on coordinate variables, respectively. Finally, we compute 38 coordinate variables with these trained systems from unseen images and extract 19 landmarks by pairing the regressed coordinates. In experiments, the public database from the Grand Challenges in Dental X-ray Image Analysis in ISBI 2015 was used and the proposed system showed promising performance by successfully locating the cephalometric landmarks within considerable margins from the ground truths.

  13. AUTOMATIC ISOCONTOUR DETERMINATION FOR IODINE DOSE CALCULATION USING CELLULAR NEURAL NETWORKS ONSCINTIGRAPHIC IMAGES

    Directory of Open Access Journals (Sweden)

    Roger Lédée

    2012-01-01

    Full Text Available The hyperthyroid disease treatment consists in swallowing iodine 131. The quantity of these radio isotope results in an evaluation of the thyroid volume from a single scintigraphic image. In medical routine, the volume is calculated from a manual selection of an isocontour defining the boundary of the thyroid. We propose in this paper an automatic method to extract this boundary using Cellular Neural Network (CNN. Results show that our method is comparable to manual choice given by four experts. Studied on 35 patients with hyperthyroid diseases, we conclude that CNN is a comprising approach in segmentation of scintigraphic images.

  14. Deep convolutional neural networks for classifying head and neck cancer using hyperspectral imaging

    Science.gov (United States)

    Halicek, Martin; Lu, Guolan; Little, James V.; Wang, Xu; Patel, Mihir; Griffith, Christopher C.; El-Deiry, Mark W.; Chen, Amy Y.; Fei, Baowei

    2017-06-01

    Surgical cancer resection requires an accurate and timely diagnosis of the cancer margins in order to achieve successful patient remission. Hyperspectral imaging (HSI) has emerged as a useful, noncontact technique for acquiring spectral and optical properties of tissue. A convolutional neural network (CNN) classifier is developed to classify excised, squamous-cell carcinoma, thyroid cancer, and normal head and neck tissue samples using HSI. The CNN classification was validated by the manual annotation of a pathologist specialized in head and neck cancer. The preliminary results of 50 patients indicate the potential of HSI and deep learning for automatic tissue-labeling of surgical specimens of head and neck patients.

  15. Using convolutional neural networks for human activity classification on micro-Doppler radar spectrograms

    Science.gov (United States)

    Jordan, Tyler S.

    2016-05-01

    This paper presents the findings of using convolutional neural networks (CNNs) to classify human activity from micro-Doppler features. An emphasis on activities involving potential security threats such as holding a gun are explored. An automotive 24 GHz radar on chip was used to collect the data and a CNN (normally applied to image classification) was trained on the resulting spectrograms. The CNN achieves an error rate of 1.65 % on classifying running vs. walking, 17.3 % error on armed walking vs. unarmed walking, and 22 % on classifying six different actions.

  16. Combining convolutional neural networks and Hough Transform for classification of images containing lines

    Science.gov (United States)

    Sheshkus, Alexander; Limonova, Elena; Nikolaev, Dmitry; Krivtsov, Valeriy

    2017-03-01

    In this paper, we propose an expansion of convolutional neural network (CNN) input features based on Hough Transform. We perform morphological contrasting of source image followed by Hough Transform, and then use it as input for some convolutional filters. Thus, CNNs computational complexity and the number of units are not affected. Morphological contrasting and Hough Transform are the only additional computational expenses of introduced CNN input features expansion. Proposed approach was demonstrated on the example of CNN with very simple structure. We considered two image recognition problems, that were object classification on CIFAR-10 and printed character recognition on private dataset with symbols taken from Russian passports. Our approach allowed to reach noticeable accuracy improvement without taking much computational effort, which can be extremely important in industrial recognition systems or difficult problems utilising CNNs, like pressure ridge analysis and classification.

  17. An adaptive deep convolutional neural network for rolling bearing fault diagnosis

    Science.gov (United States)

    Fuan, Wang; Hongkai, Jiang; Haidong, Shao; Wenjing, Duan; Shuaipeng, Wu

    2017-09-01

    The working conditions of rolling bearings usually is very complex, which makes it difficult to diagnose rolling bearing faults. In this paper, a novel method called the adaptive deep convolutional neural network (CNN) is proposed for rolling bearing fault diagnosis. Firstly, to get rid of manual feature extraction, the deep CNN model is initialized for automatic feature learning. Secondly, to adapt to different signal characteristics, the main parameters of the deep CNN model are determined with a particle swarm optimization method. Thirdly, to evaluate the feature learning ability of the proposed method, t-distributed stochastic neighbor embedding (t-SNE) is further adopted to visualize the hierarchical feature learning process. The proposed method is applied to diagnose rolling bearing faults, and the results confirm that the proposed method is more effective and robust than other intelligent methods.

  18. A convolutional neural network approach to calibrating the rotation axis for X-ray computed tomography.

    Science.gov (United States)

    Yang, Xiaogang; De Carlo, Francesco; Phatak, Charudatta; Gürsoy, Dogˇa

    2017-03-01

    This paper presents an algorithm to calibrate the center-of-rotation for X-ray tomography by using a machine learning approach, the Convolutional Neural Network (CNN). The algorithm shows excellent accuracy from the evaluation of synthetic data with various noise ratios. It is further validated with experimental data of four different shale samples measured at the Advanced Photon Source and at the Swiss Light Source. The results are as good as those determined by visual inspection and show better robustness than conventional methods. CNN has also great potential for reducing or removing other artifacts caused by instrument instability, detector non-linearity, etc. An open-source toolbox, which integrates the CNN methods described in this paper, is freely available through GitHub at tomography/xlearn and can be easily integrated into existing computational pipelines available at various synchrotron facilities. Source code, documentation and information on how to contribute are also provided.

  19. Nonrigid image registration using multi-scale 3D convolutional neural networks

    NARCIS (Netherlands)

    Sokooti, Hessam; de Vos, Bob|info:eu-repo/dai/nl/413986004; Berendsen, Floris; Lelieveldt, Boudewijn P.F.; Išgum, Ivana|info:eu-repo/dai/nl/31484984X; Staring, Marius

    2017-01-01

    In this paper we propose a method to solve nonrigid image registration through a learning approach, instead of via iterative optimization of a predefined dissimilarity metric. We design a Convolutional Neural Network (CNN) architecture that, in contrast to all other work, directly estimates the

  20. Scene Text Detection and Segmentation based on Cascaded Convolution Neural Networks.

    Science.gov (United States)

    Tang, Youbao; Wu, Xiangqian

    2017-01-20

    Scene text detection and segmentation are two important and challenging research problems in the field of computer vision. This paper proposes a novel method for scene text detection and segmentation based on cascaded convolution neural networks (CNNs). In this method, a CNN based text-aware candidate text region (CTR) extraction model (named detection network, DNet) is designed and trained using both the edges and the whole regions of text, with which coarse CTRs are detected. A CNN based CTR refinement model (named segmentation network, SNet) is then constructed to precisely segment the coarse CTRs into text to get the refined CTRs. With DNet and SNet, much fewer CTRs are extracted than with traditional approaches while more true text regions are kept. The refined CTRs are finally classified using a CNN based CTR classification model (named classification network, CNet) to get the final text regions. All of these CNN based models are modified from VGGNet-16. Extensive experiments on three benchmark datasets demonstrate that the proposed method achieves state-of-the-art performance and greatly outperforms other scene text detection and segmentation approaches.

  1. Deep convolutional neural networks for dense non-uniform motion deblurring

    CSIR Research Space (South Africa)

    Cronje, J

    2015-11-01

    Full Text Available to form a dense non-uniform motion estimation map. Furthermore, a second CNN is trained to perform deblurring given a blurry image patch and the estimated motion vector. Combining the two trained networks result in a deep learning approach that can enhance...

  2. Localization of Origins of Premature Ventricular Contraction by Means of Convolutional Neural Network from 12-lead ECG.

    Science.gov (United States)

    Yang, Ting; Yu, Long; Jin, Qi; Wu, Liqun; He, Bin

    2017-09-25

    This paper proposes a novel method to localize origins of premature ventricular contractions (PVCs) from 12-lead electrocardiography (ECG) using convolutional neural network (CNN) and a realistic computer heart model. The proposed method consists of two CNNs (Segment CNN and Epi-Endo CNN) to classify among ventricular sources from 25 segments and from epicardium (Epi) or endocardium (Endo). The inputs are the full time courses and the first half of QRS complexes of 12-lead ECG, respectively. After registering the ventricle computer model with an individual patient's heart, the training datasets were generated by multiplying ventricular current dipoles derived from single pacing at various locations with patient-specific lead field. The origins of PVC are localized by calculating the weighted center of gravity of classification returned by the CNNs. A number of computer simulations were conducted to evaluate the proposed method under a variety of noise levels and heart registration errors. Furthermore, the proposed method was evaluated on 90 PVC beats from 9 human patients with PVCs and compared against ablation outcome in the same patients. The computer simulation evaluation returned relatively high accuracies for Segment CNN (∼78%) and Epi-Endo CNN (∼90%). Clinical testing in 9 PVC patients resulted an averaged localization error of 11 mm. Our simulation and clinical evaluation results demonstrate the capability and merits of the proposed CNN-based method for localization of PVC. This work suggests a new approach for cardiac source localization of origin of arrhythmias using only the 12-lead ECG by means of CNN, and may have important applications for future real-time monitoring and localizing origins of cardiac arrhythmias guiding ablation treatment.

  3. Determination of ionization energies of CnN (n=4-12): Vacuum-ultraviolet (VUV) photoionization experiments and theoretical calculations

    Energy Technology Data Exchange (ETDEWEB)

    Kostko, Oleg; Zhou, Jia; Sun, Bian Jian; Lie, Jie Shiuan; Chang, Agnes H.H.; Kaiser, Ralf I.; Ahmed, Musahid

    2010-06-10

    Results from single photon vacuum ultraviolet photoionization of astrophysically relevant CnN clusters, n = 4 - 12, in the photon energy range of 8.0 eV to 12.8 eV are presented. The experimental photoionization efficiency curves, combined with electronic structure calculations, provide improved ionization energies of the CnN species. A search through numerous nitrogen-terminated CnN isomers for n=4-9 indicates that the linear isomer has the lowest energy, and therefore should be the most abundant isomer in the molecular beam. Comparison with calculated results also shed light on the energetics of the linear CnN clusters, particularly in the trends of the even-carbon and the odd-carbon series. These results can help guide the search of potential astronomical observations of these neutral molecules together with their cations in highly ionized regions or regions with a high UV/VUV photon flux (ranging from the visible to VUV with flux maxima in the Lyman- region) in the interstellar medium.

  4. Determination of ionization energies of CnN (n=4-12): Vacuum-ultraviolet (VUV) photoionization experiments and theoretical calculations

    Energy Technology Data Exchange (ETDEWEB)

    Kostko, Oleg; Zhou, Jia; Sun, Bian Jian; Lie, Jie Shiuan; Chang, Agnes H.H.; Kaiser, Ralf I.; Ahmed, Musahid

    2010-03-02

    Results from single photon vacuum ultraviolet photoionization of astrophysically relevant CnN clusters, n = 4 - 12, in the photon energy range of 8.0 eV to 12.8 eV are presented. The experimental photoionization efficiency curves, combined with electronic structure calculations, provide improved ionization energies of the CnN species. A search through numerous nitrogen-terminated CnN isomers for n=4-9 indicates that the linear isomer has the lowest energy, and therefore should be the most abundant isomer in the molecular beam. Comparison with calculated results also shed light on the energetics of the linear CnN clusters, particularly in the trends of the even-carbon and the odd-carbon series. These results can help guide the search of potential astronomical observations of these neutral molecules together with their cations in highly ionized regions or regions with a high UV/VUV photon flux (ranging from the visible to VUV with flux maxima in the Lyman-a region) in the interstellar medium.

  5. A fast method for particle picking in cryo-electron micrographs based on fast R-CNN

    Science.gov (United States)

    Xiao, Yifan; Yang, Guangwen

    2017-06-01

    We propose a fast method to automatically pick protein particles in cryo-EM micrographs, which is now completed manually in practice. Our method is based on Fast R-CNN, with sliding window as the regions proposal solution. To reduce the false positive detections, we set a single class for the major contaminant ice, and pick out all the ice particles in the whole datasets. Tests on the recently-published cryo-EM data of three proteins have demonstrated that our approach can automatically accomplish the human-level particle picking task, and we successfully reduce the test time from 1.5 minutes of previous deep learning method to 2 seconds without any recall or precision losses. Our program is available under the MIT License at https://github.com/xiao1fan/FastParticlePicker.

  6. A Risk Factor Analysis of West Nile Virus: Extraction of Relationships from a Neural-Network Model

    Science.gov (United States)

    Ghosh, Debarchana; Guha, Rajarshi

    The West Nile Virus (WNV) is an infectious disease spreading rapidly throughout the United States, causing illness among thousands of birds, animals, and humans. The broad categories of risk factors underlying WNV incidences are: environmental, socioeconomic, built-environment, and existing mosquito abatement policies. Computational neural network (CNN) model was developed to understand the occurrence of WNV infected dead birds because of their ability to capture complex relationships with higher accuracy than linear models. In this paper, we describe a method to interpret a CNN model by considering the final optimized weights. The research was conducted in the Metropolitan area of Minnesota, which had experienced significant outbreaks from 2002 till present.

  7. Spatio-temporal analysis of brain electrical activity in epilepsy based on cellular nonlinear networks

    Science.gov (United States)

    Gollas, Frank; Tetzlaff, Ronald

    2009-05-01

    Epilepsy is the most common chronic disorder of the nervous system. Generally, epileptic seizures appear without foregoing sign or warning. The problem of detecting a possible pre-seizure state in epilepsy from EEG signals has been addressed by many authors over the past decades. Different approaches of time series analysis of brain electrical activity already are providing valuable insights into the underlying complex dynamics. But the main goal the identification of an impending epileptic seizure with a sufficient specificity and reliability, has not been achieved up to now. An algorithm for a reliable, automated prediction of epileptic seizures would enable the realization of implantable seizure warning devices, which could provide valuable information to the patient and time/event specific drug delivery or possibly a direct electrical nerve stimulation. Cellular Nonlinear Networks (CNN) are promising candidates for future seizure warning devices. CNN are characterized by local couplings of comparatively simple dynamical systems. With this property these networks are well suited to be realized as highly parallel, analog computer chips. Today available CNN hardware realizations exhibit a processing speed in the range of TeraOps combined with low power consumption. In this contribution new algorithms based on the spatio-temporal dynamics of CNN are considered in order to analyze intracranial EEG signals and thus taking into account mutual dependencies between neighboring regions of the brain. In an identification procedure Reaction-Diffusion CNN (RD-CNN) are determined for short segments of brain electrical activity, by means of a supervised parameter optimization. RD-CNN are deduced from Reaction-Diffusion Systems, which usually are applied to investigate complex phenomena like nonlinear wave propagation or pattern formation. The Local Activity Theory provides a necessary condition for emergent behavior in RD-CNN. In comparison linear spatio

  8. Bearings Fault Diagnosis Based on Convolutional Neural Networks with 2-D Representation of Vibration Signals as Input

    Directory of Open Access Journals (Sweden)

    Zhang Wei

    2017-01-01

    Full Text Available Periodic vibration signals captured by the accelerometers carry rich information for bearing fault diagnosis. Existing methods mostly rely on hand-crafted time-consuming preprocessing of data to acquire suitable features. In this paper, we use an easy and effective method to transform the 1-D temporal vibration signal into a 2-D image. With the signal image, convolutional Neural Network (CNN is used to train the raw vibration data. As powerful feature extractor and classifier for image recognition, CNN can learn to acquire features most suitable for the classification task by being trained. With the image format of vibration signals, the neuron in fully-connected layer of CNN can see farther and capture the periodic feature of signals. According to the results of the experiments, when fed in enough training samples, the proposed method outperforms other common methods. The proposed method can also be applied to solve intelligent diagnosis problems of other machine systems.

  9. Ultrasound image-based thyroid nodule automatic segmentation using convolutional neural networks.

    Science.gov (United States)

    Ma, Jinlian; Wu, Fa; Jiang, Tian'an; Zhao, Qiyu; Kong, Dexing

    2017-11-01

    Delineation of thyroid nodule boundaries from ultrasound images plays an important role in calculation of clinical indices and diagnosis of thyroid diseases. However, it is challenging for accurate and automatic segmentation of thyroid nodules because of their heterogeneous appearance and components similar to the background. In this study, we employ a deep convolutional neural network (CNN) to automatically segment thyroid nodules from ultrasound images. Our CNN-based method formulates a thyroid nodule segmentation problem as a patch classification task, where the relationship among patches is ignored. Specifically, the CNN used image patches from images of normal thyroids and thyroid nodules as inputs and then generated the segmentation probability maps as outputs. A multi-view strategy is used to improve the performance of the CNN-based model. Additionally, we compared the performance of our approach with that of the commonly used segmentation methods on the same dataset. The experimental results suggest that our proposed method outperforms prior methods on thyroid nodule segmentation. Moreover, the results show that the CNN-based model is able to delineate multiple nodules in thyroid ultrasound images accurately and effectively. In detail, our CNN-based model can achieve an average of the overlap metric, dice ratio, true positive rate, false positive rate, and modified Hausdorff distance as [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text] on overall folds, respectively. Our proposed method is fully automatic without any user interaction. Quantitative results also indicate that our method is so efficient and accurate that it can be good enough to replace the time-consuming and tedious manual segmentation approach, demonstrating the potential clinical applications.

  10. Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images.

    Science.gov (United States)

    Hirasawa, Toshiaki; Aoyama, Kazuharu; Tanimoto, Tetsuya; Ishihara, Soichiro; Shichijo, Satoki; Ozawa, Tsuyoshi; Ohnishi, Tatsuya; Fujishiro, Mitsuhiro; Matsuo, Keigo; Fujisaki, Junko; Tada, Tomohiro

    2018-01-15

    Image recognition using artificial intelligence with deep learning through convolutional neural networks (CNNs) has dramatically improved and been increasingly applied to medical fields for diagnostic imaging. We developed a CNN that can automatically detect gastric cancer in endoscopic images. A CNN-based diagnostic system was constructed based on Single Shot MultiBox Detector architecture and trained using 13,584 endoscopic images of gastric cancer. To evaluate the diagnostic accuracy, an independent test set of 2296 stomach images collected from 69 consecutive patients with 77 gastric cancer lesions was applied to the constructed CNN. The CNN required 47 s to analyze 2296 test images. The CNN correctly diagnosed 71 of 77 gastric cancer lesions with an overall sensitivity of 92.2%, and 161 non-cancerous lesions were detected as gastric cancer, resulting in a positive predictive value of 30.6%. Seventy of the 71 lesions (98.6%) with a diameter of 6 mm or more as well as all invasive cancers were correctly detected. All missed lesions were superficially depressed and differentiated-type intramucosal cancers that were difficult to distinguish from gastritis even for experienced endoscopists. Nearly half of the false-positive lesions were gastritis with changes in color tone or an irregular mucosal surface. The constructed CNN system for detecting gastric cancer could process numerous stored endoscopic images in a very short time with a clinically relevant diagnostic ability. It may be well applicable to daily clinical practice to reduce the burden of endoscopists.

  11. Recognition of prokaryotic and eukaryotic promoters using convolutional deep learning neural networks

    KAUST Repository

    Umarov, Ramzan

    2017-02-03

    Accurate computational identification of promoters remains a challenge as these key DNA regulatory regions have variable structures composed of functional motifs that provide gene-specific initiation of transcription. In this paper we utilize Convolutional Neural Networks (CNN) to analyze sequence characteristics of prokaryotic and eukaryotic promoters and build their predictive models. We trained a similar CNN architecture on promoters of five distant organisms: human, mouse, plant (Arabidopsis), and two bacteria (Escherichia coli and Bacillus subtilis). We found that CNN trained on sigma70 subclass of Escherichia coli promoter gives an excellent classification of promoters and non-promoter sequences (Sn = 0.90, Sp = 0.96, CC = 0.84). The Bacillus subtilis promoters identification CNN model achieves Sn = 0.91, Sp = 0.95, and CC = 0.86. For human, mouse and Arabidopsis promoters we employed CNNs for identification of two well-known promoter classes (TATA and non-TATA promoters). CNN models nicely recognize these complex functional regions. For human promoters Sn/Sp/CC accuracy of prediction reached 0.95/0.98/0,90 on TATA and 0.90/0.98/0.89 for non-TATA promoter sequences, respectively. For Arabidopsis we observed Sn/Sp/CC 0.95/0.97/0.91 (TATA) and 0.94/0.94/0.86 (non-TATA) promoters. Thus, the developed CNN models, implemented in CNNProm program, demonstrated the ability of deep learning approach to grasp complex promoter sequence characteristics and achieve significantly higher accuracy compared to the previously developed promoter prediction programs. We also propose random substitution procedure to discover positionally conserved promoter functional elements. As the suggested approach does not require knowledge of any specific promoter features, it can be easily extended to identify promoters and other complex functional regions in sequences of many other and especially newly sequenced genomes. The CNNProm program is available to run at web server http://www.softberry.com.

  12. A deep convolutional neural network model to classify heartbeats.

    Science.gov (United States)

    Acharya, U Rajendra; Oh, Shu Lih; Hagiwara, Yuki; Tan, Jen Hong; Adam, Muhammad; Gertych, Arkadiusz; Tan, Ru San

    2017-10-01

    The electrocardiogram (ECG) is a standard test used to monitor the activity of the heart. Many cardiac abnormalities will be manifested in the ECG including arrhythmia which is a general term that refers to an abnormal heart rhythm. The basis of arrhythmia diagnosis is the identification of normal versus abnormal individual heart beats, and their correct classification into different diagnoses, based on ECG morphology. Heartbeats can be sub-divided into five categories namely non-ectopic, supraventricular ectopic, ventricular ectopic, fusion, and unknown beats. It is challenging and time-consuming to distinguish these heartbeats on ECG as these signals are typically corrupted by noise. We developed a 9-layer deep convolutional neural network (CNN) to automatically identify 5 different categories of heartbeats in ECG signals. Our experiment was conducted in original and noise attenuated sets of ECG signals derived from a publicly available database. This set was artificially augmented to even out the number of instances the 5 classes of heartbeats and filtered to remove high-frequency noise. The CNN was trained using the augmented data and achieved an accuracy of 94.03% and 93.47% in the diagnostic classification of heartbeats in original and noise free ECGs, respectively. When the CNN was trained with highly imbalanced data (original dataset), the accuracy of the CNN reduced to 89.07%% and 89.3% in noisy and noise-free ECGs. When properly trained, the proposed CNN model can serve as a tool for screening of ECG to quickly identify different types and frequency of arrhythmic heartbeats. Copyright © 2017 Elsevier Ltd. All rights reserved.

  13. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation.

    Science.gov (United States)

    Kamnitsas, Konstantinos; Ledig, Christian; Newcombe, Virginia F J; Simpson, Joanna P; Kane, Andrew D; Menon, David K; Rueckert, Daniel; Glocker, Ben

    2017-02-01

    We propose a dual pathway, 11-layers deep, three-dimensional Convolutional Neural Network for the challenging task of brain lesion segmentation. The devised architecture is the result of an in-depth analysis of the limitations of current networks proposed for similar applications. To overcome the computational burden of processing 3D medical scans, we have devised an efficient and effective dense training scheme which joins the processing of adjacent image patches into one pass through the network while automatically adapting to the inherent class imbalance present in the data. Further, we analyze the development of deeper, thus more discriminative 3D CNNs. In order to incorporate both local and larger contextual information, we employ a dual pathway architecture that processes the input images at multiple scales simultaneously. For post-processing of the network's soft segmentation, we use a 3D fully connected Conditional Random Field which effectively removes false positives. Our pipeline is extensively evaluated on three challenging tasks of lesion segmentation in multi-channel MRI patient data with traumatic brain injuries, brain tumours, and ischemic stroke. We improve on the state-of-the-art for all three applications, with top ranking performance on the public benchmarks BRATS 2015 and ISLES 2015. Our method is computationally efficient, which allows its adoption in a variety of research and clinical settings. The source code of our implementation is made publicly available. Copyright © 2016 The Authors. Published by Elsevier B.V. All rights reserved.

  14. The Dynamical Recollection of Interconnected Neural Networks Using Meta-heuristics

    Science.gov (United States)

    Kuremoto, Takashi; Watanabe, Shun; Kobayashi, Kunikazu; Feng, Laing-Bing; Obayashi, Masanao

    The interconnected recurrent neural networks are well-known with their abilities of associative memory of characteristic patterns. For example, the traditional Hopfield network (HN) can recall stored pattern stably, meanwhile, Aihara's chaotic neural network (CNN) is able to realize dynamical recollection of a sequence of patterns. In this paper, we propose to use meta-heuristic (MH) methods such as the particle swarm optimization (PSO) and the genetic algorithm (GA) to improve traditional associative memory systems. Using PSO or GA, for CNN, optimal parameters are found to accelerate the recollection process and raise the rate of successful recollection, and for HN, optimized bias current is calculated to improve the network with dynamical association of a series of patterns. Simulation results of binary pattern association showed effectiveness of the proposed methods.

  15. A Novel Chaotic Neural Network Using Memristive Synapse with Applications in Associative Memory

    Directory of Open Access Journals (Sweden)

    Xiaofang Hu

    2012-01-01

    Full Text Available Chaotic Neural Network, also denoted by the acronym CNN, has rich dynamical behaviors that can be harnessed in promising engineering applications. However, due to its complex synapse learning rules and network structure, it is difficult to update its synaptic weights quickly and implement its large scale physical circuit. This paper addresses an implementation scheme of a novel CNN with memristive neural synapses that may provide a feasible solution for further development of CNN. Memristor, widely known as the fourth fundamental circuit element, was theoretically predicted by Chua in 1971 and has been developed in 2008 by the researchers in Hewlett-Packard Laboratory. Memristor based hybrid nanoscale CMOS technology is expected to revolutionize the digital and neuromorphic computation. The proposed memristive CNN has four significant features: (1 nanoscale memristors can simplify the synaptic circuit greatly and enable the synaptic weights update easily; (2 it can separate stored patterns from superimposed input; (3 it can deal with one-to-many associative memory; (4 it can deal with many-to-many associative memory. Simulation results are provided to illustrate the effectiveness of the proposed scheme.

  16. Cancer Hallmark Text Classification Using Convolutional Neural Networks

    OpenAIRE

    Baker, Simon; Korhonen, Anna-Leena; Pyysalo, S

    2017-01-01

    Methods based on deep learning approaches have recently achieved state-of-the-art performance in a range of machine learning tasks and are increasingly applied to natural language processing (NLP). Despite strong results in various established NLP tasks involving general domain texts, here is only limited work applying these models to biomedical NLP. In this paper, we consider a Convolutional Neural Network (CNN) approach to biomedical text classification. Evaluation using a recently intr...

  17. Conference "Internet, Web, What's next?" on 26 June 1998 at CERN: Mark Bernstein, Vice President of CNN Interactive, describes the impact of the Web on world media and predicts what we can expect as the next developments

    CERN Multimedia

    1998-01-01

    Conference "Internet, Web, What's next?" on 26 June 1998 at CERN: Mark Bernstein, Vice President of CNN Interactive, describes the impact of the Web on world media and predicts what we can expect as the next developments

  18. Spatio-Temporal Pain Recognition in CNN-based Super-Resolved Facial Images

    DEFF Research Database (Denmark)

    Bellantonio, Marco; Haque, Mohammad Ahsanul; Rodriguez, Pau

    2017-01-01

    Automatic pain detection is a long expected solution to a prevalent medical problem of pain management. This is more relevant when the subject of pain is young children or patients with limited ability to communicate about their pain experience. Computer vision-based analysis of facial pain...... to pain in each of the facial video frames, temporal axis information regarding to pain expression pattern in a subject video sequence, and variation of face resolution. We employed a combination of convolutional neural network and recurrent neural network to setup a deep hybrid pain detection framework...... that is able to exploit both spatial and temporal pain information from facial video. In order to analyze the effect of different facial resolutions, we introduce a super-resolution algorithm to generate facial video frames with different resolution setups. We investigated the performance on the publicly...

  19. What do We Learn by Semantic Scene Understanding for Remote Sensing imagery in CNN framework?

    OpenAIRE

    Li, Haifeng; Peng, Jian; Tao, Chao; Chen, Jie; Deng, Min

    2017-01-01

    Recently, deep convolutional neural network (DCNN) achieved increasingly remarkable success and rapidly developed in the field of natural image recognition. Compared with the natural image, the scale of remote sensing image is larger and the scene and the object it represents are more macroscopic. This study inquires whether remote sensing scene and natural scene recognitions differ and raises the following questions: What are the key factors in remote sensing scene recognition? Is the DCNN r...

  20. Infrared variation reduction by simultaneous background suppression and target contrast enhancement for deep convolutional neural network-based automatic target recognition

    Science.gov (United States)

    Kim, Sungho

    2017-06-01

    Automatic target recognition (ATR) is a traditionally challenging problem in military applications because of the wide range of infrared (IR) image variations and the limited number of training images. IR variations are caused by various three-dimensional target poses, noncooperative weather conditions (fog and rain), and difficult target acquisition environments. Recently, deep convolutional neural network-based approaches for RGB images (RGB-CNN) showed breakthrough performance in computer vision problems, such as object detection and classification. The direct use of RGB-CNN to the IR ATR problem fails to work because of the IR database problems (limited database size and IR image variations). An IR variation-reduced deep CNN (IVR-CNN) to cope with the problems is presented. The problem of limited IR database size is solved by a commercial thermal simulator (OKTAL-SE). The second problem of IR variations is mitigated by the proposed shifted ramp function-based intensity transformation. This can suppress the background and enhance the target contrast simultaneously. The experimental results on the synthesized IR images generated by the thermal simulator (OKTAL-SE) validated the feasibility of IVR-CNN for military ATR applications.

  1. Existence of periodic solutions for the discrete-time counterpart of a neutral-type cellular neural network with time-varying delays and impulses

    Science.gov (United States)

    Akça, Haydar; Al-Zahrani, Eadah; Covachev, Valéry; Covacheva, Zlatinka

    2017-07-01

    From the mathematical point of view, a cellular neural network (CNN) can be characterized by an array of identical nonlinear dynamical systems called cells (neurons) that are locally interconnected. Using the semi-discretization method, in the present talk we construct a discrete-time counterpart of a neutral-type CNN with time-varying delays and impulses. Sufficient conditions for the existence of periodic solutions of the discrete-time system thus obtained are found by using the continuation theorem of coincidence degree theory.

  2. Convolutional neural network architecture and input volume matrix design for ERP classifications in a tactile P300-based Brain-Computer Interface.

    Science.gov (United States)

    Kodama, Takumi; Makino, Shoji

    2017-07-01

    In the presented study we conduct the off-line ERP classification using the convolutional neural network (CNN) classifier for somatosensory ERP intervals acquired in the full- body tactile P300-based Brain-Computer Interface paradigm (fbBCI). The main objective of the study is to enhance fbBCI stimulus pattern classification accuracies by applying the CNN classifier. A 60 × 60 squared input volume transformed by one-dimensional somatosensory ERP intervals in each electrode channel is input to the convolutional architecture for a filter training. The flattened activation maps are evaluated by a multilayer perceptron with one-hidden-layer in order to calculate classification accuracy results. The proposed method reveals that the CNN classifier model can achieve a non-personal- training ERP classification with the fbBCI paradigm, scoring 100 % classification accuracy results for all the participated ten users.

  3. Does Al Jazeera make a difference? The framing of the Iranian election 2009 by Al Jazeera Arabic and CNN International

    Directory of Open Access Journals (Sweden)

    Susan Schenk

    2011-12-01

    Full Text Available The election in Iran 2009 caused a serious crisis in Iranian society. The news media around the world reported about alleged manipulation, election fraud and other irregularities. “Where is my vote?” became the rallying cry of Iran’s opposition. This paper presents a crossnational comparative media analysis of news reporting on the Iranian election and the subsequent national and international reactions. It focuses on how a controversial political event was covered by two of the world´s leading television news broadcasters: Al Jazeera Arabic and CNN International, with a particular focus on Al Jazeera. Two theoretical frameworks were adopted: a contra-flow approach – Al Jazeera as an alternative source of news – as well as its role with respect to democratization. Two flagship news programs were analyzed over a six-week period in summer 2009. With quantitative framing analysis as the central methodology (using statistical factor analysis, we focused on the content of 66 television news stories.

  4. Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network.

    Science.gov (United States)

    Anthimopoulos, Marios; Christodoulidis, Stergios; Ebner, Lukas; Christe, Andreas; Mougiakakou, Stavroula

    2016-05-01

    Automated tissue characterization is one of the most crucial components of a computer aided diagnosis (CAD) system for interstitial lung diseases (ILDs). Although much research has been conducted in this field, the problem remains challenging. Deep learning techniques have recently achieved impressive results in a variety of computer vision problems, raising expectations that they might be applied in other domains, such as medical image analysis. In this paper, we propose and evaluate a convolutional neural network (CNN), designed for the classification of ILD patterns. The proposed network consists of 5 convolutional layers with 2 × 2 kernels and LeakyReLU activations, followed by average pooling with size equal to the size of the final feature maps and three dense layers. The last dense layer has 7 outputs, equivalent to the classes considered: healthy, ground glass opacity (GGO), micronodules, consolidation, reticulation, honeycombing and a combination of GGO/reticulation. To train and evaluate the CNN, we used a dataset of 14696 image patches, derived by 120 CT scans from different scanners and hospitals. To the best of our knowledge, this is the first deep CNN designed for the specific problem. A comparative analysis proved the effectiveness of the proposed CNN against previous methods in a challenging dataset. The classification performance ( ~ 85.5%) demonstrated the potential of CNNs in analyzing lung patterns. Future work includes, extending the CNN to three-dimensional data provided by CT volume scans and integrating the proposed method into a CAD system that aims to provide differential diagnosis for ILDs as a supportive tool for radiologists.

  5. Multi-focus image fusion with the all convolutional neural network

    Science.gov (United States)

    Du, Chao-ben; Gao, She-sheng

    2018-01-01

    A decision map contains complete and clear information about the image to be fused, which is crucial to various image fusion issues, especially multi-focus image fusion. However, in order to get a satisfactory image fusion effect, getting a decision map is very necessary and usually difficult to finish. In this letter, we address this problem with convolutional neural network (CNN), aiming to get a state-of-the-art decision map. The main idea is that the max-pooling of CNN is replaced by a convolution layer, the residuals are propagated backwards by gradient descent, and the training parameters of the individual layers of the CNN are updated layer by layer. Based on this, we propose a new all CNN (ACNN)-based multi-focus image fusion method in spatial domain. We demonstrate that the decision map obtained from the ACNN is reliable and can lead to high-quality fusion results. Experimental results clearly validate that the proposed algorithm can obtain state-of-the-art fusion performance in terms of both qualitative and quantitative evaluations.

  6. A universal concept based on cellular neural networks for ultrafast and flexible solving of differential equations.

    Science.gov (United States)

    Chedjou, Jean Chamberlain; Kyamakya, Kyandoghere

    2015-04-01

    This paper develops and validates a comprehensive and universally applicable computational concept for solving nonlinear differential equations (NDEs) through a neurocomputing concept based on cellular neural networks (CNNs). High-precision, stability, convergence, and lowest-possible memory requirements are ensured by the CNN processor architecture. A significant challenge solved in this paper is that all these cited computing features are ensured in all system-states (regular or chaotic ones) and in all bifurcation conditions that may be experienced by NDEs.One particular quintessence of this paper is to develop and demonstrate a solver concept that shows and ensures that CNN processors (realized either in hardware or in software) are universal solvers of NDE models. The solving logic or algorithm of given NDEs (possible examples are: Duffing, Mathieu, Van der Pol, Jerk, Chua, Rössler, Lorenz, Burgers, and the transport equations) through a CNN processor system is provided by a set of templates that are computed by our comprehensive templates calculation technique that we call nonlinear adaptive optimization. This paper is therefore a significant contribution and represents a cutting-edge real-time computational engineering approach, especially while considering the various scientific and engineering applications of this ultrafast, energy-and-memory-efficient, and high-precise NDE solver concept. For illustration purposes, three NDE models are demonstratively solved, and related CNN templates are derived and used: the periodically excited Duffing equation, the Mathieu equation, and the transport equation.

  7. Indian Classical Dance Action Identification and Classification with Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    P. V. V. Kishore

    2018-01-01

    Full Text Available Extracting and recognizing complex human movements from unconstrained online/offline video sequence is a challenging task in computer vision. This paper proposes the classification of Indian classical dance actions using a powerful artificial intelligence tool: convolutional neural networks (CNN. In this work, human action recognition on Indian classical dance videos is performed on recordings from both offline (controlled recording and online (live performances, YouTube data. The offline data is created with ten different subjects performing 200 familiar dance mudras/poses from different Indian classical dance forms under various background environments. The online dance data is collected from YouTube for ten different subjects. Each dance pose is occupied for 60 frames or images in a video in both the cases. CNN training is performed with 8 different sample sizes, each consisting of multiple sets of subjects. The remaining 2 samples are used for testing the trained CNN. Different CNN architectures were designed and tested with our data to obtain a better accuracy in recognition. We achieved a 93.33% recognition rate compared to other classifier models reported on the same dataset.

  8. Objects Classification by Learning-Based Visual Saliency Model and Convolutional Neural Network

    Directory of Open Access Journals (Sweden)

    Na Li

    2016-01-01

    Full Text Available Humans can easily classify different kinds of objects whereas it is quite difficult for computers. As a hot and difficult problem, objects classification has been receiving extensive interests with broad prospects. Inspired by neuroscience, deep learning concept is proposed. Convolutional neural network (CNN as one of the methods of deep learning can be used to solve classification problem. But most of deep learning methods, including CNN, all ignore the human visual information processing mechanism when a person is classifying objects. Therefore, in this paper, inspiring the completed processing that humans classify different kinds of objects, we bring forth a new classification method which combines visual attention model and CNN. Firstly, we use the visual attention model to simulate the processing of human visual selection mechanism. Secondly, we use CNN to simulate the processing of how humans select features and extract the local features of those selected areas. Finally, not only does our classification method depend on those local features, but also it adds the human semantic features to classify objects. Our classification method has apparently advantages in biology. Experimental results demonstrated that our method made the efficiency of classification improve significantly.

  9. Deep convolutional neural network approach for forehead tissue thickness estimation

    Directory of Open Access Journals (Sweden)

    Manit Jirapong

    2017-09-01

    Full Text Available In this paper, we presented a deep convolutional neural network (CNN approach for forehead tissue thickness estimation. We use down sampled NIR laser backscattering images acquired from a novel marker-less near-infrared laser-based head tracking system, combined with the beam’s incident angle parameter. These two-channel augmented images were constructed for the CNN input, while a single node output layer represents the estimated value of the forehead tissue thickness. The models were – separately for each subject – trained and tested on datasets acquired from 30 subjects (high resolution MRI data is used as ground truth. To speed up training, we used a pre-trained network from the first subject to bootstrap training for each of the other subjects. We could show a clear improvement for the tissue thickness estimation (mean RMSE of 0.096 mm. This proposed CNN model outperformed previous support vector regression (mean RMSE of 0.155 mm or Gaussian processes learning approaches (mean RMSE of 0.114 mm and eliminated their restrictions for future research.

  10. Multi-Input Convolutional Neural Network for Flower Grading

    Directory of Open Access Journals (Sweden)

    Yu Sun

    2017-01-01

    Full Text Available Flower grading is a significant task because it is extremely convenient for managing the flowers in greenhouse and market. With the development of computer vision, flower grading has become an interdisciplinary focus in both botany and computer vision. A new dataset named BjfuGloxinia contains three quality grades; each grade consists of 107 samples and 321 images. A multi-input convolutional neural network is designed for large scale flower grading. Multi-input CNN achieves a satisfactory accuracy of 89.6% on the BjfuGloxinia after data augmentation. Compared with a single-input CNN, the accuracy of multi-input CNN is increased by 5% on average, demonstrating that multi-input convolutional neural network is a promising model for flower grading. Although data augmentation contributes to the model, the accuracy is still limited by lack of samples diversity. Majority of misclassification is derived from the medium class. The image processing based bud detection is useful for reducing the misclassification, increasing the accuracy of flower grading to approximately 93.9%.

  11. Glomerulus Classification and Detection Based on Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Jaime Gallego

    2018-01-01

    Full Text Available Glomerulus classification and detection in kidney tissue segments are key processes in nephropathology used for the correct diagnosis of the diseases. In this paper, we deal with the challenge of automating Glomerulus classification and detection from digitized kidney slide segments using a deep learning framework. The proposed method applies Convolutional Neural Networks (CNNs between two classes: Glomerulus and Non-Glomerulus, to detect the image segments belonging to Glomerulus regions. We configure the CNN with the public pre-trained AlexNet model and adapt it to our system by learning from Glomerulus and Non-Glomerulus regions extracted from training slides. Once the model is trained, labeling is performed by applying the CNN classification to the image blocks under analysis. The results of the method indicate that this technique is suitable for correct Glomerulus detection in Whole Slide Images (WSI, showing robustness while reducing false positive and false negative detections.

  12. An effective convolutional neural network model for Chinese sentiment analysis

    Science.gov (United States)

    Zhang, Yu; Chen, Mengdong; Liu, Lianzhong; Wang, Yadong

    2017-06-01

    Nowadays microblog is getting more and more popular. People are increasingly accustomed to expressing their opinions on Twitter, Facebook and Sina Weibo. Sentiment analysis of microblog has received significant attention, both in academia and in industry. So far, Chinese microblog exploration still needs lots of further work. In recent years CNN has also been used to deal with NLP tasks, and already achieved good results. However, these methods ignore the effective use of a large number of existing sentimental resources. For this purpose, we propose a Lexicon-based Sentiment Convolutional Neural Networks (LSCNN) model focus on Weibo's sentiment analysis, which combines two CNNs, trained individually base on sentiment features and word embedding, at the fully connected hidden layer. The experimental results show that our model outperforms the CNN model only with word embedding features on microblog sentiment analysis task.

  13. AUTOMATIC MUSCLE PERIMYSIUM ANNOTATION USING DEEP CONVOLUTIONAL NEURAL NETWORK.

    Science.gov (United States)

    Sapkota, Manish; Xing, Fuyong; Su, Hai; Yang, Lin

    2015-04-01

    Diseased skeletal muscle expresses mononuclear cell infiltration in the regions of perimysium. Accurate annotation or segmentation of perimysium can help biologists and clinicians to determine individualized patient treatment and allow for reasonable prognostication. However, manual perimysium annotation is time consuming and prone to inter-observer variations. Meanwhile, the presence of ambiguous patterns in muscle images significantly challenge many traditional automatic annotation algorithms. In this paper, we propose an automatic perimysium annotation algorithm based on deep convolutional neural network (CNN). We formulate the automatic annotation of perimysium in muscle images as a pixel-wise classification problem, and the CNN is trained to label each image pixel with raw RGB values of the patch centered at the pixel. The algorithm is applied to 82 diseased skeletal muscle images. We have achieved an average precision of 94% on the test dataset.

  14. Deep vector-based convolutional neural network approach for automatic recognition of colonies of induced pluripotent stem cells.

    Directory of Open Access Journals (Sweden)

    Muthu Subash Kavitha

    Full Text Available Pluripotent stem cells can potentially be used in clinical applications as a model for studying disease progress. This tracking of disease-causing events in cells requires constant assessment of the quality of stem cells. Existing approaches are inadequate for robust and automated differentiation of stem cell colonies. In this study, we developed a new model of vector-based convolutional neural network (V-CNN with respect to extracted features of the induced pluripotent stem cell (iPSC colony for distinguishing colony characteristics. A transfer function from the feature vectors to the virtual image was generated at the front of the CNN in order for classification of feature vectors of healthy and unhealthy colonies. The robustness of the proposed V-CNN model in distinguishing colonies was compared with that of the competitive support vector machine (SVM classifier based on morphological, textural, and combined features. Additionally, five-fold cross-validation was used to investigate the performance of the V-CNN model. The precision, recall, and F-measure values of the V-CNN model were comparatively higher than those of the SVM classifier, with a range of 87-93%, indicating fewer false positives and false negative rates. Furthermore, for determining the quality of colonies, the V-CNN model showed higher accuracy values based on morphological (95.5%, textural (91.0%, and combined (93.2% features than those estimated with the SVM classifier (86.7, 83.3, and 83.4%, respectively. Similarly, the accuracy of the feature sets using five-fold cross-validation was above 90% for the V-CNN model, whereas that yielded by the SVM model was in the range of 75-77%. We thus concluded that the proposed V-CNN model outperforms the conventional SVM classifier, which strongly suggests that it as a reliable framework for robust colony classification of iPSCs. It can also serve as a cost-effective quality recognition tool during culture and other experimental

  15. Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification

    Directory of Open Access Journals (Sweden)

    Bodo Rueckauer

    2017-12-01

    Full Text Available Spiking neural networks (SNNs can potentially offer an efficient way of doing inference because the neurons in the networks are sparsely activated and computations are event-driven. Previous work showed that simple continuous-valued deep Convolutional Neural Networks (CNNs can be converted into accurate spiking equivalents. These networks did not include certain common operations such as max-pooling, softmax, batch-normalization and Inception-modules. This paper presents spiking equivalents of these operations therefore allowing conversion of nearly arbitrary CNN architectures. We show conversion of popular CNN architectures, including VGG-16 and Inception-v3, into SNNs that produce the best results reported to date on MNIST, CIFAR-10 and the challenging ImageNet dataset. SNNs can trade off classification error rate against the number of available operations whereas deep continuous-valued neural networks require a fixed number of operations to achieve their classification error rate. From the examples of LeNet for MNIST and BinaryNet for CIFAR-10, we show that with an increase in error rate of a few percentage points, the SNNs can achieve more than 2x reductions in operations compared to the original CNNs. This highlights the potential of SNNs in particular when deployed on power-efficient neuromorphic spiking neuron chips, for use in embedded applications.

  16. Convolutional neural networks and face recognition task

    Science.gov (United States)

    Sochenkova, A.; Sochenkov, I.; Makovetskii, A.; Vokhmintsev, A.; Melnikov, A.

    2017-09-01

    Computer vision tasks are remaining very important for the last couple of years. One of the most complicated problems in computer vision is face recognition that could be used in security systems to provide safety and to identify person among the others. There is a variety of different approaches to solve this task, but there is still no universal solution that would give adequate results in some cases. Current paper presents following approach. Firstly, we extract an area containing face, then we use Canny edge detector. On the next stage we use convolutional neural networks (CNN) to finally solve face recognition and person identification task.

  17. Convolution neural networks for ship type recognition

    Science.gov (United States)

    Rainey, Katie; Reeder, John D.; Corelli, Alexander G.

    2016-05-01

    Algorithms to automatically recognize ship type from satellite imagery are desired for numerous maritime applications. This task is difficult, and example imagery accurately labeled with ship type is hard to obtain. Convolutional neural networks (CNNs) have shown promise in image recognition settings, but many of these applications rely on the availability of thousands of example images for training. This work attempts to under- stand for which types of ship recognition tasks CNNs might be well suited. We report the results of baseline experiments applying a CNN to several ship type classification tasks, and discuss many of the considerations that must be made in approaching this problem.

  18. Transforming Musical Signals through a Genre Classifying Convolutional Neural Network

    Science.gov (United States)

    Geng, S.; Ren, G.; Ogihara, M.

    2017-05-01

    Convolutional neural networks (CNNs) have been successfully applied on both discriminative and generative modeling for music-related tasks. For a particular task, the trained CNN contains information representing the decision making or the abstracting process. One can hope to manipulate existing music based on this 'informed' network and create music with new features corresponding to the knowledge obtained by the network. In this paper, we propose a method to utilize the stored information from a CNN trained on musical genre classification task. The network was composed of three convolutional layers, and was trained to classify five-second song clips into five different genres. After training, randomly selected clips were modified by maximizing the sum of outputs from the network layers. In addition to the potential of such CNNs to produce interesting audio transformation, more information about the network and the original music could be obtained from the analysis of the generated features since these features indicate how the network 'understands' the music.

  19. A two-step convolutional neural network based computer-aided detection scheme for automatically segmenting adipose tissue volume depicting on CT images.

    Science.gov (United States)

    Wang, Yunzhi; Qiu, Yuchen; Thai, Theresa; Moore, Kathleen; Liu, Hong; Zheng, Bin

    2017-06-01

    Accurately assessment of adipose tissue volume inside a human body plays an important role in predicting disease or cancer risk, diagnosis and prognosis. In order to overcome limitation of using only one subjectively selected CT image slice to estimate size of fat areas, this study aims to develop and test a computer-aided detection (CAD) scheme based on deep learning technique to automatically segment subcutaneous fat areas (SFA) and visceral fat areas (VFA) depicting on volumetric CT images. A retrospectively collected CT image dataset was divided into two independent training and testing groups. The proposed CAD framework consisted of two steps with two convolution neural networks (CNNs) namely, Selection-CNN and Segmentation-CNN. The first CNN was trained using 2,240 CT slices to select abdominal CT slices depicting SFA and VFA. The second CNN was trained with 84,000pixel patches and applied to the selected CT slices to identify fat-related pixels and assign them into SFA and VFA classes. Comparing to the manual CT slice selection and fat pixel segmentation results, the accuracy of CT slice selection using the Selection-CNN yielded 95.8%, while the accuracy of fat pixel segmentation using the Segmentation-CNN was 96.8%. This study demonstrated the feasibility of applying a new deep learning based CAD scheme to automatically recognize abdominal section of human body from CT scans and segment SFA and VFA from volumetric CT data with high accuracy or agreement with the manual segmentation results. Copyright © 2017 Elsevier B.V. All rights reserved.

  20. Convolutional neural networks for segmentation and object detection of human semen

    DEFF Research Database (Denmark)

    Nissen, Malte Stær; Krause, Oswin; Almstrup, Kristian

    2017-01-01

    We compare a set of convolutional neural network (CNN) architectures for the task of segmenting and detecting human sperm cells in an image taken from a semen sample. In contrast to previous work, samples are not stained or washed to allow for full sperm quality analysis, making analysis harder due...... are found by using connected components on the CNN predictions. We investigate optimization of a threshold parameter on the size of detected components. Our best network achieves 93.87% precision and 91.89% recall on our test dataset after thresholding outperforming a classical image analysis approach....... to clutter. Our results indicate that training on full images is superior to training on patches when class-skew is properly handled. Full image training including up-sampling during training proves to be beneficial in deep CNNs for pixel wise accuracy and detection performance. Predicted sperm cells...

  1. Pancreas Segmentation in MRI using Graph-Based Decision Fusion on Convolutional Neural Networks.

    Science.gov (United States)

    Cai, Jinzheng; Lu, Le; Zhang, Zizhao; Xing, Fuyong; Yang, Lin; Yin, Qian

    2016-10-01

    Automated pancreas segmentation in medical images is a prerequisite for many clinical applications, such as diabetes inspection, pancreatic cancer diagnosis, and surgical planing. In this paper, we formulate pancreas segmentation in magnetic resonance imaging (MRI) scans as a graph based decision fusion process combined with deep convolutional neural networks (CNN). Our approach conducts pancreatic detection and boundary segmentation with two types of CNN models respectively: 1) the tissue detection step to differentiate pancreas and non-pancreas tissue with spatial intensity context; 2) the boundary detection step to allocate the semantic boundaries of pancreas. Both detection results of the two networks are fused together as the initialization of a conditional random field (CRF) framework to obtain the final segmentation output. Our approach achieves the mean dice similarity coefficient (DSC) 76.1% with the standard deviation of 8.7% in a dataset containing 78 abdominal MRI scans. The proposed algorithm achieves the best results compared with other state of the arts.

  2. Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals.

    Science.gov (United States)

    Acharya, U Rajendra; Oh, Shu Lih; Hagiwara, Yuki; Tan, Jen Hong; Adeli, Hojjat

    2017-09-27

    An encephalogram (EEG) is a commonly used ancillary test to aide in the diagnosis of epilepsy. The EEG signal contains information about the electrical activity of the brain. Traditionally, neurologists employ direct visual inspection to identify epileptiform abnormalities. This technique can be time-consuming, limited by technical artifact, provides variable results secondary to reader expertise level, and is limited in identifying abnormalities. Therefore, it is essential to develop a computer-aided diagnosis (CAD) system to automatically distinguish the class of these EEG signals using machine learning techniques. This is the first study to employ the convolutional neural network (CNN) for analysis of EEG signals. In this work, a 13-layer deep convolutional neural network (CNN) algorithm is implemented to detect normal, preictal, and seizure classes. The proposed technique achieved an accuracy, specificity, and sensitivity of 88.67%, 90.00% and 95.00%, respectively. Copyright © 2017 Elsevier Ltd. All rights reserved.

  3. Cascaded ensemble of convolutional neural networks and handcrafted features for mitosis detection

    Science.gov (United States)

    Wang, Haibo; Cruz-Roa, Angel; Basavanhally, Ajay; Gilmore, Hannah; Shih, Natalie; Feldman, Mike; Tomaszewski, John; Gonzalez, Fabio; Madabhushi, Anant

    2014-03-01

    Breast cancer (BCa) grading plays an important role in predicting disease aggressiveness and patient outcome. A key component of BCa grade is mitotic count, which involves quantifying the number of cells in the process of dividing (i.e. undergoing mitosis) at a specific point in time. Currently mitosis counting is done manually by a pathologist looking at multiple high power fields on a glass slide under a microscope, an extremely laborious and time consuming process. The development of computerized systems for automated detection of mitotic nuclei, while highly desirable, is confounded by the highly variable shape and appearance of mitoses. Existing methods use either handcrafted features that capture certain morphological, statistical or textural attributes of mitoses or features learned with convolutional neural networks (CNN). While handcrafted features are inspired by the domain and the particular application, the data-driven CNN models tend to be domain agnostic and attempt to learn additional feature bases that cannot be represented through any of the handcrafted features. On the other hand, CNN is computationally more complex and needs a large number of labeled training instances. Since handcrafted features attempt to model domain pertinent attributes and CNN approaches are largely unsupervised feature generation methods, there is an appeal to attempting to combine these two distinct classes of feature generation strategies to create an integrated set of attributes that can potentially outperform either class of feature extraction strategies individually. In this paper, we present a cascaded approach for mitosis detection that intelligently combines a CNN model and handcrafted features (morphology, color and texture features). By employing a light CNN model, the proposed approach is far less demanding computationally, and the cascaded strategy of combining handcrafted features and CNN-derived features enables the possibility of maximizing performance by

  4. Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?

    Science.gov (United States)

    Tajbakhsh, Nima; Shin, Jae Y; Gurudu, Suryakanth R; Hurst, R Todd; Kendall, Christopher B; Gotway, Michael B; Jianming Liang

    2016-05-01

    Training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. A promising alternative is to fine-tune a CNN that has been pre-trained using, for instance, a large set of labeled natural images. However, the substantial differences between natural and medical images may advise against such knowledge transfer. In this paper, we seek to answer the following central question in the context of medical image analysis: Can the use of pre-trained deep CNNs with sufficient fine-tuning eliminate the need for training a deep CNN from scratch? To address this question, we considered four distinct medical imaging applications in three specialties (radiology, cardiology, and gastroenterology) involving classification, detection, and segmentation from three different imaging modalities, and investigated how the performance of deep CNNs trained from scratch compared with the pre-trained CNNs fine-tuned in a layer-wise manner. Our experiments consistently demonstrated that 1) the use of a pre-trained CNN with adequate fine-tuning outperformed or, in the worst case, performed as well as a CNN trained from scratch; 2) fine-tuned CNNs were more robust to the size of training sets than CNNs trained from scratch; 3) neither shallow tuning nor deep tuning was the optimal choice for a particular application; and 4) our layer-wise fine-tuning scheme could offer a practical way to reach the best performance for the application at hand based on the amount of available data.

  5. Deep Convolutional Neural Networks: Structure, Feature Extraction and Training

    Directory of Open Access Journals (Sweden)

    Namatēvs Ivars

    2017-12-01

    Full Text Available Deep convolutional neural networks (CNNs are aimed at processing data that have a known network like topology. They are widely used to recognise objects in images and diagnose patterns in time series data as well as in sensor data classification. The aim of the paper is to present theoretical and practical aspects of deep CNNs in terms of convolution operation, typical layers and basic methods to be used for training and learning. Some practical applications are included for signal and image classification. Finally, the present paper describes the proposed block structure of CNN for classifying crucial features from 3D sensor data.

  6. Systematic Assessment of the Impact of User Roles on Network Flow Patterns

    Science.gov (United States)

    2017-09-01

    Broadcasting Company BCC Bi-Connected Components CERT Computer Emergency Readiness Team CNN Cable News Network CTMC Continuous-Time Markov Chain DDoS ...detected. These and other Netflow-based anomaly detection systems can work very well for detecting scanning, DDoS or worm behaviors [57], and have...available bandwidth, DDoS attacks, and routing problems. To use Netflow as a means of monitoring user behavior however, it makes sense to isolate the

  7. Combining LiDAR Space Clustering and Convolutional Neural Networks for Pedestrian Detection

    OpenAIRE

    Matti, Damien; Ekenel, Hazim Kemal; Thiran, Jean-Philippe

    2017-01-01

    Pedestrian detection is an important component for safety of autonomous vehicles, as well as for traffic and street surveillance. There are extensive benchmarks on this topic and it has been shown to be a challenging problem when applied on real use-case scenarios. In purely image-based pedestrian detection approaches, the state-of-the-art results have been achieved with convolutional neural networks (CNN) and surprisingly few detection frameworks have been built upon multi-cue approaches. In...

  8. Two-phase deep convolutional neural network for reducing class skewness in histopathological images based breast cancer detection.

    Science.gov (United States)

    Wahab, Noorul; Khan, Asifullah; Lee, Yeon Soo

    2017-06-01

    Different types of breast cancer are affecting lives of women across the world. Common types include Ductal carcinoma in situ (DCIS), Invasive ductal carcinoma (IDC), Tubular carcinoma, Medullary carcinoma, and Invasive lobular carcinoma (ILC). While detecting cancer, one important factor is mitotic count - showing how rapidly the cells are dividing. But the class imbalance problem, due to the small number of mitotic nuclei in comparison to the overwhelming number of non-mitotic nuclei, affects the performance of classification models. This work presents a two-phase model to mitigate the class biasness issue while classifying mitotic and non-mitotic nuclei in breast cancer histopathology images through a deep convolutional neural network (CNN). First, nuclei are segmented out using blue ratio and global binary thresholding. In Phase-1 a CNN is then trained on the segmented out 80×80 pixel patches based on a standard dataset. Hard non-mitotic examples are identified and augmented; mitotic examples are oversampled by rotation and flipping; whereas non-mitotic examples are undersampled by blue ratio histogram based k-means clustering. Based on this information from Phase-1, the dataset is modified for Phase-2 in order to reduce the effects of class imbalance. The proposed CNN architecture and data balancing technique yielded an F-measure of 0.79, and outperformed all the methods relying on specific handcrafted features, as well as those using a combination of handcrafted and CNN-generated features. Copyright © 2017 Elsevier Ltd. All rights reserved.

  9. Animal Recognition System Based on Convolutional Neural Network

    Directory of Open Access Journals (Sweden)

    Tibor Trnovszky

    2017-01-01

    Full Text Available In this paper, the performances of well-known image recognition methods such as Principal Component Analysis (PCA, Linear Discriminant Analysis (LDA, Local Binary Patterns Histograms (LBPH and Support Vector Machine (SVM are tested and compared with proposed convolutional neural network (CNN for the recognition rate of the input animal images. In our experiments, the overall recognition accuracy of PCA, LDA, LBPH and SVM is demonstrated. Next, the time execution for animal recognition process is evaluated. The all experimental results on created animal database were conducted. This created animal database consist of 500 different subjects (5 classes/ 100 images for each class. The experimental result shows that the PCA features provide better results as LDA and LBPH for large training set. On the other hand, LBPH is better than PCA and LDA for small training data set. For proposed CNN we have obtained a recognition accuracy of 98%. The proposed method based on CNN outperforms the state of the art methods.

  10. Classifications of multispectral colorectal cancer tissues using convolution neural network

    Directory of Open Access Journals (Sweden)

    Hawraa Haj-Hassan

    2017-01-01

    Full Text Available Background: Colorectal cancer (CRC is the third most common cancer among men and women. Its diagnosis in early stages, typically done through the analysis of colon biopsy images, can greatly improve the chances of a successful treatment. This paper proposes to use convolution neural networks (CNNs to predict three tissue types related to the progression of CRC: benign hyperplasia (BH, intraepithelial neoplasia (IN, and carcinoma (Ca. Methods: Multispectral biopsy images of thirty CRC patients were retrospectively analyzed. Images of tissue samples were divided into three groups, based on their type (10 BH, 10 IN, and 10 Ca. An active contour model was used to segment image regions containing pathological tissues. Tissue samples were classified using a CNN containing convolution, max-pooling, and fully-connected layers. Available tissue samples were split into a training set, for learning the CNN parameters, and test set, for evaluating its performance. Results: An accuracy of 99.17% was obtained from segmented image regions, outperforming existing approaches based on traditional feature extraction, and classification techniques. Conclusions: Experimental results demonstrate the effectiveness of CNN for the classification of CRC tissue types, in particular when using presegmented regions of interest.

  11. A deep convolutional neural network for recognizing foods

    Science.gov (United States)

    Jahani Heravi, Elnaz; Habibi Aghdam, Hamed; Puig, Domenec

    2015-12-01

    Controlling the food intake is an efficient way that each person can undertake to tackle the obesity problem in countries worldwide. This is achievable by developing a smartphone application that is able to recognize foods and compute their calories. State-of-art methods are chiefly based on hand-crafted feature extraction methods such as HOG and Gabor. Recent advances in large-scale object recognition datasets such as ImageNet have revealed that deep Convolutional Neural Networks (CNN) possess more representation power than the hand-crafted features. The main challenge with CNNs is to find the appropriate architecture for each problem. In this paper, we propose a deep CNN which consists of 769; 988 parameters. Our experiments show that the proposed CNN outperforms the state-of-art methods and improves the best result of traditional methods 17%. Moreover, using an ensemble of two CNNs that have been trained two different times, we are able to improve the classification performance 21:5%.

  12. HLA class I binding prediction via convolutional neural networks.

    Science.gov (United States)

    Vang, Yeeleng S; Xie, Xiaohui

    2017-09-01

    Many biological processes are governed by protein-ligand interactions. One such example is the recognition of self and non-self cells by the immune system. This immune response process is regulated by the major histocompatibility complex (MHC) protein which is encoded by the human leukocyte antigen (HLA) complex. Understanding the binding potential between MHC and peptides can lead to the design of more potent, peptide-based vaccines and immunotherapies for infectious autoimmune diseases. We apply machine learning techniques from the natural language processing (NLP) domain to address the task of MHC-peptide binding prediction. More specifically, we introduce a new distributed representation of amino acids, name HLA-Vec, that can be used for a variety of downstream proteomic machine learning tasks. We then propose a deep convolutional neural network architecture, name HLA-CNN, for the task of HLA class I-peptide binding prediction. Experimental results show combining the new distributed representation with our HLA-CNN architecture achieves state-of-the-art results in the majority of the latest two Immune Epitope Database (IEDB) weekly automated benchmark datasets. We further apply our model to predict binding on the human genome and identify 15 genes with potential for self binding. Codes to generate the HLA-Vec and HLA-CNN are publicly available at: https://github.com/uci-cbcl/HLA-bind . xhx@ics.uci.edu. Supplementary data are available at Bioinformatics online.

  13. Village Building Identification Based on Ensemble Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Zhiling Guo

    2017-10-01

    Full Text Available In this study, we present the Ensemble Convolutional Neural Network (ECNN, an elaborate CNN frame formulated based on ensembling state-of-the-art CNN models, to identify village buildings from open high-resolution remote sensing (HRRS images. First, to optimize and mine the capability of CNN for village mapping and to ensure compatibility with our classification targets, a few state-of-the-art models were carefully optimized and enhanced based on a series of rigorous analyses and evaluations. Second, rather than directly implementing building identification by using these models, we exploited most of their advantages by ensembling their feature extractor parts into a stronger model called ECNN based on the multiscale feature learning method. Finally, the generated ECNN was applied to a pixel-level classification frame to implement object identification. The proposed method can serve as a viable tool for village building identification with high accuracy and efficiency. The experimental results obtained from the test area in Savannakhet province, Laos, prove that the proposed ECNN model significantly outperforms existing methods, improving overall accuracy from 96.64% to 99.26%, and kappa from 0.57 to 0.86.

  14. Single-trial EEG RSVP classification using convolutional neural networks

    Science.gov (United States)

    Shamwell, Jared; Lee, Hyungtae; Kwon, Heesung; Marathe, Amar R.; Lawhern, Vernon; Nothwang, William

    2016-05-01

    Traditionally, Brain-Computer Interfaces (BCI) have been explored as a means to return function to paralyzed or otherwise debilitated individuals. An emerging use for BCIs is in human-autonomy sensor fusion where physiological data from healthy subjects is combined with machine-generated information to enhance the capabilities of artificial systems. While human-autonomy fusion of physiological data and computer vision have been shown to improve classification during visual search tasks, to date these approaches have relied on separately trained classification models for each modality. We aim to improve human-autonomy classification performance by developing a single framework that builds codependent models of human electroencephalograph (EEG) and image data to generate fused target estimates. As a first step, we developed a novel convolutional neural network (CNN) architecture and applied it to EEG recordings of subjects classifying target and non-target image presentations during a rapid serial visual presentation (RSVP) image triage task. The low signal-to-noise ratio (SNR) of EEG inherently limits the accuracy of single-trial classification and when combined with the high dimensionality of EEG recordings, extremely large training sets are needed to prevent overfitting and achieve accurate classification from raw EEG data. This paper explores a new deep CNN architecture for generalized multi-class, single-trial EEG classification across subjects. We compare classification performance from the generalized CNN architecture trained across all subjects to the individualized XDAWN, HDCA, and CSP neural classifiers which are trained and tested on single subjects. Preliminary results show that our CNN meets and slightly exceeds the performance of the other classifiers despite being trained across subjects.

  15. A patch-based convolutional neural network for remote sensing image classification.

    Science.gov (United States)

    Sharma, Atharva; Liu, Xiuwen; Yang, Xiaojun; Shi, Di

    2017-11-01

    Availability of accurate land cover information over large areas is essential to the global environment sustainability; digital classification using medium-resolution remote sensing data would provide an effective method to generate the required land cover information. However, low accuracy of existing per-pixel based classification methods for medium-resolution data is a fundamental limiting factor. While convolutional neural networks (CNNs) with deep layers have achieved unprecedented improvements in object recognition applications that rely on fine image structures, they cannot be applied directly to medium-resolution data due to lack of such fine structures. In this paper, considering the spatial relation of a pixel to its neighborhood, we propose a new deep patch-based CNN system tailored for medium-resolution remote sensing data. The system is designed by incorporating distinctive characteristics of medium-resolution data; in particular, the system computes patch-based samples from multidimensional top of atmosphere reflectance data. With a test site from the Florida Everglades area (with a size of 771 square kilometers), the proposed new system has outperformed pixel-based neural network, pixel-based CNN and patch-based neural network by 24.36%, 24.23% and 11.52%, respectively, in overall classification accuracy. By combining the proposed deep CNN and the huge collection of medium-resolution remote sensing data, we believe that much more accurate land cover datasets can be produced over large areas. Copyright © 2017 Elsevier Ltd. All rights reserved.

  16. Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection.

    Science.gov (United States)

    Kim, Jihun; Kim, Jonghong; Jang, Gil-Jin; Lee, Minho

    2017-03-01

    Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance. Copyright © 2016 Elsevier Ltd. All rights reserved.

  17. Pedestrian detection in video surveillance using fully convolutional YOLO neural network

    Science.gov (United States)

    Molchanov, V. V.; Vishnyakov, B. V.; Vizilter, Y. V.; Vishnyakova, O. V.; Knyaz, V. A.

    2017-06-01

    More than 80% of video surveillance systems are used for monitoring people. Old human detection algorithms, based on background and foreground modelling, could not even deal with a group of people, to say nothing of a crowd. Recent robust and highly effective pedestrian detection algorithms are a new milestone of video surveillance systems. Based on modern approaches in deep learning, these algorithms produce very discriminative features that can be used for getting robust inference in real visual scenes. They deal with such tasks as distinguishing different persons in a group, overcome problem with sufficient enclosures of human bodies by the foreground, detect various poses of people. In our work we use a new approach which enables to combine detection and classification tasks into one challenge using convolution neural networks. As a start point we choose YOLO CNN, whose authors propose a very efficient way of combining mentioned above tasks by learning a single neural network. This approach showed competitive results with state-of-the-art models such as FAST R-CNN, significantly overcoming them in speed, which allows us to apply it in real time video surveillance and other video monitoring systems. Despite all advantages it suffers from some known drawbacks, related to the fully-connected layers that obstruct applying the CNN to images with different resolution. Also it limits the ability to distinguish small close human figures in groups which is crucial for our tasks since we work with rather low quality images which often include dense small groups of people. In this work we gradually change network architecture to overcome mentioned above problems, train it on a complex pedestrian dataset and finally get the CNN detecting small pedestrians in real scenes.

  18. Balance the nodule shape and surroundings: a new multichannel image based convolutional neural network scheme on lung nodule diagnosis

    Science.gov (United States)

    Sun, Wenqing; Zheng, Bin; Huang, Xia; Qian, Wei

    2017-03-01

    Deep learning is a trending promising method in medical image analysis area, but how to efficiently prepare the input image for the deep learning algorithms remains a challenge. In this paper, we introduced a novel artificial multichannel region of interest (ROI) generation procedure for convolutional neural networks (CNN). From LIDC database, we collected 54880 benign nodule samples and 59848 malignant nodule samples based on the radiologists' annotations. The proposed CNN consists of three pairs of convolutional layers and two fully connected layers. For each original ROI, two new ROIs were generated: one contains the segmented nodule which highlighted the nodule shape, and the other one contains the gradient of the original ROI which highlighted the textures. By combining the three channel images into a pseudo color ROI, the CNN was trained and tested on the new multichannel ROIs (multichannel ROI II). For the comparison, we generated another type of multichannel image by replacing the gradient image channel with a ROI contains whitened background region (multichannel ROI I). With the 5-fold cross validation evaluation method, the CNN using multichannel ROI II achieved the ROI based area under the curve (AUC) of 0.8823+/-0.0177, compared to the AUC of 0.8484+/-0.0204 generated by the original ROI. By calculating the average of ROI scores from one nodule, the lesion based AUC using multichannel ROI was 0.8793+/-0.0210. By comparing the convolved features maps from CNN using different types of ROIs, it can be noted that multichannel ROI II contains more accurate nodule shapes and surrounding textures.

  19. Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging.

    Science.gov (United States)

    Liu, Fang; Zhou, Zhaoye; Jang, Hyungseok; Samsonov, Alexey; Zhao, Gengyan; Kijowski, Richard

    2017-07-21

    To describe and evaluate a new fully automated musculoskeletal tissue segmentation method using deep convolutional neural network (CNN) and three-dimensional (3D) simplex deformable modeling to improve the accuracy and efficiency of cartilage and bone segmentation within the knee joint. A fully automated segmentation pipeline was built by combining a semantic segmentation CNN and 3D simplex deformable modeling. A CNN technique called SegNet was applied as the core of the segmentation method to perform high resolution pixel-wise multi-class tissue classification. The 3D simplex deformable modeling refined the output from SegNet to preserve the overall shape and maintain a desirable smooth surface for musculoskeletal structure. The fully automated segmentation method was tested using a publicly available knee image data set to compare with currently used state-of-the-art segmentation methods. The fully automated method was also evaluated on two different data sets, which include morphological and quantitative MR images with different tissue contrasts. The proposed fully automated segmentation method provided good segmentation performance with segmentation accuracy superior to most of state-of-the-art methods in the publicly available knee image data set. The method also demonstrated versatile segmentation performance on both morphological and quantitative musculoskeletal MR images with different tissue contrasts and spatial resolutions. The study demonstrates that the combined CNN and 3D deformable modeling approach is useful for performing rapid and accurate cartilage and bone segmentation within the knee joint. The CNN has promising potential applications in musculoskeletal imaging. Magn Reson Med, 2017. © 2017 International Society for Magnetic Resonance in Medicine. © 2017 International Society for Magnetic Resonance in Medicine.

  20. Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study.

    Science.gov (United States)

    Yasaka, Koichiro; Akai, Hiroyuki; Abe, Osamu; Kiryu, Shigeru

    2017-10-27

    Purpose To investigate diagnostic performance by using a deep learning method with a convolutional neural network (CNN) for the differentiation of liver masses at dynamic contrast agent-enhanced computed tomography (CT). Materials and Methods This clinical retrospective study used CT image sets of liver masses over three phases (noncontrast-agent enhanced, arterial, and delayed). Masses were diagnosed according to five categories (category A, classic hepatocellular carcinomas [HCCs]; category B, malignant liver tumors other than classic and early HCCs; category C, indeterminate masses or mass-like lesions [including early HCCs and dysplastic nodules] and rare benign liver masses other than hemangiomas and cysts; category D, hemangiomas; and category E, cysts). Supervised training was performed by using 55 536 image sets obtained in 2013 (from 460 patients, 1068 sets were obtained and they were augmented by a factor of 52 [rotated, parallel-shifted, strongly enlarged, and noise-added images were generated from the original images]). The CNN was composed of six convolutional, three maximum pooling, and three fully connected layers. The CNN was tested with 100 liver mass image sets obtained in 2016 (74 men and 26 women; mean age, 66.4 years ± 10.6 [standard deviation]; mean mass size, 26.9 mm ± 25.9; 21, nine, 35, 20, and 15 liver masses for categories A, B, C, D, and E, respectively). Training and testing were performed five times. Accuracy for categorizing liver masses with CNN model and the area under receiver operating characteristic curve for differentiating categories A-B versus categories C-E were calculated. Results Median accuracy of differential diagnosis of liver masses for test data were 0.84. Median area under the receiver operating characteristic curve for differentiating categories A-B from C-E was 0.92. Conclusion Deep learning with CNN showed high diagnostic performance in differentiation of liver masses at dynamic CT. (©) RSNA, 2017 Online

  1. Colonoscopic polyp detection using convolutional neural networks

    Science.gov (United States)

    Park, Sun Young; Sargent, Dusty

    2016-03-01

    Computer aided diagnosis (CAD) systems for medical image analysis rely on accurate and efficient feature extraction methods. Regardless of which type of classifier is used, the results will be limited if the input features are not diagnostically relevant and do not properly discriminate between the different classes of images. Thus, a large amount of research has been dedicated to creating feature sets that capture the salient features that physicians are able to observe in the images. Successful feature extraction reduces the semantic gap between the physician's interpretation and the computer representation of images, and helps to reduce the variability in diagnosis between physicians. Due to the complexity of many medical image classification tasks, feature extraction for each problem often requires domainspecific knowledge and a carefully constructed feature set for the specific type of images being classified. In this paper, we describe a method for automatic diagnostic feature extraction from colonoscopy images that may have general application and require a lower level of domain-specific knowledge. The work in this paper expands on our previous CAD algorithm for detecting polyps in colonoscopy video. In that work, we applied an eigenimage model to extract features representing polyps, normal tissue, diverticula, etc. from colonoscopy videos taken from various viewing angles and imaging conditions. Classification was performed using a conditional random field (CRF) model that accounted for the spatial and temporal adjacency relationships present in colonoscopy video. In this paper, we replace the eigenimage feature descriptor with features extracted from a convolutional neural network (CNN) trained to recognize the same image types in colonoscopy video. The CNN-derived features show greater invariance to viewing angles and image quality factors when compared to the eigenimage model. The CNN features are used as input to the CRF classifier as before. We report

  2. Agenda Trending: Reciprocity and the Predictive Capacity of Social Networking Sites in Intermedia Agenda Setting across Topics over Time

    OpenAIRE

    Jacob Groshek; Megan Clough Groshek

    2013-01-01

    In the contemporary converged media environment, agenda setting is being transformed by the dramatic growth of audiences that are simultaneously media users and producers. The study reported here addresses related gaps in the literature by first comparing the topical agendas of two leading traditional media outlets (New York Times and CNN) with the most frequently shared stories and trending topics on two widely popular Social Networking Sites (Facebook and Twitter). Time-series analyses of t...

  3. Motor Fault Diagnosis Based on Short-time Fourier Transform and Convolutional Neural Network

    Science.gov (United States)

    Wang, Li-Hua; Zhao, Xiao-Ping; Wu, Jia-Xin; Xie, Yang-Yang; Zhang, Yong-Hong

    2017-11-01

    With the rapid development of mechanical equipment, the mechanical health monitoring field has entered the era of big data. However, the method of manual feature extraction has the disadvantages of low efficiency and poor accuracy, when handling big data. In this study, the research object was the asynchronous motor in the drivetrain diagnostics simulator system. The vibration signals of different fault motors were collected. The raw signal was pretreated using short time Fourier transform (STFT) to obtain the corresponding time-frequency map. Then, the feature of the time-frequency map was adaptively extracted by using a convolutional neural network (CNN). The effects of the pretreatment method, and the hyper parameters of network diagnostic accuracy, were investigated experimentally. The experimental results showed that the influence of the preprocessing method is small, and that the batch-size is the main factor affecting accuracy and training efficiency. By investigating feature visualization, it was shown that, in the case of big data, the extracted CNN features can represent complex mapping relationships between signal and health status, and can also overcome the prior knowledge and engineering experience requirement for feature extraction, which is used by traditional diagnosis methods. This paper proposes a new method, based on STFT and CNN, which can complete motor fault diagnosis tasks more intelligently and accurately.

  4. DeepFruits: A Fruit Detection System Using Deep Neural Networks.

    Science.gov (United States)

    Sa, Inkyu; Ge, Zongyuan; Dayoub, Feras; Upcroft, Ben; Perez, Tristan; McCool, Chris

    2016-08-03

    This paper presents a novel approach to fruit detection using deep convolutional neural networks. The aim is to build an accurate, fast and reliable fruit detection system, which is a vital element of an autonomous agricultural robotic platform; it is a key element for fruit yield estimation and automated harvesting. Recent work in deep neural networks has led to the development of a state-of-the-art object detector termed Faster Region-based CNN (Faster R-CNN). We adapt this model, through transfer learning, for the task of fruit detection using imagery obtained from two modalities: colour (RGB) and Near-Infrared (NIR). Early and late fusion methods are explored for combining the multi-modal (RGB and NIR) information. This leads to a novel multi-modal Faster R-CNN model, which achieves state-of-the-art results compared to prior work with the F1 score, which takes into account both precision and recall performances improving from 0 . 807 to 0 . 838 for the detection of sweet pepper. In addition to improved accuracy, this approach is also much quicker to deploy for new fruits, as it requires bounding box annotation rather than pixel-level annotation (annotating bounding boxes is approximately an order of magnitude quicker to perform). The model is retrained to perform the detection of seven fruits, with the entire process taking four hours to annotate and train the new model per fruit.

  5. DeepFruits: A Fruit Detection System Using Deep Neural Networks

    Directory of Open Access Journals (Sweden)

    Inkyu Sa

    2016-08-01

    Full Text Available This paper presents a novel approach to fruit detection using deep convolutional neural networks. The aim is to build an accurate, fast and reliable fruit detection system, which is a vital element of an autonomous agricultural robotic platform; it is a key element for fruit yield estimation and automated harvesting. Recent work in deep neural networks has led to the development of a state-of-the-art object detector termed Faster Region-based CNN (Faster R-CNN. We adapt this model, through transfer learning, for the task of fruit detection using imagery obtained from two modalities: colour (RGB and Near-Infrared (NIR. Early and late fusion methods are explored for combining the multi-modal (RGB and NIR information. This leads to a novel multi-modal Faster R-CNN model, which achieves state-of-the-art results compared to prior work with the F1 score, which takes into account both precision and recall performances improving from 0 . 807 to 0 . 838 for the detection of sweet pepper. In addition to improved accuracy, this approach is also much quicker to deploy for new fruits, as it requires bounding box annotation rather than pixel-level annotation (annotating bounding boxes is approximately an order of magnitude quicker to perform. The model is retrained to perform the detection of seven fruits, with the entire process taking four hours to annotate and train the new model per fruit.

  6. Convolutional neural networks for P300 detection with application to brain-computer interfaces.

    Science.gov (United States)

    Cecotti, Hubert; Gräser, Axel

    2011-03-01

    A Brain-Computer Interface (BCI) is a specific type of human-computer interface that enables the direct communication between human and computers by analyzing brain measurements. Oddball paradigms are used in BCI to generate event-related potentials (ERPs), like the P300 wave, on targets selected by the user. A P300 speller is based on this principle, where the detection of P300 waves allows the user to write characters. The P300 speller is composed of two classification problems. The first classification is to detect the presence of a P300 in the electroencephalogram (EEG). The second one corresponds to the combination of different P300 responses for determining the right character to spell. A new method for the detection of P300 waves is presented. This model is based on a convolutional neural network (CNN). The topology of the network is adapted to the detection of P300 waves in the time domain. Seven classifiers based on the CNN are proposed: four single classifiers with different features set and three multiclassifiers. These models are tested and compared on the Data set II of the third BCI competition. The best result is obtained with a multiclassifier solution with a recognition rate of 95.5 percent, without channel selection before the classification. The proposed approach provides also a new way for analyzing brain activities due to the receptive field of the CNN models.

  7. Using Convolutional Neural Network Filters to Measure Left-Right Mirror Symmetry in Images

    Directory of Open Access Journals (Sweden)

    Anselm Brachmann

    2016-12-01

    Full Text Available We propose a method for measuring symmetry in images by using filter responses from Convolutional Neural Networks (CNNs. The aim of the method is to model human perception of left/right symmetry as closely as possible. Using the Convolutional Neural Network (CNN approach has two main advantages: First, CNN filter responses closely match the responses of neurons in the human visual system; they take information on color, edges and texture into account simultaneously. Second, we can measure higher-order symmetry, which relies not only on color, edges and texture, but also on the shapes and objects that are depicted in images. We validated our algorithm on a dataset of 300 music album covers, which were rated according to their symmetry by 20 human observers, and compared results with those from a previously proposed method. With our method, human perception of symmetry can be predicted with high accuracy. Moreover, we demonstrate that the inclusion of features from higher CNN layers, which encode more abstract image content, increases the performance further. In conclusion, we introduce a model of left/right symmetry that closely models human perception of symmetry in CD album covers.

  8. Spectral–Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network

    Directory of Open Access Journals (Sweden)

    Ying Li

    2017-01-01

    Full Text Available Recent research has shown that using spectral–spatial information can considerably improve the performance of hyperspectral image (HSI classification. HSI data is typically presented in the format of 3D cubes. Thus, 3D spatial filtering naturally offers a simple and effective method for simultaneously extracting the spectral–spatial features within such images. In this paper, a 3D convolutional neural network (3D-CNN framework is proposed for accurate HSI classification. The proposed method views the HSI cube data altogether without relying on any preprocessing or post-processing, extracting the deep spectral–spatial-combined features effectively. In addition, it requires fewer parameters than other deep learning-based methods. Thus, the model is lighter, less likely to over-fit, and easier to train. For comparison and validation, we test the proposed method along with three other deep learning-based HSI classification methods—namely, stacked autoencoder (SAE, deep brief network (DBN, and 2D-CNN-based methods—on three real-world HSI datasets captured by different sensors. Experimental results demonstrate that our 3D-CNN-based method outperforms these state-of-the-art methods and sets a new record.

  9. Classification of clinical significance of MRI prostate findings using 3D convolutional neural networks

    Science.gov (United States)

    Mehrtash, Alireza; Sedghi, Alireza; Ghafoorian, Mohsen; Taghipour, Mehdi; Tempany, Clare M.; Wells, William M.; Kapur, Tina; Mousavi, Parvin; Abolmaesumi, Purang; Fedorov, Andriy

    2017-03-01

    Prostate cancer (PCa) remains a leading cause of cancer mortality among American men. Multi-parametric magnetic resonance imaging (mpMRI) is widely used to assist with detection of PCa and characterization of its aggressiveness. Computer-aided diagnosis (CADx) of PCa in MRI can be used as clinical decision support system to aid radiologists in interpretation and reporting of mpMRI. We report on the development of a convolution neural network (CNN) model to support CADx in PCa based on the appearance of prostate tissue in mpMRI, conducted as part of the SPIE-AAPM-NCI PROSTATEx challenge. The performance of different combinations of mpMRI inputs to CNN was assessed and the best result was achieved using DWI and DCE-MRI modalities together with the zonal information of the finding. On the test set, the model achieved an area under the receiver operating characteristic curve of 0.80.

  10. Optical fingerprint identification using cellular neural network and joint transform correlation

    Science.gov (United States)

    Bal, Abdullah; Alam, Mohammad S.; El-Saba, Aed

    2004-10-01

    An important step in the fingerprint identification system is the extraction of relevant details against distributed complex features. Identification performance is directly related to the enhancement of fingerprint images during or after the enrollment phase. Among the various enhancement algorithms, artificial intelligence based feature extraction techniques are attractive due to their adaptive learning properties. In this paper, we propose a cellular neural network (CNN) based filtering technique due to its ability of parallel processing and generating learnable filtering features. CNN offers high efficient feature extraction and enhancement possibility for fingerprint images. The enhanced fingerprint images are then introduced to joint transform correlator (JTC) architecture to identify unknown fingerprint from the database. Since the fringe-adjusted JTC algorithm has been found to yield significantly better correlation output compared to alternate JTCs, we used it for the identification process. Test results are presented to verify the effectiveness of the proposed algorithm.

  11. Melanoma detection by analysis of clinical images using convolutional neural network.

    Science.gov (United States)

    Nasr-Esfahani, E; Samavi, S; Karimi, N; Soroushmehr, S M R; Jafari, M H; Ward, K; Najarian, K

    2016-08-01

    Melanoma, most threatening type of skin cancer, is on the rise. In this paper an implementation of a deep-learning system on a computer server, equipped with graphic processing unit (GPU), is proposed for detection of melanoma lesions. Clinical (non-dermoscopic) images are used in the proposed system, which could assist a dermatologist in early diagnosis of this type of skin cancer. In the proposed system, input clinical images, which could contain illumination and noise effects, are preprocessed in order to reduce such artifacts. Afterward, the enhanced images are fed to a pre-trained convolutional neural network (CNN) which is a member of deep learning models. The CNN classifier, which is trained by large number of training samples, distinguishes between melanoma and benign cases. Experimental results show that the proposed method is superior in terms of diagnostic accuracy in comparison with the state-of-the-art methods.

  12. Surgical-tools detection based on Convolutional Neural Network in laparoscopic robot-assisted surgery.

    Science.gov (United States)

    Bareum Choi; Kyungmin Jo; Songe Choi; Jaesoon Choi

    2017-07-01

    Laparoscopic surgery, a type of minimally invasive surgery, is used in a variety of clinical surgeries because it has a faster recovery rate and causes less pain. However, in general, the robotic system used in laparoscopic surgery can cause damage to the surgical instruments, organs, or tissues during surgery due to a narrow field of view and operating space, and insufficient tactile feedback. This study proposes real-time models for the detection of surgical instruments during laparoscopic surgery by using a CNN(Convolutional Neural Network). A dataset included information of the 7 surgical tools is used for learning CNN. To track surgical instruments in real time, unified architecture of YOLO apply to the models. So as to evaluate performance of the suggested models, degree of recall and precision is calculated and compared. Finally, we achieve 72.26% mean average precision over our dataset.

  13. Flare Occurrence Prediction based on Convolution Neural Network using SOHO MDI data

    Science.gov (United States)

    Yi, Kangwoo; Moon, Yong-Jae; Park, Eunsu; Shin, Seulki

    2017-08-01

    In this study we apply Convolution Neural Network(CNN) to solar flare occurrence prediction with various parameter options using the 00:00 UT MDI images from 1996 to 2010 (total 4962 images). We assume that only X, M and C class flares correspond to “flare occurrence” and the others to “non-flare”. We have attempted to look for the best options for the models with two CNN pre-trained models (AlexNet and GoogLeNet), by modifying training images and changing hyper parameters. Our major results from this study are as follows. First, the flare occurrence predictions are relatively good with about 80 % accuracies. Second, both flare prediction models based on AlexNet and GoogLeNet have similar results but AlexNet is faster than GoogLeNet. Third, modifying the training images to reduce the projection effect is not effective.

  14. Deep residual networks for automatic segmentation of laparoscopic videos of the liver

    Science.gov (United States)

    Gibson, Eli; Robu, Maria R.; Thompson, Stephen; Edwards, P. Eddie; Schneider, Crispin; Gurusamy, Kurinchi; Davidson, Brian; Hawkes, David J.; Barratt, Dean C.; Clarkson, Matthew J.

    2017-03-01

    Motivation: For primary and metastatic liver cancer patients undergoing liver resection, a laparoscopic approach can reduce recovery times and morbidity while offering equivalent curative results; however, only about 10% of tumours reside in anatomical locations that are currently accessible for laparoscopic resection. Augmenting laparoscopic video with registered vascular anatomical models from pre-procedure imaging could support using laparoscopy in a wider population. Segmentation of liver tissue on laparoscopic video supports the robust registration of anatomical liver models by filtering out false anatomical correspondences between pre-procedure and intra-procedure images. In this paper, we present a convolutional neural network (CNN) approach to liver segmentation in laparoscopic liver procedure videos. Method: We defined a CNN architecture comprising fully-convolutional deep residual networks with multi-resolution loss functions. The CNN was trained in a leave-one-patient-out cross-validation on 2050 video frames from 6 liver resections and 7 laparoscopic staging procedures, and evaluated using the Dice score. Results: The CNN yielded segmentations with Dice scores >=0.95 for the majority of images; however, the inter-patient variability in median Dice score was substantial. Four failure modes were identified from low scoring segmentations: minimal visible liver tissue, inter-patient variability in liver appearance, automatic exposure correction, and pathological liver tissue that mimics non-liver tissue appearance. Conclusion: CNNs offer a feasible approach for accurately segmenting liver from other anatomy on laparoscopic video, but additional data or computational advances are necessary to address challenges due to the high inter-patient variability in liver appearance.

  15. Low-complexity object detection with deep convolutional neural network for embedded systems

    Science.gov (United States)

    Tripathi, Subarna; Kang, Byeongkeun; Dane, Gokce; Nguyen, Truong

    2017-09-01

    We investigate low-complexity convolutional neural networks (CNNs) for object detection for embedded vision applications. It is well-known that consolidation of an embedded system for CNN-based object detection is more challenging due to computation and memory requirement comparing with problems like image classification. To achieve these requirements, we design and develop an end-to-end TensorFlow (TF)-based fully-convolutional deep neural network for generic object detection task inspired by one of the fastest framework, YOLO.1 The proposed network predicts the localization of every object by regressing the coordinates of the corresponding bounding box as in YOLO. Hence, the network is able to detect any objects without any limitations in the size of the objects. However, unlike YOLO, all the layers in the proposed network is fully-convolutional. Thus, it is able to take input images of any size. We pick face detection as an use case. We evaluate the proposed model for face detection on FDDB dataset and Widerface dataset. As another use case of generic object detection, we evaluate its performance on PASCAL VOC dataset. The experimental results demonstrate that the proposed network can predict object instances of different sizes and poses in a single frame. Moreover, the results show that the proposed method achieves comparative accuracy comparing with the state-of-the-art CNN-based object detection methods while reducing the model size by 3× and memory-BW by 3 - 4× comparing with one of the best real-time CNN-based object detectors, YOLO. Our 8-bit fixed-point TF-model provides additional 4× memory reduction while keeping the accuracy nearly as good as the floating-point model. Moreover, the fixed- point model is capable of achieving 20× faster inference speed comparing with the floating-point model. Thus, the proposed method is promising for embedded implementations.

  16. Multiscale Convolutional Neural Networks for Hand Detection

    Directory of Open Access Journals (Sweden)

    Shiyang Yan

    2017-01-01

    Full Text Available Unconstrained hand detection in still images plays an important role in many hand-related vision problems, for example, hand tracking, gesture analysis, human action recognition and human-machine interaction, and sign language recognition. Although hand detection has been extensively studied for decades, it is still a challenging task with many problems to be tackled. The contributing factors for this complexity include heavy occlusion, low resolution, varying illumination conditions, different hand gestures, and the complex interactions between hands and objects or other hands. In this paper, we propose a multiscale deep learning model for unconstrained hand detection in still images. Deep learning models, and deep convolutional neural networks (CNNs in particular, have achieved state-of-the-art performances in many vision benchmarks. Developed from the region-based CNN (R-CNN model, we propose a hand detection scheme based on candidate regions generated by a generic region proposal algorithm, followed by multiscale information fusion from the popular VGG16 model. Two benchmark datasets were applied to validate the proposed method, namely, the Oxford Hand Detection Dataset and the VIVA Hand Detection Challenge. We achieved state-of-the-art results on the Oxford Hand Detection Dataset and had satisfactory performance in the VIVA Hand Detection Challenge.

  17. A bi-hemispheric neuronal network model of the cerebellum with spontaneous climbing fiber firing produces asymmetrical motor learning during robot control

    Directory of Open Access Journals (Sweden)

    Ruben Dario Pinzon Morales

    2014-11-01

    Full Text Available To acquire and maintain precise movement controls over a lifespan, changes in the physical and physiological characteristics of muscles must be compensated for adaptively. The cerebellum plays a crucial role in such adaptation. Changes in muscle characteristics are not always symmetrical. For example, it is unlikely that muscles that bend and straighten a joint will change to the same degree. Thus, different (i.e., asymmetrical adaptation is required for bending and straightening motions. To date, little is known about the role of the cerebellum in asymmetrical adaptation. Here, we investigate the cerebellar mechanisms required for asymmetrical adaptation using a bi-hemispheric cerebellar neuronal network model (biCNN. The bi-hemispheric structure is inspired by the observation that lesioning one hemisphere reduces motor performance asymmetrically. The biCNN model was constructed to run in real-time and used to control an unstable two-wheeled balancing robot. The load of the robot and its environment were modified to create asymmetrical perturbations. Plasticity at parallel fiber-Purkinje cell synapses in the biCNN model was driven by error signal in the climbing fiber (cf input. This cf input was configured to increase and decrease its firing rate from its spontaneous firing rate (approximately 1 Hz with sensory errors in the preferred and non-preferred direction of each hemisphere, as demonstrated in the monkey cerebellum. Our results showed that asymmetrical conditions were successfully handled by the biCNN model, in contrast to a single hemisphere model or a classical non-adaptive proportional and derivative controller. Further, the spontaneous activity of the cf, while relatively small, was critical for balancing the contribution of each cerebellar hemisphere to the overall motor command sent to the robot. Eliminating the spontaneous activity compromised the asymmetrical learning capabilities of the biCNN model. Thus, we conclude that a bi

  18. Pedestrian Detection Based on Adaptive Selection of Visible Light or Far-Infrared Light Camera Image by Fuzzy Inference System and Convolutional Neural Network-Based Verification.

    Science.gov (United States)

    Kang, Jin Kyu; Hong, Hyung Gil; Park, Kang Ryoung

    2017-07-08

    A number of studies have been conducted to enhance the pedestrian detection accuracy of intelligent surveillance systems. However, detecting pedestrians under outdoor conditions is a challenging problem due to the varying lighting, shadows, and occlusions. In recent times, a growing number of studies have been performed on visible light camera-based pedestrian detection systems using a convolutional neural network (CNN) in order to make the pedestrian detection process more resilient to such conditions. However, visible light cameras still cannot detect pedestrians during nighttime, and are easily affected by shadows and lighting. There are many studies on CNN-based pedestrian detection through the use of far-infrared (FIR) light cameras (i.e., thermal cameras) to address such difficulties. However, when the solar radiation increases and the background temperature reaches the same level as the body temperature, it remains difficult for the FIR light camera to detect pedestrians due to the insignificant difference between the pedestrian and non-pedestrian features within the images. Researchers have been trying to solve this issue by inputting both the visible light and the FIR camera images into the CNN as the input. This, however, takes a longer time to process, and makes the system structure more complex as the CNN needs to process both camera images. This research adaptively selects a more appropriate candidate between two pedestrian images from visible light and FIR cameras based on a fuzzy inference system (FIS), and the selected candidate is verified with a CNN. Three types of databases were tested, taking into account various environmental factors using visible light and FIR cameras. The results showed that the proposed method performs better than the previously reported methods.

  19. Chinese Sentence Classification Based on Convolutional Neural Network

    Science.gov (United States)

    Gu, Chengwei; Wu, Ming; Zhang, Chuang

    2017-10-01

    Sentence classification is one of the significant issues in Natural Language Processing (NLP). Feature extraction is often regarded as the key point for natural language processing. Traditional ways based on machine learning can not take high level features into consideration, such as Naive Bayesian Model. The neural network for sentence classification can make use of contextual information to achieve greater results in sentence classification tasks. In this paper, we focus on classifying Chinese sentences. And the most important is that we post a novel architecture of Convolutional Neural Network (CNN) to apply on Chinese sentence classification. In particular, most of the previous methods often use softmax classifier for prediction, we embed a linear support vector machine to substitute softmax in the deep neural network model, minimizing a margin-based loss to get a better result. And we use tanh as an activation function, instead of ReLU. The CNN model improve the result of Chinese sentence classification tasks. Experimental results on the Chinese news title database validate the effectiveness of our model.

  20. Few-shot learning in deep networks through global prototyping.

    Science.gov (United States)

    Blaes, Sebastian; Burwick, Thomas

    2017-10-01

    Training a deep convolution neural network (CNN) to succeed in visual object classification usually requires a great number of examples. Here, starting from such a pre-learned CNN, we study the task of extending the network to classify additional categories on the basis of only few examples ("few-shot learning"). We find that a simple and fast prototype-based learning procedure in the global feature layers ("Global Prototype Learning", GPL) leads to some remarkably good classification results for a large portion of the new classes. It requires only up to ten examples for the new classes to reach a plateau in performance. To understand this few-shot learning performance resulting from GPL as well as the performance of the original network, we use the t-SNE method (Maaten and Hinton, 2008) to visualize clusters of object category examples. This reveals the strong connection between classification performance and data distribution and explains why some new categories only need few examples for learning while others resist good classification results even when trained with many more examples. Copyright © 2017 Elsevier Ltd. All rights reserved.

  1. Deep Convolutional Neural Networks for large-scale speech tasks.

    Science.gov (United States)

    Sainath, Tara N; Kingsbury, Brian; Saon, George; Soltau, Hagen; Mohamed, Abdel-rahman; Dahl, George; Ramabhadran, Bhuvana

    2015-04-01

    Convolutional Neural Networks (CNNs) are an alternative type of neural network that can be used to reduce spectral variations and model spectral correlations which exist in signals. Since speech signals exhibit both of these properties, we hypothesize that CNNs are a more effective model for speech compared to Deep Neural Networks (DNNs). In this paper, we explore applying CNNs to large vocabulary continuous speech recognition (LVCSR) tasks. First, we determine the appropriate architecture to make CNNs effective compared to DNNs for LVCSR tasks. Specifically, we focus on how many convolutional layers are needed, what is an appropriate number of hidden units, what is the best pooling strategy. Second, investigate how to incorporate speaker-adapted features, which cannot directly be modeled by CNNs as they do not obey locality in frequency, into the CNN framework. Third, given the importance of sequence training for speech tasks, we introduce a strategy to use ReLU+dropout during Hessian-free sequence training of CNNs. Experiments on 3 LVCSR tasks indicate that a CNN with the proposed speaker-adapted and ReLU+dropout ideas allow for a 12%-14% relative improvement in WER over a strong DNN system, achieving state-of-the art results in these 3 tasks. Copyright © 2014 Elsevier Ltd. All rights reserved.

  2. Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction

    OpenAIRE

    Dat Tien Nguyen; Ki Wan Kim; Hyung Gil Hong; Ja Hyung Koo; Min Cheol Kim; Kang Ryoung Park

    2017-01-01

    Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT), speed-up robust feature (SURF), local binary patterns (LBP), histogram of oriented gradients (HOG), and weighted HOG. Recently, the convolutional neural network (CNN) method for image feature extraction and classification in computer vision has ...

  3. Surgical tool detection in cataract surgery videos through multi-image fusion inside a convolutional neural network.

    Science.gov (United States)

    Al Hajj, Hassan; Lamard, Mathieu; Charriere, Katia; Cochener, Beatrice; Quellec, Gwenole

    2017-07-01

    The automatic detection of surgical tools in surgery videos is a promising solution for surgical workflow analysis. It paves the way to various applications, including surgical workflow optimization, surgical skill evaluation and real-time warning generation. A solution based on convolutional neural networks (CNNs) is proposed in this paper. Unlike existing solutions, the proposed CNN does not analyze images independently. it analyzes sequences of consecutive images. Features extracted from each image by the CNN are fused inside the network using the optical flow. For improved performance, this multi-image fusion strategy is also applied while training the CNN. The proposed framework was evaluated in a dataset of 30 cataract surgery videos (6 hours of videos). Ten tool categories were defined by surgeons. The proposed system was able to detect each of these categories with a high area under the ROC curve (0.953 ≤ Az ≤ 0.987). The proposed detector, based on multi-image fusion, was significantly more sensitive and specific than a similar system analyzing images independently (p = 2.98 × 10(-6) and p = 2.07 × 10(-3), respectively).

  4. Classification of mitotic figures with convolutional neural networks and seeded blob features.

    Science.gov (United States)

    Malon, Christopher D; Cosatto, Eric

    2013-01-01

    The mitotic figure recognition contest at the 2012 International Conference on Pattern Recognition (ICPR) challenges a system to identify all mitotic figures in a region of interest of hematoxylin and eosin stained tissue, using each of three scanners (Aperio, Hamamatsu, and multispectral). Our approach combines manually designed nuclear features with the learned features extracted by convolutional neural networks (CNN). The nuclear features capture color, texture, and shape information of segmented regions around a nucleus. The use of a CNN handles the variety of appearances of mitotic figures and decreases sensitivity to the manually crafted features and thresholds. On the test set provided by the contest, the trained system achieves F1 scores up to 0.659 on color scanners and 0.589 on multispectral scanner. We demonstrate a powerful technique combining segmentation-based features with CNN, identifying the majority of mitotic figures with a fair precision. Further, we show that the approach accommodates information from the additional focal planes and spectral bands from a multi-spectral scanner without major redesign.

  5. Classification of mitotic figures with convolutional neural networks and seeded blob features

    Directory of Open Access Journals (Sweden)

    Christopher D Malon

    2013-01-01

    Full Text Available Background: The mitotic figure recognition contest at the 2012 International Conference on Pattern Recognition (ICPR challenges a system to identify all mitotic figures in a region of interest of hematoxylin and eosin stained tissue, using each of three scanners (Aperio, Hamamatsu, and multispectral. Methods: Our approach combines manually designed nuclear features with the learned features extracted by convolutional neural networks (CNN. The nuclear features capture color, texture, and shape information of segmented regions around a nucleus. The use of a CNN handles the variety of appearances of mitotic figures and decreases sensitivity to the manually crafted features and thresholds. Results : On the test set provided by the contest, the trained system achieves F1 scores up to 0.659 on color scanners and 0.589 on multispectral scanner. Conclusions : We demonstrate a powerful technique combining segmentation-based features with CNN, identifying the majority of mitotic figures with a fair precision. Further, we show that the approach accommodates information from the additional focal planes and spectral bands from a multi-spectral scanner without major redesign.

  6. Application of Convolutional Neural Network in Classification of High Resolution Agricultural Remote Sensing Images

    Science.gov (United States)

    Yao, C.; Zhang, Y.; Zhang, Y.; Liu, H.

    2017-09-01

    With the rapid development of Precision Agriculture (PA) promoted by high-resolution remote sensing, it makes significant sense in management and estimation of agriculture through crop classification of high-resolution remote sensing image. Due to the complex and fragmentation of the features and the surroundings in the circumstance of high-resolution, the accuracy of the traditional classification methods has not been able to meet the standard of agricultural problems. In this case, this paper proposed a classification method for high-resolution agricultural remote sensing images based on convolution neural networks(CNN). For training, a large number of training samples were produced by panchromatic images of GF-1 high-resolution satellite of China. In the experiment, through training and testing on the CNN under the toolbox of deep learning by MATLAB, the crop classification finally got the correct rate of 99.66 % after the gradual optimization of adjusting parameter during training. Through improving the accuracy of image classification and image recognition, the applications of CNN provide a reference value for the field of remote sensing in PA.

  7. Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition

    Science.gov (United States)

    Yin, Xi; Liu, Xiaoming

    2018-02-01

    This paper explores multi-task learning (MTL) for face recognition. We answer the questions of how and why MTL can improve the face recognition performance. First, we propose a multi-task Convolutional Neural Network (CNN) for face recognition where identity classification is the main task and pose, illumination, and expression estimations are the side tasks. Second, we develop a dynamic-weighting scheme to automatically assign the loss weight to each side task, which is a crucial problem in MTL. Third, we propose a pose-directed multi-task CNN by grouping different poses to learn pose-specific identity features, simultaneously across all poses. Last but not least, we propose an energy-based weight analysis method to explore how CNN-based MTL works. We observe that the side tasks serve as regularizations to disentangle the variations from the learnt identity features. Extensive experiments on the entire Multi-PIE dataset demonstrate the effectiveness of the proposed approach. To the best of our knowledge, this is the first work using all data in Multi-PIE for face recognition. Our approach is also applicable to in-the-wild datasets for pose-invariant face recognition and achieves comparable or better performance than state of the art on LFW, CFP, and IJB-A datasets.

  8. Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes.

    Science.gov (United States)

    Luo, Yuan; Cheng, Yu; Uzuner, Özlem; Szolovits, Peter; Starren, Justin

    2018-01-01

    We propose Segment Convolutional Neural Networks (Seg-CNNs) for classifying relations from clinical notes. Seg-CNNs use only word-embedding features without manual feature engineering. Unlike typical CNN models, relations between 2 concepts are identified by simultaneously learning separate representations for text segments in a sentence: preceding, concept1, middle, concept2, and succeeding. We evaluate Seg-CNN on the i2b2/VA relation classification challenge dataset. We show that Seg-CNN achieves a state-of-the-art micro-average F-measure of 0.742 for overall evaluation, 0.686 for classifying medical problem-treatment relations, 0.820 for medical problem-test relations, and 0.702 for medical problem-medical problem relations. We demonstrate the benefits of learning segment-level representations. We show that medical domain word embeddings help improve relation classification. Seg-CNNs can be trained quickly for the i2b2/VA dataset on a graphics processing unit (GPU) platform. These results support the use of CNNs computed over segments of text for classifying medical relations, as they show state-of-the-art performance while requiring no manual feature engineering. © The Author 2017. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

  9. A convolutional neural network approach to calibrating the rotation axis for X-ray computed tomography

    Energy Technology Data Exchange (ETDEWEB)

    Yang, Xiaogang; De Carlo, Francesco; Phatak, Charudatta; Gürsoy, Dogˇa

    2017-01-24

    This paper presents an algorithm to calibrate the center-of-rotation for X-ray tomography by using a machine learning approach, the Convolutional Neural Network (CNN). The algorithm shows excellent accuracy from the evaluation of synthetic data with various noise ratios. It is further validated with experimental data of four different shale samples measured at the Advanced Photon Source and at the Swiss Light Source. The results are as good as those determined by visual inspection and show better robustness than conventional methods. CNN has also great potential forreducing or removingother artifacts caused by instrument instability, detector non-linearity,etc. An open-source toolbox, which integrates the CNN methods described in this paper, is freely available through GitHub at tomography/xlearn and can be easily integrated into existing computational pipelines available at various synchrotron facilities. Source code, documentation and information on how to contribute are also provided.

  10. Hyperspectral Image Spatial Super-Resolution via 3D Full Convolutional Neural Network

    Directory of Open Access Journals (Sweden)

    Shaohui Mei

    2017-11-01

    Full Text Available Hyperspectral images are well-known for their fine spectral resolution to discriminate different materials. However, their spatial resolution is relatively low due to the trade-off in imaging sensor technologies, resulting in limitations in their applications. Inspired by recent achievements in convolutional neural network (CNN based super-resolution (SR for natural images, a novel three-dimensional full CNN (3D-FCNN is constructed for spatial SR of hyperspectral images in this paper. Specifically, 3D convolution is used to exploit both the spatial context of neighboring pixels and spectral correlation of neighboring bands, such that spectral distortion when directly applying traditional CNN based SR algorithms to hyperspectral images in band-wise manners is alleviated. Furthermore, a sensor-specific mode is designed for the proposed 3D-FCNN such that none of the samples from the target scene are required for training. Fine-tuning by a small number of training samples from the target scene can further improve the performance of such a sensor-specific method. Extensive experimental results on four benchmark datasets from two well-known hyperspectral sensors, namely hyperspectral digital imagery collection experiment (HYDICE and reflective optics system imaging spectrometer (ROSIS sensors, demonstrate that our proposed 3D-FCNN outperforms several existing SR methods by ensuring higher quality both in reconstruction and spectral fidelity.

  11. APPLICATION OF CONVOLUTIONAL NEURAL NETWORK IN CLASSIFICATION OF HIGH RESOLUTION AGRICULTURAL REMOTE SENSING IMAGES

    Directory of Open Access Journals (Sweden)

    C. Yao

    2017-09-01

    Full Text Available With the rapid development of Precision Agriculture (PA promoted by high-resolution remote sensing, it makes significant sense in management and estimation of agriculture through crop classification of high-resolution remote sensing image. Due to the complex and fragmentation of the features and the surroundings in the circumstance of high-resolution, the accuracy of the traditional classification methods has not been able to meet the standard of agricultural problems. In this case, this paper proposed a classification method for high-resolution agricultural remote sensing images based on convolution neural networks(CNN. For training, a large number of training samples were produced by panchromatic images of GF-1 high-resolution satellite of China. In the experiment, through training and testing on the CNN under the toolbox of deep learning by MATLAB, the crop classification finally got the correct rate of 99.66 % after the gradual optimization of adjusting parameter during training. Through improving the accuracy of image classification and image recognition, the applications of CNN provide a reference value for the field of remote sensing in PA.

  12. Prediction of protein function using a deep convolutional neural network ensemble

    Directory of Open Access Journals (Sweden)

    Evangelia I. Zacharaki

    2017-07-01

    Full Text Available Background The availability of large databases containing high resolution three-dimensional (3D models of proteins in conjunction with functional annotation allows the exploitation of advanced supervised machine learning techniques for automatic protein function prediction. Methods In this work, novel shape features are extracted representing protein structure in the form of local (per amino acid distribution of angles and amino acid distances, respectively. Each of the multi-channel feature maps is introduced into a deep convolutional neural network (CNN for function prediction and the outputs are fused through support vector machines or a correlation-based k-nearest neighbor classifier. Two different architectures are investigated employing either one CNN per multi-channel feature set, or one CNN per image channel. Results Cross validation experiments on single-functional enzymes (n = 44,661 from the PDB database achieved 90.1% correct classification, demonstrating an improvement over previous results on the same dataset when sequence similarity was not considered. Discussion The automatic prediction of protein function can provide quick annotations on extensive datasets opening the path for relevant applications, such as pharmacological target identification. The proposed method shows promise for structure-based protein function prediction, but sufficient data may not yet be available to properly assess the method’s performance on non-homologous proteins and thus reduce the confounding factor of evolutionary relationships.

  13. A novel approach for tuberculosis screening based on deep convolutional neural networks

    Science.gov (United States)

    Hwang, Sangheum; Kim, Hyo-Eun; Jeong, Jihoon; Kim, Hee-Jin

    2016-03-01

    Tuberculosis (TB) is one of the major global health threats especially in developing countries. Although newly diagnosed TB patients can be recovered with high cure rate, many curable TB patients in the developing countries are obliged to die because of delayed diagnosis, partly by the lack of radiography and radiologists. Therefore, developing a computer-aided diagnosis (CAD) system for TB screening can contribute to early diagnosis of TB, which results in prevention of deaths from TB. Currently, most CAD algorithms adopt carefully designed morphological features distinguishing different lesion types to improve screening performances. However, such engineered features cannot be guaranteed to be the best descriptors for TB screening. Deep learning has become a majority in machine learning society. Especially in computer vision fields, it has been verified that deep convolutional neural networks (CNN) is a very promising algorithm for various visual tasks. Since deep CNN enables end-to-end training from feature extraction to classification, it does not require objective-specific manual feature engineering. In this work, we designed CAD system based on deep CNN for automatic TB screening. Based on large-scale chest X-rays (CXRs), we achieved viable TB screening performance of 0.96, 0.93 and 0.88 in terms of AUC for three real field datasets, respectively, by exploiting the effect of transfer learning.

  14. Automatic detection of lung nodules: false positive reduction using convolution neural networks and handcrafted features

    Science.gov (United States)

    Fu, Ling; Ma, Jingchen; Ren, Yacheng; Han, Youn Seon; Zhao, Jun

    2017-03-01

    Lung cancer is the leading cause of cancer deaths worldwide. Early diagnosis is critical in increasing the 5-year survival rate of lung cancer, so the efficient and accurate detection of lung nodules, potential precursors to lung cancer, is evermore important. In this paper, a computer-aided lung nodule detection system using convolution neural networks (CNN) and handcrafted features for false positive reduction is developed. The CNNs were trained with three types of images: lung CT images, their nodule-enhanced images, and their blood vessel-enhanced images. For each nodule candidate, nine 2D patches from differently oriented planes were extracted from each type of images. Patches of the same orientation from the same type of image across different candidates were used to train the CNNs independently, which were used to extract 864 features. 88 handcrafted features including intensity, shape, and texture features were also obtained from the lung CT images. The CNN features and handcrafted features were then combined to train a classifier, and a support vector machine was adopted to achieve the final classification results. The proposed method was evaluated on 1004 CT scans from the LIDC-IDRI database using 10-fold cross-validation. Compared with the traditional CNN method using only lung CT images, the proposed method boosted the sensitivity of nodule detection from 89.0% to 90.9% at 4 FPs/scan and from 71.6% to 78.2% at 1 FP/scan. This indicates that a combination of handcrafted features and CNN features from both lung CT images and enhanced images is a promising method for lung nodule detection.

  15. Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography.

    Science.gov (United States)

    Nakao, Takahiro; Hanaoka, Shouhei; Nomura, Yukihiro; Sato, Issei; Nemoto, Mitsutaka; Miki, Soichiro; Maeda, Eriko; Yoshikawa, Takeharu; Hayashi, Naoto; Abe, Osamu

    2017-08-24

    The usefulness of computer-assisted detection (CAD) for detecting cerebral aneurysms has been reported; therefore, the improved performance of CAD will help to detect cerebral aneurysms. To develop a CAD system for intracranial aneurysms on unenhanced magnetic resonance angiography (MRA) images based on a deep convolutional neural network (CNN) and a maximum intensity projection (MIP) algorithm, and to demonstrate the usefulness of the system by training and evaluating it using a large dataset. Retrospective study. There were 450 cases with intracranial aneurysms. The diagnoses of brain aneurysms were made on the basis of MRA, which was performed as part of a brain screening program. Noncontrast-enhanced 3D time-of-flight (TOF) MRA on 3T MR scanners. In our CAD, we used a CNN classifier that predicts whether each voxel is inside or outside aneurysms by inputting MIP images generated from a volume of interest (VOI) around the voxel. The CNN was trained in advance using manually inputted labels. We evaluated our method using 450 cases with intracranial aneurysms, 300 of which were used for training, 50 for parameter tuning, and 100 for the final evaluation. Free-response receiver operating characteristic (FROC) analysis. Our CAD system detected 94.2% (98/104) of aneurysms with 2.9 false positives per case (FPs/case). At a sensitivity of 70%, the number of FPs/case was 0.26. We showed that the combination of a CNN and an MIP algorithm is useful for the detection of intracranial aneurysms. 4 Technical Efficacy Stage 1 J. Magn. Reson. Imaging 2017. © 2017 International Society for Magnetic Resonance in Medicine.

  16. Lung nodule malignancy prediction using multi-task convolutional neural network

    Science.gov (United States)

    Li, Xiuli; Kao, Yueying; Shen, Wei; Li, Xiang; Xie, Guotong

    2017-03-01

    In this paper, we investigated the problem of diagnostic lung nodule malignancy prediction using thoracic Computed Tomography (CT) screening. Unlike most existing studies classify the nodules into two types benign and malignancy, we interpreted the nodule malignancy prediction as a regression problem to predict continuous malignancy level. We proposed a joint multi-task learning algorithm using Convolutional Neural Network (CNN) to capture nodule heterogeneity by extracting discriminative features from alternatingly stacked layers. We trained a CNN regression model to predict the nodule malignancy, and designed a multi-task learning mechanism to simultaneously share knowledge among 9 different nodule characteristics (Subtlety, Calcification, Sphericity, Margin, Lobulation, Spiculation, Texture, Diameter and Malignancy), and improved the final prediction result. Each CNN would generate characteristic-specific feature representations, and then we applied multi-task learning on the features to predict the corresponding likelihood for that characteristic. We evaluated the proposed method on 2620 nodules CT scans from LIDC-IDRI dataset with the 5-fold cross validation strategy. The multitask CNN regression result for regression RMSE and mapped classification ACC were 0.830 and 83.03%, while the results for single task regression RMSE 0.894 and mapped classification ACC 74.9%. Experiments show that the proposed method could predict the lung nodule malignancy likelihood effectively and outperforms the state-of-the-art methods. The learning framework could easily be applied in other anomaly likelihood prediction problem, such as skin cancer and breast cancer. It demonstrated the possibility of our method facilitating the radiologists for nodule staging assessment and individual therapeutic planning.

  17. Optimal Seamline Detection for Orthoimage Mosaicking by Combining Deep Convolutional Neural Network and Graph Cuts

    Directory of Open Access Journals (Sweden)

    Li Li

    2017-07-01

    Full Text Available When mosaicking orthoimages, especially in urban areas with various obvious ground objects like buildings, roads, cars or trees, the detection of optimal seamlines is one of the key technologies for creating seamless and pleasant image mosaics. In this paper, we propose a new approach to detect optimal seamlines for orthoimage mosaicking with the use of deep convolutional neural network (CNN and graph cuts. Deep CNNs have been widely used in many fields of computer vision and photogrammetry in recent years, and graph cuts is one of the most widely used energy optimization frameworks. We first propose a deep CNN for land cover semantic segmentation in overlap regions between two adjacent images. Then, the energy cost of each pixel in the overlap regions is defined based on the classification probabilities of belonging to each of the specified classes. To find the optimal seamlines globally, we fuse the CNN-classified energy costs of all pixels into the graph cuts energy minimization framework. The main advantage of our proposed method is that the pixel similarity energy costs between two images are defined using the classification results of the CNN based semantic segmentation instead of using the image informations of color, gradient or texture as traditional methods do. Another advantage of our proposed method is that the semantic informations are fully used to guide the process of optimal seamline detection, which is more reasonable than only using the hand designed features defined to represent the image differences. Finally, the experimental results on several groups of challenging orthoimages show that the proposed method is capable of finding high-quality seamlines among urban and non-urban orthoimages, and outperforms the state-of-the-art algorithms and the commercial software based on the visual comparison, statistical evaluation and quantitative evaluation based on the structural similarity (SSIM index.

  18. SLIDE: automatic spine level identification system using a deep convolutional neural network.

    Science.gov (United States)

    Hetherington, Jorden; Lessoway, Victoria; Gunka, Vit; Abolmaesumi, Purang; Rohling, Robert

    2017-07-01

    Percutaneous spinal needle insertion procedures often require proper identification of the vertebral level to effectively and safely deliver analgesic agents. The current clinical method involves "blind" identification of the vertebral level through manual palpation of the spine, which has only 30% reported accuracy. Therefore, there is a need for better anatomical identification prior to needle insertion. A real-time system was developed to identify the vertebral level from a sequence of ultrasound images, following a clinical imaging protocol. The system uses a deep convolutional neural network (CNN) to classify transverse images of the lower spine. Several existing CNN architectures were implemented, utilizing transfer learning, and compared for adequacy in a real-time system. In the system, the CNN output is processed, using a novel state machine, to automatically identify vertebral levels as the transducer moves up the spine. Additionally, a graphical display was developed and integrated within 3D Slicer. Finally, an augmented reality display, projecting the level onto the patient's back, was also designed. A small feasibility study [Formula: see text] evaluated performance. The proposed CNN successfully discriminates ultrasound images of the sacrum, intervertebral gaps, and vertebral bones, achieving 88% 20-fold cross-validation accuracy. Seventeen of 20 test ultrasound scans had successful identification of all vertebral levels, processed at real-time speed (40 frames/s). A machine learning system is presented that successfully identifies lumbar vertebral levels. The small study on human subjects demonstrated real-time performance. A projection-based augmented reality display was used to show the vertebral level directly on the subject adjacent to the puncture site.

  19. Finding strong gravitational lenses in the Kilo Degree Survey with Convolutional Neural Networks

    Science.gov (United States)

    Petrillo, C. E.; Tortora, C.; Chatterjee, S.; Vernardos, G.; Koopmans, L. V. E.; Verdoes Kleijn, G.; Napolitano, N. R.; Covone, G.; Schneider, P.; Grado, A.; McFarland, J.

    2017-11-01

    The volume of data that will be produced by new-generation surveys requires automatic classification methods to select and analyse sources. Indeed, this is the case for the search for strong gravitational lenses, where the population of the detectable lensed sources is only a very small fraction of the full source population. We apply for the first time a morphological classification method based on a Convolutional Neural Network (CNN) for recognizing strong gravitational lenses in 255 deg2 of the Kilo Degree Survey (KiDS), one of the current-generation optical wide surveys. The CNN is currently optimized to recognize lenses with Einstein radii ≳1.4 arcsec, about twice the r-band seeing in KiDS. In a sample of 21 789 colour-magnitude selected luminous red galaxies (LRGs), of which three are known lenses, the CNN retrieves 761 strong-lens candidates and correctly classifies two out of three of the known lenses. The misclassified lens has an Einstein radius below the range on which the algorithm is trained. We down-select the most reliable 56 candidates by a joint visual inspection. This final sample is presented and discussed. A conservative estimate based on our results shows that with our proposed method it should be possible to find ∼100 massive LRG-galaxy lenses at z ≲ 0.4 in KiDS when completed. In the most optimistic scenario, this number can grow considerably (to maximally ∼2400 lenses), when widening the colour-magnitude selection and training the CNN to recognize smaller image-separation lens systems.

  20. Esophagus segmentation in CT via 3D fully convolutional neural network and random walk.

    Science.gov (United States)

    Fechter, Tobias; Adebahr, Sonja; Baltas, Dimos; Ben Ayed, Ismail; Desrosiers, Christian; Dolz, Jose

    2017-12-01

    Precise delineation of organs at risk is a crucial task in radiotherapy treatment planning for delivering high doses to the tumor while sparing healthy tissues. In recent years, automated segmentation methods have shown an increasingly high performance for the delineation of various anatomical structures. However, this task remains challenging for organs like the esophagus, which have a versatile shape and poor contrast to neighboring tissues. For human experts, segmenting the esophagus from CT images is a time-consuming and error-prone process. To tackle these issues, we propose a random walker approach driven by a 3D fully convolutional neural network (CNN) to automatically segment the esophagus from CT images. First, a soft probability map is generated by the CNN. Then, an active contour model (ACM) is fitted to the CNN soft probability map to get a first estimation of the esophagus location. The outputs of the CNN and ACM are then used in conjunction with a probability model based on CT Hounsfield (HU) values to drive the random walker. Training and evaluation were done on 50 CTs from two different datasets, with clinically used peer-reviewed esophagus contours. Results were assessed regarding spatial overlap and shape similarity. The esophagus contours generated by the proposed algorithm showed a mean Dice coefficient of 0.76 ± 0.11, an average symmetric square distance of 1.36 ± 0.90 mm, and an average Hausdorff distance of 11.68 ± 6.80, compared to the reference contours. These results translate to a very good agreement with reference contours and an increase in accuracy compared to existing methods. Furthermore, when considering the results reported in the literature for the publicly available Synapse dataset, our method outperformed all existing approaches, which suggests that the proposed method represents the current state-of-the-art for automatic esophagus segmentation. We show that a CNN can yield accurate estimations of esophagus location, and that

  1. Segmentation of Bone Structure in X-ray Images using Convolutional Neural Network

    Directory of Open Access Journals (Sweden)

    CERNAZANU-GLAVAN, C.

    2013-02-01

    Full Text Available The segmentation process represents a first step necessary for any automatic method of extracting information from an image. In the case of X-ray images, through segmentation we can differentiate the bone tissue from the rest of the image. There are nowadays several segmentation techniques, but in general, they all require the human intervention in the segmentation process. Consequently, this article proposes a new segmentation method for the X-ray images using a Convolutional Neural Network (CNN. In present, the convolutional networks are the best techniques for image segmentation. This fact is demonstrated by their wide usage in all the fields, including the medical one. As the X-ray images have large dimensions, for reducing the training time, the method proposed by the present article selects only certain areas (maximum interest areas from the entire image. The neural network is used as pixel classifier thus causing the label of each pixel (bone or none-bone from a raw pixel values in a square area. We will also present the method through which the network final configuration was chosen and we will make a comparative analysis with other 3 CNN configurations. The network chosen by us obtained the best results for all the evaluation metrics used, i.e. warping error, rand error and pixel error.

  2. Multisource Transfer Learning With Convolutional Neural Networks for Lung Pattern Analysis.

    Science.gov (United States)

    Christodoulidis, Stergios; Anthimopoulos, Marios; Ebner, Lukas; Christe, Andreas; Mougiakakou, Stavroula

    2017-01-01

    Early diagnosis of interstitial lung diseases is crucial for their treatment, but even experienced physicians find it difficult, as their clinical manifestations are similar. In order to assist with the diagnosis, computer-aided diagnosis systems have been developed. These commonly rely on a fixed scale classifier that scans CT images, recognizes textural lung patterns, and generates a map of pathologies. In a previous study, we proposed a method for classifying lung tissue patterns using a deep convolutional neural network (CNN), with an architecture designed for the specific problem. In this study, we present an improved method for training the proposed network by transferring knowledge from the similar domain of general texture classification. Six publicly available texture databases are used to pretrain networks with the proposed architecture, which are then fine-tuned on the lung tissue data. The resulting CNNs are combined in an ensemble and their fused knowledge is compressed back to a network with the original architecture. The proposed approach resulted in an absolute increase of about 2% in the performance of the proposed CNN. The results demonstrate the potential of transfer learning in the field of medical image analysis, indicate the textural nature of the problem and show that the method used for training a network can be as important as designing its architecture.

  3. Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks

    Science.gov (United States)

    Alshehhi, Rasha; Marpu, Prashanth Reddy; Woon, Wei Lee; Mura, Mauro Dalla

    2017-08-01

    Extraction of man-made objects (e.g., roads and buildings) from remotely sensed imagery plays an important role in many urban applications (e.g., urban land use and land cover assessment, updating geographical databases, change detection, etc). This task is normally difficult due to complex data in the form of heterogeneous appearance with large intra-class and lower inter-class variations. In this work, we propose a single patch-based Convolutional Neural Network (CNN) architecture for extraction of roads and buildings from high-resolution remote sensing data. Low-level features of roads and buildings (e.g., asymmetry and compactness) of adjacent regions are integrated with Convolutional Neural Network (CNN) features during the post-processing stage to improve the performance. Experiments are conducted on two challenging datasets of high-resolution images to demonstrate the performance of the proposed network architecture and the results are compared with other patch-based network architectures. The results demonstrate the validity and superior performance of the proposed network architecture for extracting roads and buildings in urban areas.

  4. A multi-scale convolutional neural network for phenotyping high-content cellular images.

    Science.gov (United States)

    Godinez, William J; Hossain, Imtiaz; Lazic, Stanley E; Davies, John W; Zhang, Xian

    2017-07-01

    Identifying phenotypes based on high-content cellular images is challenging. Conventional image analysis pipelines for phenotype identification comprise multiple independent steps, with each step requiring method customization and adjustment of multiple parameters. Here, we present an approach based on a multi-scale convolutional neural network (M-CNN) that classifies, in a single cohesive step, cellular images into phenotypes by using directly and solely the images' pixel intensity values. The only parameters in the approach are the weights of the neural network, which are automatically optimized based on training images. The approach requires no a priori knowledge or manual customization, and is applicable to single- or multi-channel images displaying single or multiple cells. We evaluated the classification performance of the approach on eight diverse benchmark datasets. The approach yielded overall a higher classification accuracy compared with state-of-the-art results, including those of other deep CNN architectures. In addition to using the network to simply obtain a yes-or-no prediction for a given phenotype, we use the probability outputs calculated by the network to quantitatively describe the phenotypes. This study shows that these probability values correlate with chemical treatment concentrations. This finding validates further our approach and enables chemical treatment potency estimation via CNNs. The network specifications and solver definitions are provided in Supplementary Software 1. william_jose.godinez_navarro@novartis.com or xian-1.zhang@novartis.com. Supplementary data are available at Bioinformatics online.

  5. A model of traffic signs recognition with convolutional neural network

    Science.gov (United States)

    Hu, Haihe; Li, Yujian; Zhang, Ting; Huo, Yi; Kuang, Wenqing

    2016-10-01

    In real traffic scenes, the quality of captured images are generally low due to some factors such as lighting conditions, and occlusion on. All of these factors are challengeable for automated recognition algorithms of traffic signs. Deep learning has provided a new way to solve this kind of problems recently. The deep network can automatically learn features from a large number of data samples and obtain an excellent recognition performance. We therefore approach this task of recognition of traffic signs as a general vision problem, with few assumptions related to road signs. We propose a model of Convolutional Neural Network (CNN) and apply the model to the task of traffic signs recognition. The proposed model adopts deep CNN as the supervised learning model, directly takes the collected traffic signs image as the input, alternates the convolutional layer and subsampling layer, and automatically extracts the features for the recognition of the traffic signs images. The proposed model includes an input layer, three convolutional layers, three subsampling layers, a fully-connected layer, and an output layer. To validate the proposed model, the experiments are implemented using the public dataset of China competition of fuzzy image processing. Experimental results show that the proposed model produces a recognition accuracy of 99.01 % on the training dataset, and yield a record of 92% on the preliminary contest within the fourth best.

  6. Artificial neural network for bubbles pattern recognition on the images

    Science.gov (United States)

    Poletaev, I. E.; Pervunin, K. S.; Tokarev, M. P.

    2016-10-01

    Two-phase bubble flows have been used in many technological and energy processes as processing oil, chemical and nuclear reactors. This explains large interest to experimental and numerical studies of such flows last several decades. Exploiting of optical diagnostics for analysis of the bubble flows allows researchers obtaining of instantaneous velocity fields and gaseous phase distribution with the high spatial resolution non-intrusively. Behavior of light rays exhibits an intricate manner when they cross interphase boundaries of gaseous bubbles hence the identification of the bubbles images is a complicated problem. This work presents a method of bubbles images identification based on a modern technology of deep learning called convolutional neural networks (CNN). Neural networks are able to determine overlapping, blurred, and non-spherical bubble images. They can increase accuracy of the bubble image recognition, reduce the number of outliers, lower data processing time, and significantly decrease the number of settings for the identification in comparison with standard recognition methods developed before. In addition, usage of GPUs speeds up the learning process of CNN owning to the modern adaptive subgradient optimization techniques.

  7. Tongue Images Classification Based on Constrained High Dispersal Network

    Directory of Open Access Journals (Sweden)

    Dan Meng

    2017-01-01

    Full Text Available Computer aided tongue diagnosis has a great potential to play important roles in traditional Chinese medicine (TCM. However, the majority of the existing tongue image analyses and classification methods are based on the low-level features, which may not provide a holistic view of the tongue. Inspired by deep convolutional neural network (CNN, we propose a novel feature extraction framework called constrained high dispersal neural networks (CHDNet to extract unbiased features and reduce human labor for tongue diagnosis in TCM. Previous CNN models have mostly focused on learning convolutional filters and adapting weights between them, but these models have two major issues: redundancy and insufficient capability in handling unbalanced sample distribution. We introduce high dispersal and local response normalization operation to address the issue of redundancy. We also add multiscale feature analysis to avoid the problem of sensitivity to deformation. Our proposed CHDNet learns high-level features and provides more classification information during training time, which may result in higher accuracy when predicting testing samples. We tested the proposed method on a set of 267 gastritis patients and a control group of 48 healthy volunteers. Test results show that CHDNet is a promising method in tongue image classification for the TCM study.

  8. Object Recognition in Aerial Images Using Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Matija Radovic

    2017-06-01

    Full Text Available There are numerous applications of unmanned aerial vehicles (UAVs in the management of civil infrastructure assets. A few examples include routine bridge inspections, disaster management, power line surveillance and traffic surveying. As UAV applications become widespread, increased levels of autonomy and independent decision-making are necessary to improve the safety, efficiency, and accuracy of the devices. This paper details the procedure and parameters used for the training of convolutional neural networks (CNNs on a set of aerial images for efficient and automated object recognition. Potential application areas in the transportation field are also highlighted. The accuracy and reliability of CNNs depend on the network’s training and the selection of operational parameters. This paper details the CNN training procedure and parameter selection. The object recognition results show that by selecting a proper set of parameters, a CNN can detect and classify objects with a high level of accuracy (97.5% and computational efficiency. Furthermore, using a convolutional neural network implemented in the “YOLO” (“You Only Look Once” platform, objects can be tracked, detected (“seen”, and classified (“comprehended” from video feeds supplied by UAVs in real-time.

  9. Toward Content Based Image Retrieval with Deep Convolutional Neural Networks.

    Science.gov (United States)

    Sklan, Judah E S; Plassard, Andrew J; Fabbri, Daniel; Landman, Bennett A

    2015-03-19

    Content-based image retrieval (CBIR) offers the potential to identify similar case histories, understand rare disorders, and eventually, improve patient care. Recent advances in database capacity, algorithm efficiency, and deep Convolutional Neural Networks (dCNN), a machine learning technique, have enabled great CBIR success for general photographic images. Here, we investigate applying the leading ImageNet CBIR technique to clinically acquired medical images captured by the Vanderbilt Medical Center. Briefly, we (1) constructed a dCNN with four hidden layers, reducing dimensionality of an input scaled to 128×128 to an output encoded layer of 4×384, (2) trained the network using back-propagation 1 million random magnetic resonance (MR) and computed tomography (CT) images, (3) labeled an independent set of 2100 images, and (4) evaluated classifiers on the projection of the labeled images into manifold space. Quantitative results were disappointing (averaging a true positive rate of only 20%); however, the data suggest that improvements would be possible with more evenly distributed sampling across labels and potential re-grouping of label structures. This prelimainry effort at automated classification of medical images with ImageNet is promising, but shows that more work is needed beyond direct adaptation of existing techniques.

  10. Automated embolic signal detection using Deep Convolutional Neural Network.

    Science.gov (United States)

    Sombune, Praotasna; Phienphanich, Phongphan; Phuechpanpaisal, Sutanya; Muengtaweepongsa, Sombat; Ruamthanthong, Anuchit; Tantibundhit, Charturong

    2017-07-01

    This work investigated the potential of Deep Neural Network in detection of cerebral embolic signal (ES) from transcranial Doppler ultrasound (TCD). The resulting system is aimed to couple with TCD devices in diagnosing a risk of stroke in real-time with high accuracy. The Adaptive Gain Control (AGC) approach developed in our previous study is employed to capture suspected ESs in real-time. By using spectrograms of the same TCD signal dataset as that of our previous work as inputs and the same experimental setup, Deep Convolutional Neural Network (CNN), which can learn features while training, was investigated for its ability to bypass the traditional handcrafted feature extraction and selection process. Extracted feature vectors from the suspected ESs are later determined whether they are of an ES, artifact (AF) or normal (NR) interval. The effectiveness of the developed system was evaluated over 19 subjects going under procedures generating emboli. The CNN-based system could achieve in average of 83.0% sensitivity, 80.1% specificity, and 81.4% accuracy, with considerably much less time consumption in development. The certainly growing set of training samples and computational resources will contribute to high performance. Besides having potential use in various clinical ES monitoring settings, continuation of this promising study will benefit developments of wearable applications by leveraging learnable features to serve demographic differentials.

  11. Numerical analysis of modeling based on improved Elman neural network.

    Science.gov (United States)

    Jie, Shao; Li, Wang; WeiSong, Zhao; YaQin, Zhong; Malekian, Reza

    2014-01-01

    A modeling based on the improved Elman neural network (IENN) is proposed to analyze the nonlinear circuits with the memory effect. The hidden layer neurons are activated by a group of Chebyshev orthogonal basis functions instead of sigmoid functions in this model. The error curves of the sum of squared error (SSE) varying with the number of hidden neurons and the iteration step are studied to determine the number of the hidden layer neurons. Simulation results of the half-bridge class-D power amplifier (CDPA) with two-tone signal and broadband signals as input have shown that the proposed behavioral modeling can reconstruct the system of CDPAs accurately and depict the memory effect of CDPAs well. Compared with Volterra-Laguerre (VL) model, Chebyshev neural network (CNN) model, and basic Elman neural network (BENN) model, the proposed model has better performance.

  12. Cross-Spectral Local Descriptors via Quadruplet Network.

    Science.gov (United States)

    Aguilera, Cristhian A; Sappa, Angel D; Aguilera, Cristhian; Toledo, Ricardo

    2017-04-15

    This paper presents a novel CNN-based architecture, referred to as Q-Net, to learn local feature descriptors that are useful for matching image patches from two different spectral bands. Given correctly matched and non-matching cross-spectral image pairs, a quadruplet network is trained to map input image patches to a common Euclidean space, regardless of the input spectral band. Our approach is inspired by the recent success of triplet networks in the visible spectrum, but adapted for cross-spectral scenarios, where, for each matching pair, there are always two possible non-matching patches: one for each spectrum. Experimental evaluations on a public cross-spectral VIS-NIR dataset shows that the proposed approach improves the state-of-the-art. Moreover, the proposed technique can also be used in mono-spectral settings, obtaining a similar performance to triplet network descriptors, but requiring less training data.

  13. Cross-Spectral Local Descriptors via Quadruplet Network

    Science.gov (United States)

    Aguilera, Cristhian A.; Sappa, Angel D.; Aguilera, Cristhian; Toledo, Ricardo

    2017-01-01

    This paper presents a novel CNN-based architecture, referred to as Q-Net, to learn local feature descriptors that are useful for matching image patches from two different spectral bands. Given correctly matched and non-matching cross-spectral image pairs, a quadruplet network is trained to map input image patches to a common Euclidean space, regardless of the input spectral band. Our approach is inspired by the recent success of triplet networks in the visible spectrum, but adapted for cross-spectral scenarios, where, for each matching pair, there are always two possible non-matching patches: one for each spectrum. Experimental evaluations on a public cross-spectral VIS-NIR dataset shows that the proposed approach improves the state-of-the-art. Moreover, the proposed technique can also be used in mono-spectral settings, obtaining a similar performance to triplet network descriptors, but requiring less training data. PMID:28420142

  14. Numerical Analysis of Modeling Based on Improved Elman Neural Network

    Directory of Open Access Journals (Sweden)

    Shao Jie

    2014-01-01

    Full Text Available A modeling based on the improved Elman neural network (IENN is proposed to analyze the nonlinear circuits with the memory effect. The hidden layer neurons are activated by a group of Chebyshev orthogonal basis functions instead of sigmoid functions in this model. The error curves of the sum of squared error (SSE varying with the number of hidden neurons and the iteration step are studied to determine the number of the hidden layer neurons. Simulation results of the half-bridge class-D power amplifier (CDPA with two-tone signal and broadband signals as input have shown that the proposed behavioral modeling can reconstruct the system of CDPAs accurately and depict the memory effect of CDPAs well. Compared with Volterra-Laguerre (VL model, Chebyshev neural network (CNN model, and basic Elman neural network (BENN model, the proposed model has better performance.

  15. Improving deep convolutional neural networks with mixed maxout units.

    Directory of Open Access Journals (Sweden)

    Hui-Zhen Zhao

    Full Text Available Motivated by insights from the maxout-units-based deep Convolutional Neural Network (CNN that "non-maximal features are unable to deliver" and "feature mapping subspace pooling is insufficient," we present a novel mixed variant of the recently introduced maxout unit called a mixout unit. Specifically, we do so by calculating the exponential probabilities of feature mappings gained by applying different convolutional transformations over the same input and then calculating the expected values according to their exponential probabilities. Moreover, we introduce the Bernoulli distribution to balance the maximum values with the expected values of the feature mappings subspace. Finally, we design a simple model to verify the pooling ability of mixout units and a Mixout-units-based Network-in-Network (NiN model to analyze the feature learning ability of the mixout models. We argue that our proposed units improve the pooling ability and that mixout models can achieve better feature learning and classification performance.

  16. Training Deep Spiking Neural Networks Using Backpropagation.

    Science.gov (United States)

    Lee, Jun Haeng; Delbruck, Tobi; Pfeiffer, Michael

    2016-01-01

    Deep spiking neural networks (SNNs) hold the potential for improving the latency and energy efficiency of deep neural networks through data-driven event-based computation. However, training such networks is difficult due to the non-differentiable nature of spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are considered as noise. This enables an error backpropagation mechanism for deep SNNs that follows the same principles as in conventional deep networks, but works directly on spike signals and membrane potentials. Compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statistics of spikes more precisely. We evaluate the proposed framework on artificially generated events from the original MNIST handwritten digit benchmark, and also on the N-MNIST benchmark recorded with an event-based dynamic vision sensor, in which the proposed method reduces the error rate by a factor of more than three compared to the best previous SNN, and also achieves a higher accuracy than a conventional convolutional neural network (CNN) trained and tested on the same data. We demonstrate in the context of the MNIST task that thanks to their event-driven operation, deep SNNs (both fully connected and convolutional) trained with our method achieve accuracy equivalent with conventional neural networks. In the N-MNIST example, equivalent accuracy is achieved with about five times fewer computational operations.

  17. Text-Attentional Convolutional Neural Network for Scene Text Detection.

    Science.gov (United States)

    He, Tong; Huang, Weilin; Qiao, Yu; Yao, Jian

    2016-06-01

    Recent deep learning models have demonstrated strong capabilities for classifying text and non-text components in natural images. They extract a high-level feature globally computed from a whole image component (patch), where the cluttered background information may dominate true text features in the deep representation. This leads to less discriminative power and poorer robustness. In this paper, we present a new system for scene text detection by proposing a novel text-attentional convolutional neural network (Text-CNN) that particularly focuses on extracting text-related regions and features from the image components. We develop a new learning mechanism to train the Text-CNN with multi-level and rich supervised information, including text region mask, character label, and binary text/non-text information. The rich supervision information enables the Text-CNN with a strong capability for discriminating ambiguous texts, and also increases its robustness against complicated background components. The training process is formulated as a multi-task learning problem, where low-level supervised information greatly facilitates the main task of text/non-text classification. In addition, a powerful low-level detector called contrast-enhancement maximally stable extremal regions (MSERs) is developed, which extends the widely used MSERs by enhancing intensity contrast between text patterns and background. This allows it to detect highly challenging text patterns, resulting in a higher recall. Our approach achieved promising results on the ICDAR 2013 data set, with an F-measure of 0.82, substantially improving the state-of-the-art results.

  18. Text-Attentional Convolutional Neural Networks for Scene Text Detection.

    Science.gov (United States)

    He, Tong; Huang, Weilin; Qiao, Yu; Yao, Jian

    2016-03-28

    Recent deep learning models have demonstrated strong capabilities for classifying text and non-text components in natural images. They extract a high-level feature computed globally from a whole image component (patch), where the cluttered background information may dominate true text features in the deep representation. This leads to less discriminative power and poorer robustness. In this work, we present a new system for scene text detection by proposing a novel Text-Attentional Convolutional Neural Network (Text-CNN) that particularly focuses on extracting text-related regions and features from the image components. We develop a new learning mechanism to train the Text-CNN with multi-level and rich supervised information, including text region mask, character label, and binary text/nontext information. The rich supervision information enables the Text-CNN with a strong capability for discriminating ambiguous texts, and also increases its robustness against complicated background components. The training process is formulated as a multi-task learning problem, where low-level supervised information greatly facilitates main task of text/non-text classification. In addition, a powerful low-level detector called Contrast- Enhancement Maximally Stable Extremal Regions (CE-MSERs) is developed, which extends the widely-used MSERs by enhancing intensity contrast between text patterns and background. This allows it to detect highly challenging text patterns, resulting in a higher recall. Our approach achieved promising results on the ICDAR 2013 dataset, with a F-measure of 0.82, improving the state-of-the-art results substantially.

  19. Classifying patient portal messages using Convolutional Neural Networks.

    Science.gov (United States)

    Sulieman, Lina; Gilmore, David; French, Christi; Cronin, Robert M; Jackson, Gretchen Purcell; Russell, Matthew; Fabbri, Daniel

    2017-10-01

    Patients communicate with healthcare providers via secure messaging in patient portals. As patient portal adoption increases, growing messaging volumes may overwhelm providers. Prior research has demonstrated promise in automating classification of patient portal messages into communication types to support message triage or answering. This paper examines if using semantic features and word context improves portal message classification. Portal messages were classified into the following categories: informational, medical, social, and logistical. We constructed features from portal messages including bag of words, bag of phrases, graph representations, and word embeddings. We trained one-versus-all random forest and logistic regression classifiers, and convolutional neural network (CNN) with a softmax output. We evaluated each classifier's performance using Area Under the Curve (AUC). Representing the messages using bag of words, the random forest detected informational, medical, social, and logistical communications in patient portal messages with AUCs: 0.803, 0.884, 0.828, and 0.928, respectively. Graph representations of messages outperformed simpler features with AUCs: 0.837, 0.914, 0.846, 0.884 for informational, medical, social, and logistical communication, respectively. Representing words with Word2Vec embeddings, and mapping features using a CNN had the best performance with AUCs: 0.908 for informational, 0.917 for medical, 0.935 for social, and 0.943 for logistical categories. Word2Vec and graph representations improved the accuracy of classifying portal messages compared to features that lacked semantic information such as bag of words, and bag of phrases. Furthermore, using Word2Vec along with a CNN model, which provide a higher order representation, improved the classification of portal messages. Copyright © 2017 Elsevier Inc. All rights reserved.

  20. Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction

    Science.gov (United States)

    Nguyen, Dat Tien; Kim, Ki Wan; Hong, Hyung Gil; Koo, Ja Hyung; Kim, Min Cheol; Park, Kang Ryoung

    2017-01-01

    Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT), speed-up robust feature (SURF), local binary patterns (LBP), histogram of oriented gradients (HOG), and weighted HOG. Recently, the convolutional neural network (CNN) method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images. PMID:28335510

  1. Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction

    Directory of Open Access Journals (Sweden)

    Dat Tien Nguyen

    2017-03-01

    Full Text Available Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT, speed-up robust feature (SURF, local binary patterns (LBP, histogram of oriented gradients (HOG, and weighted HOG. Recently, the convolutional neural network (CNN method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images.

  2. Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction.

    Science.gov (United States)

    Nguyen, Dat Tien; Kim, Ki Wan; Hong, Hyung Gil; Koo, Ja Hyung; Kim, Min Cheol; Park, Kang Ryoung

    2017-03-20

    Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT), speed-up robust feature (SURF), local binary patterns (LBP), histogram of oriented gradients (HOG), and weighted HOG. Recently, the convolutional neural network (CNN) method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images.

  3. Analyzing Brain Functions by Subject Classification of Functional Near-Infrared Spectroscopy Data Using Convolutional Neural Networks Analysis

    Directory of Open Access Journals (Sweden)

    Satoru Hiwa

    2016-01-01

    Full Text Available Functional near-infrared spectroscopy (fNIRS is suitable for noninvasive mapping of relative changes in regional cortical activity but is limited for quantitative comparisons among cortical sites, subjects, and populations. We have developed a convolutional neural network (CNN analysis method that learns feature vectors for accurate identification of group differences in fNIRS responses. In this study, subject gender was classified using CNN analysis of fNIRS data. fNIRS data were acquired from male and female subjects during a visual number memory task performed in a white noise environment because previous studies had revealed that the pattern of cortical blood flow during the task differed between males and females. A learned classifier accurately distinguished males from females based on distinct fNIRS signals from regions of interest (ROI including the inferior frontal gyrus and premotor areas that were identified by the learning algorithm. These cortical regions are associated with memory storage, attention, and task motor response. The accuracy of the classifier suggests stable gender-based differences in cerebral blood flow during this task. The proposed CNN analysis method can objectively identify ROIs using fNIRS time series data for machine learning to distinguish features between groups.

  4. Classification of coronary artery calcifications according to motion artifacts in chest CT using a convolutional neural network

    Science.gov (United States)

    Šprem, Jurica; de Vos, Bob D.; de Jong, Pim A.; Viergever, Max A.; Išgum, Ivana

    2017-02-01

    Coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular events (CVEs). CAC can be quantified in chest CT scans acquired in lung screening. However, in these images the reproducibility of CAC quantification is compromised by cardiac motion that occurs during scanning, thereby limiting the reproducibility of CVE risk assessment. We present a system for the identification of CACs strongly affected by cardiac motion artifacts by using a convolutional neural network (CNN). This study included 125 chest CT scans from the National Lung Screening Trial (NLST). Images were acquired with CT scanners from four different vendors (GE, Siemens, Philips, Toshiba) with varying tube voltage, image resolution settings, and without ECG synchronization. To define the reference standard, an observer manually identified CAC lesions and labeled each according to the presence of cardiac motion: strongly affected (positive), mildly affected/not affected (negative). A CNN was designed to automatically label the identified CAC lesions according to the presence of cardiac motion by analyzing a patch from the axial CT slice around each lesion. From 125 CT scans, 9201 CAC lesions were analyzed. 8001 lesions were used for training (19% positive) and the remaining 1200 (50% positive) were used for testing. The proposed CNN achieved a classification accuracy of 85% (86% sensitivity, 84% specificity). The obtained results demonstrate that the proposed algorithm can identify CAC lesions that are strongly affected by cardiac motion. This could facilitate further investigation into the relation of CAC scoring reproducibility and the presence of cardiac motion artifacts.

  5. Context-aware stacked convolutional neural networks for classification of breast carcinomas in whole-slide histopathology images.

    Science.gov (United States)

    Bejnordi, Babak Ehteshami; Zuidhof, Guido; Balkenhol, Maschenka; Hermsen, Meyke; Bult, Peter; van Ginneken, Bram; Karssemeijer, Nico; Litjens, Geert; van der Laak, Jeroen

    2017-10-01

    Currently, histopathological tissue examination by a pathologist represents the gold standard for breast lesion diagnostics. Automated classification of histopathological whole-slide images (WSIs) is challenging owing to the wide range of appearances of benign lesions and the visual similarity of ductal carcinoma in-situ (DCIS) to invasive lesions at the cellular level. Consequently, analysis of tissue at high resolutions with a large contextual area is necessary. We present context-aware stacked convolutional neural networks (CNN) for classification of breast WSIs into normal/benign, DCIS, and invasive ductal carcinoma (IDC). We first train a CNN using high pixel resolution to capture cellular level information. The feature responses generated by this model are then fed as input to a second CNN, stacked on top of the first. Training of this stacked architecture with large input patches enables learning of fine-grained (cellular) details and global tissue structures. Our system is trained and evaluated on a dataset containing 221 WSIs of hematoxylin and eosin stained breast tissue specimens. The system achieves an AUC of 0.962 for the binary classification of nonmalignant and malignant slides and obtains a three-class accuracy of 81.3% for classification of WSIs into normal/benign, DCIS, and IDC, demonstrating its potential for routine diagnostics.

  6. Decoding of visual activity patterns from fMRI responses using multivariate pattern analyses and convolutional neural network.

    Science.gov (United States)

    Zafar, Raheel; Kamel, Nidal; Naufal, Mohamad; Malik, Aamir Saeed; Dass, Sarat C; Ahmad, Rana Fayyaz; Abdullah, Jafri M; Reza, Faruque

    2017-01-01

    Decoding of human brain activity has always been a primary goal in neuroscience especially with functional magnetic resonance imaging (fMRI) data. In recent years, Convolutional neural network (CNN) has become a popular method for the extraction of features due to its higher accuracy, however it needs a lot of computation and training data. In this study, an algorithm is developed using Multivariate pattern analysis (MVPA) and modified CNN to decode the behavior of brain for different images with limited data set. Selection of significant features is an important part of fMRI data analysis, since it reduces the computational burden and improves the prediction performance; significant features are selected using t-test. MVPA uses machine learning algorithms to classify different brain states and helps in prediction during the task. General linear model (GLM) is used to find the unknown parameters of every individual voxel and the classification is done using multi-class support vector machine (SVM). MVPA-CNN based proposed algorithm is compared with region of interest (ROI) based method and MVPA based estimated values. The proposed method showed better overall accuracy (68.6%) compared to ROI (61.88%) and estimation values (64.17%).

  7. A Study of Deep CNN-Based Classification of Open and Closed Eyes Using a Visible Light Camera Sensor

    Directory of Open Access Journals (Sweden)

    Ki Wan Kim

    2017-06-01

    Full Text Available The necessity for the classification of open and closed eyes is increasing in various fields, including analysis of eye fatigue in 3D TVs, analysis of the psychological states of test subjects, and eye status tracking-based driver drowsiness detection. Previous studies have used various methods to distinguish between open and closed eyes, such as classifiers based on the features obtained from image binarization, edge operators, or texture analysis. However, when it comes to eye images with different lighting conditions and resolutions, it can be difficult to find an optimal threshold for image binarization or optimal filters for edge and texture extraction. In order to address this issue, we propose a method to classify open and closed eye images with different conditions, acquired by a visible light camera, using a deep residual convolutional neural network. After conducting performance analysis on both self-collected and open databases, we have determined that the classification accuracy of the proposed method is superior to that of existing methods.

  8. Classification of Urban Aerial Data Based on Pixel Labelling with Deep Convolutional Neural Networks and Logistic Regression

    Science.gov (United States)

    Yao, W.; Poleswki, P.; Krzystek, P.

    2016-06-01

    The recent success of deep convolutional neural networks (CNN) on a large number of applications can be attributed to large amounts of available training data and increasing computing power. In this paper, a semantic pixel labelling scheme for urban areas using multi-resolution CNN and hand-crafted spatial-spectral features of airborne remotely sensed data is presented. Both CNN and hand-crafted features are applied to image/DSM patches to produce per-pixel class probabilities with a L1-norm regularized logistical regression classifier. The evidence theory infers a degree of belief for pixel labelling from different sources to smooth regions by handling the conflicts present in the both classifiers while reducing the uncertainty. The aerial data used in this study were provided by ISPRS as benchmark datasets for 2D semantic labelling tasks in urban areas, which consists of two data sources from LiDAR and color infrared camera. The test sites are parts of a city in Germany which is assumed to consist of typical object classes including impervious surfaces, trees, buildings, low vegetation, vehicles and clutter. The evaluation is based on the computation of pixel-based confusion matrices by random sampling. The performance of the strategy with respect to scene characteristics and method combination strategies is analyzed and discussed. The competitive classification accuracy could be not only explained by the nature of input data sources: e.g. the above-ground height of nDSM highlight the vertical dimension of houses, trees even cars and the nearinfrared spectrum indicates vegetation, but also attributed to decision-level fusion of CNN's texture-based approach with multichannel spatial-spectral hand-crafted features based on the evidence combination theory.

  9. Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study

    Science.gov (United States)

    Zhen, Xin; Chen, Jiawei; Zhong, Zichun; Hrycushko, Brian; Zhou, Linghong; Jiang, Steve; Albuquerque, Kevin; Gu, Xuejun

    2017-11-01

    Better understanding of the dose-toxicity relationship is critical for safe dose escalation to improve local control in late-stage cervical cancer radiotherapy. In this study, we introduced a convolutional neural network (CNN) model to analyze rectum dose distribution and predict rectum toxicity. Forty-two cervical cancer patients treated with combined external beam radiotherapy (EBRT) and brachytherapy (BT) were retrospectively collected, including twelve toxicity patients and thirty non-toxicity patients. We adopted a transfer learning strategy to overcome the limited patient data issue. A 16-layers CNN developed by the visual geometry group (VGG-16) of the University of Oxford was pre-trained on a large-scale natural image database, ImageNet, and fine-tuned with patient rectum surface dose maps (RSDMs), which were accumulated EBRT  +  BT doses on the unfolded rectum surface. We used the adaptive synthetic sampling approach and the data augmentation method to address the two challenges, data imbalance and data scarcity. The gradient-weighted class activation maps (Grad-CAM) were also generated to highlight the discriminative regions on the RSDM along with the prediction model. We compare different CNN coefficients fine-tuning strategies, and compare the predictive performance using the traditional dose volume parameters, e.g. D 0.1/1/2cc, and the texture features extracted from the RSDM. Satisfactory prediction performance was achieved with the proposed scheme, and we found that the mean Grad-CAM over the toxicity patient group has geometric consistence of distribution with the statistical analysis result, which indicates possible rectum toxicity location. The evaluation results have demonstrated the feasibility of building a CNN-based rectum dose-toxicity prediction model with transfer learning for cervical cancer radiotherapy.

  10. Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study.

    Science.gov (United States)

    Zhen, Xin; Chen, Jiawei; Zhong, Zichun; Hrycushko, Brian; Zhou, Linghong; Jiang, Steve; Albuquerque, Kevin; Gu, Xuejun

    2017-10-12

    Better understanding of the dose-toxicity relationship is critical for safe dose escalation to improve local control in late-stage cervical cancer radiotherapy. In this study, we introduced a convolutional neural network (CNN) model to analyze rectum dose distribution and predict rectum toxicity. Forty-two cervical cancer patients treated with combined external beam radiotherapy (EBRT) and brachytherapy (BT) were retrospectively collected, including twelve toxicity patients and thirty non-toxicity patients. We adopted a transfer learning strategy to overcome the limited patient data issue. A 16-layers CNN developed by the visual geometry group (VGG-16) of the University of Oxford was pre-trained on a large-scale natural image database, ImageNet, and fine-tuned with patient rectum surface dose maps (RSDMs), which were accumulated EBRT  +  BT doses on the unfolded rectum surface. We used the adaptive synthetic sampling approach and the data augmentation method to address the two challenges, data imbalance and data scarcity. The gradient-weighted class activation maps (Grad-CAM) were also generated to highlight the discriminative regions on the RSDM along with the prediction model. We compare different CNN coefficients fine-tuning strategies, and compare the predictive performance using the traditional dose volume parameters, e.g. D 0.1/1/2cc, and the texture features extracted from the RSDM. Satisfactory prediction performance was achieved with the proposed scheme, and we found that the mean Grad-CAM over the toxicity patient group has geometric consistence of distribution with the statistical analysis result, which indicates possible rectum toxicity location. The evaluation results have demonstrated the feasibility of building a CNN-based rectum dose-toxicity prediction model with transfer learning for cervical cancer radiotherapy.

  11. Hourglass-ShapeNetwork Based Semantic Segmentation for High Resolution Aerial Imagery

    Directory of Open Access Journals (Sweden)

    Yu Liu

    2017-05-01

    Full Text Available A new convolution neural network (CNN architecture for semantic segmentation of high resolution aerial imagery is proposed in this paper. The proposed architecture follows an hourglass-shaped network (HSN design being structured into encoding and decoding stages. By taking advantage of recent advances in CNN designs, we use the composed inception module to replace common convolutional layers, providing the network with multi-scale receptive areas with rich context. Additionally, in order to reduce spatial ambiguities in the up-sampling stage, skip connections with residual units are also employed to feed forward encoding-stage information directly to the decoder. Moreover, overlap inference is employed to alleviate boundary effects occurring when high resolution images are inferred from small-sized patches. Finally, we also propose a post-processing method based on weighted belief propagation to visually enhance the classification results. Extensive experiments based on the Vaihingen and Potsdam datasets demonstrate that the proposed architectures outperform three reference state-of-the-art network designs both numerically and visually.

  12. Predicting mental conditions based on "history of present illness" in psychiatric notes with deep neural networks.

    Science.gov (United States)

    Tran, Tung; Kavuluru, Ramakanth

    2017-11-01

    Applications of natural language processing to mental health notes are not common given the sensitive nature of the associated narratives. The CEGS N-GRID 2016 Shared Task in Clinical Natural Language Processing (NLP) changed this scenario by providing the first set of neuropsychiatric notes to participants. This study summarizes our efforts and results in proposing a novel data use case for this dataset as part of the third track in this shared task. We explore the feasibility and effectiveness of predicting a set of common mental conditions a patient has based on the short textual description of patient's history of present illness typically occurring in the beginning of a psychiatric initial evaluation note. We clean and process the 1000 records made available through the N-GRID clinical NLP task into a key-value dictionary and build a dataset of 986 examples for which there is a narrative for history of present illness as well as Yes/No responses with regards to presence of specific mental conditions. We propose two independent deep neural network models: one based on convolutional neural networks (CNN) and another based on recurrent neural networks with hierarchical attention (ReHAN), the latter of which allows for interpretation of model decisions. We conduct experiments to compare these methods to each other and to baselines based on linear models and named entity recognition (NER). Our CNN model with optimized thresholding of output probability estimates achieves best overall mean micro-F score of 63.144% for 11 common mental conditions with statistically significant gains (ptext segment averaging 300 words, it is a good predictor for a few conditions such as anxiety, depression, panic disorder, and attention deficit hyperactivity disorder. Proposed CNN and RNN models outperform baseline approaches and complement each other when evaluating on a per-label basis. Copyright © 2017. Published by Elsevier Inc.

  13. Feature extraction using convolutional neural network for classifying breast density in mammographic images

    Science.gov (United States)

    Thomaz, Ricardo L.; Carneiro, Pedro C.; Patrocinio, Ana C.

    2017-03-01

    Breast cancer is the leading cause of death for women in most countries. The high levels of mortality relate mostly to late diagnosis and to the direct proportionally relationship between breast density and breast cancer development. Therefore, the correct assessment of breast density is important to provide better screening for higher risk patients. However, in modern digital mammography the discrimination among breast densities is highly complex due to increased contrast and visual information for all densities. Thus, a computational system for classifying breast density might be a useful tool for aiding medical staff. Several machine-learning algorithms are already capable of classifying small number of classes with good accuracy. However, machinelearning algorithms main constraint relates to the set of features extracted and used for classification. Although well-known feature extraction techniques might provide a good set of features, it is a complex task to select an initial set during design of a classifier. Thus, we propose feature extraction using a Convolutional Neural Network (CNN) for classifying breast density by a usual machine-learning classifier. We used 307 mammographic images downsampled to 260x200 pixels to train a CNN and extract features from a deep layer. After training, the activation of 8 neurons from a deep fully connected layer are extracted and used as features. Then, these features are feedforward to a single hidden layer neural network that is cross-validated using 10-folds to classify among four classes of breast density. The global accuracy of this method is 98.4%, presenting only 1.6% of misclassification. However, the small set of samples and memory constraints required the reuse of data in both CNN and MLP-NN, therefore overfitting might have influenced the results even though we cross-validated the network. Thus, although we presented a promising method for extracting features and classifying breast density, a greater database is

  14. 2D-3D Fully Convolutional Neural Networks for Cardiac MR Segmentation

    OpenAIRE

    Patravali, Jay; Jain, Shubham; Chilamkurthy, Sasank

    2017-01-01

    In this paper, we develop a 2D and 3D segmentation pipelines for fully automated cardiac MR image segmentation using Deep Convolutional Neural Networks (CNN). Our models are trained end-to-end from scratch using the ACD Challenge 2017 dataset comprising of 100 studies, each containing Cardiac MR images in End Diastole and End Systole phase. We show that both our segmentation models achieve near state-of-the-art performance scores in terms of distance metrics and have convincing accuracy in te...

  15. Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Martin Längkvist

    2016-04-01

    Full Text Available The availability of high-resolution remote sensing (HRRS data has opened up the possibility for new interesting applications, such as per-pixel classification of individual objects in greater detail. This paper shows how a convolutional neural network (CNN can be applied to multispectral orthoimagery and a digital surface model (DSM of a small city for a full, fast and accurate per-pixel classification. The predicted low-level pixel classes are then used to improve the high-level segmentation. Various design choices of the CNN architecture are evaluated and analyzed. The investigated land area is fully manually labeled into five categories (vegetation, ground, roads, buildings and water, and the classification accuracy is compared to other per-pixel classification works on other land areas that have a similar choice of categories. The results of the full classification and segmentation on selected segments of the map show that CNNs are a viable tool for solving both the segmentation and object recognition task for remote sensing data.

  16. Classification of Two Comic Books based on Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Miki UENO

    2017-03-01

    Full Text Available Unphotographic images are the powerful representations described various situations. Thus, understanding intellectual products such as comics and picture books is one of the important topics in the field of artificial intelligence. Hence, stepwise analysis of a comic story, i.e., features of a part of the image, information features, features relating to continuous scene etc., was pursued. Especially, the length and each scene of four-scene comics are limited so as to ensure a clear interpretation of the contents.In this study, as the first step in this direction, the problem to classify two four-scene comics by the same artists were focused as the example. Several classifiers were constructed by utilizing a Convolutional Neural Network(CNN, and the results of classification by a human annotator and by a computational method were compared.From these experiments, we have clearly shown that CNN is efficient way to classify unphotographic gray scaled images and found that characteristic features of images to classify incorrectly.

  17. Forged Signature Distinction Using Convolutional Neural Network for Feature Extraction

    Directory of Open Access Journals (Sweden)

    Seungsoo Nam

    2018-01-01

    Full Text Available This paper proposes a dynamic verification scheme for finger-drawn signatures in smartphones. As a dynamic feature, the movement of a smartphone is recorded with accelerometer sensors in the smartphone, in addition to the moving coordinates of the signature. To extract high-level longitudinal and topological features, the proposed scheme uses a convolution neural network (CNN for feature extraction, and not as a conventional classifier. We assume that a CNN trained with forged signatures can extract effective features (called S-vector, which are common in forging activities such as hesitation and delay before drawing the complicated part. The proposed scheme also exploits an autoencoder (AE as a classifier, and the S-vector is used as the input vector to the AE. An AE has high accuracy for the one-class distinction problem such as signature verification, and is also greatly dependent on the accuracy of input data. S-vector is valuable as the input of AE, and, consequently, could lead to improved verification accuracy especially for distinguishing forged signatures. Compared to the previous work, i.e., the MLP-based finger-drawn signature verification scheme, the proposed scheme decreases the equal error rate by 13.7%, specifically, from 18.1% to 4.4%, for discriminating forged signatures.

  18. Large patch convolutional neural networks for the scene classification of high spatial resolution imagery

    Science.gov (United States)

    Zhong, Yanfei; Fei, Feng; Zhang, Liangpei

    2016-04-01

    The increase of the spatial resolution of remote-sensing sensors helps to capture the abundant details related to the semantics of surface objects. However, it is difficult for the popular object-oriented classification approaches to acquire higher level semantics from the high spatial resolution remote-sensing (HSR-RS) images, which is often referred to as the "semantic gap." Instead of designing sophisticated operators, convolutional neural networks (CNNs), a typical deep learning method, can automatically discover intrinsic feature descriptors from a large number of input images to bridge the semantic gap. Due to the small data volume of the available HSR-RS scene datasets, which is far away from that of the natural scene datasets, there have been few reports of CNN approaches for HSR-RS image scene classifications. We propose a practical CNN architecture for HSR-RS scene classification, named the large patch convolutional neural network (LPCNN). The large patch sampling is used to generate hundreds of possible scene patches for the feature learning, and a global average pooling layer is used to replace the fully connected network as the classifier, which can greatly reduce the total parameters. The experiments confirm that the proposed LPCNN can learn effective local features to form an effective representation for different land-use scenes, and can achieve a performance that is comparable to the state-of-the-art on public HSR-RS scene datasets.

  19. Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities.

    Science.gov (United States)

    Ghafoorian, Mohsen; Karssemeijer, Nico; Heskes, Tom; van Uden, Inge W M; Sanchez, Clara I; Litjens, Geert; de Leeuw, Frank-Erik; van Ginneken, Bram; Marchiori, Elena; Platel, Bram

    2017-07-11

    The anatomical location of imaging features is of crucial importance for accurate diagnosis in many medical tasks. Convolutional neural networks (CNN) have had huge successes in computer vision, but they lack the natural ability to incorporate the anatomical location in their decision making process, hindering success in some medical image analysis tasks. In this paper, to integrate the anatomical location information into the network, we propose several deep CNN architectures that consider multi-scale patches or take explicit location features while training. We apply and compare the proposed architectures for segmentation of white matter hyperintensities in brain MR images on a large dataset. As a result, we observe that the CNNs that incorporate location information substantially outperform a conventional segmentation method with handcrafted features as well as CNNs that do not integrate location information. On a test set of 50 scans, the best configuration of our networks obtained a Dice score of 0.792, compared to 0.805 for an independent human observer. Performance levels of the machine and the independent human observer were not statistically significantly different (p-value = 0.06).

  20. A fast button surface defects detection method based on convolutional neural network

    Science.gov (United States)

    Liu, Lizhe; Cao, Danhua; Wu, Songlin; Wu, Yubin; Wei, Taoran

    2018-01-01

    Considering the complexity of the button surface texture and the variety of buttons and defects, we propose a fast visual method for button surface defect detection, based on convolutional neural network (CNN). CNN has the ability to extract the essential features by training, avoiding designing complex feature operators adapted to different kinds of buttons, textures and defects. Firstly, we obtain the normalized button region and then use HOG-SVM method to identify the front and back side of the button. Finally, a convolutional neural network is developed to recognize the defects. Aiming at detecting the subtle defects, we propose a network structure with multiple feature channels input. To deal with the defects of different scales, we take a strategy of multi-scale image block detection. The experimental results show that our method is valid for a variety of buttons and able to recognize all kinds of defects that have occurred, including dent, crack, stain, hole, wrong paint and uneven. The detection rate exceeds 96%, which is much better than traditional methods based on SVM and methods based on template match. Our method can reach the speed of 5 fps on DSP based smart camera with 600 MHz frequency.

  1. Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices

    Directory of Open Access Journals (Sweden)

    Tayfun Gokmen

    2017-10-01

    Full Text Available In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU devices to convolutional neural networks (CNNs. We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures.

  2. Convolutional neural network-based encoding and decoding of visual object recognition in space and time.

    Science.gov (United States)

    Seeliger, K; Fritsche, M; Güçlü, U; Schoenmakers, S; Schoffelen, J-M; Bosch, S E; van Gerven, M A J

    2017-07-16

    Representations learned by deep convolutional neural networks (CNNs) for object recognition are a widely investigated model of the processing hierarchy in the human visual system. Using functional magnetic resonance imaging, CNN representations of visual stimuli have previously been shown to correspond to processing stages in the ventral and dorsal streams of the visual system. Whether this correspondence between models and brain signals also holds for activity acquired at high temporal resolution has been explored less exhaustively. Here, we addressed this question by combining CNN-based encoding models with magnetoencephalography (MEG). Human participants passively viewed 1,000 images of objects while MEG signals were acquired. We modelled their high temporal resolution source-reconstructed cortical activity with CNNs, and observed a feed-forward sweep across the visual hierarchy between 75 and 200 ms after stimulus onset. This spatiotemporal cascade was captured by the network layer representations, where the increasingly abstract stimulus representation in the hierarchical network model was reflected in different parts of the visual cortex, following the visual ventral stream. We further validated the accuracy of our encoding model by decoding stimulus identity in a left-out validation set of viewed objects, achieving state-of-the-art decoding accuracy. Copyright © 2017 Elsevier Inc. All rights reserved.

  3. Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices

    Science.gov (United States)

    Gokmen, Tayfun; Onen, Murat; Haensch, Wilfried

    2017-01-01

    In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional neural networks (CNNs). We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures.

  4. Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices.

    Science.gov (United States)

    Gokmen, Tayfun; Onen, Murat; Haensch, Wilfried

    2017-01-01

    In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional neural networks (CNNs). We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures.

  5. Application of a neural network for reflectance spectrum classification

    Science.gov (United States)

    Yang, Gefei; Gartley, Michael

    2017-05-01

    Traditional reflectance spectrum classification algorithms are based on comparing spectrum across the electromagnetic spectrum anywhere from the ultra-violet to the thermal infrared regions. These methods analyze reflectance on a pixel by pixel basis. Inspired by high performance that Convolution Neural Networks (CNN) have demonstrated in image classification, we applied a neural network to analyze directional reflectance pattern images. By using the bidirectional reflectance distribution function (BRDF) data, we can reformulate the 4-dimensional into 2 dimensions, namely incident direction × reflected direction × channels. Meanwhile, RIT's micro-DIRSIG model is utilized to simulate additional training samples for improving the robustness of the neural networks training. Unlike traditional classification by using hand-designed feature extraction with a trainable classifier, neural networks create several layers to learn a feature hierarchy from pixels to classifier and all layers are trained jointly. Hence, the our approach of utilizing the angular features are different to traditional methods utilizing spatial features. Although training processing typically has a large computational cost, simple classifiers work well when subsequently using neural network generated features. Currently, most popular neural networks such as VGG, GoogLeNet and AlexNet are trained based on RGB spatial image data. Our approach aims to build a directional reflectance spectrum based neural network to help us to understand from another perspective. At the end of this paper, we compare the difference among several classifiers and analyze the trade-off among neural networks parameters.

  6. Dermatologist-level classification of skin cancer with deep neural networks.

    Science.gov (United States)

    Esteva, Andre; Kuprel, Brett; Novoa, Roberto A; Ko, Justin; Swetter, Susan M; Blau, Helen M; Thrun, Sebastian

    2017-02-02

    Skin cancer, the most common human malignancy, is primarily diagnosed visually, beginning with an initial clinical screening and followed potentially by dermoscopic analysis, a biopsy and histopathological examination. Automated classification of skin lesions using images is a challenging task owing to the fine-grained variability in the appearance of skin lesions. Deep convolutional neural networks (CNNs) show potential for general and highly variable tasks across many fine-grained object categories. Here we demonstrate classification of skin lesions using a single CNN, trained end-to-end from images directly, using only pixels and disease labels as inputs. We train a CNN using a dataset of 129,450 clinical images-two orders of magnitude larger than previous datasets-consisting of 2,032 different diseases. We test its performance against 21 board-certified dermatologists on biopsy-proven clinical images with two critical binary classification use cases: keratinocyte carcinomas versus benign seborrheic keratoses; and malignant melanomas versus benign nevi. The first case represents the identification of the most common cancers, the second represents the identification of the deadliest skin cancer. The CNN achieves performance on par with all tested experts across both tasks, demonstrating an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists. Outfitted with deep neural networks, mobile devices can potentially extend the reach of dermatologists outside of the clinic. It is projected that 6.3 billion smartphone subscriptions will exist by the year 2021 (ref. 13) and can therefore potentially provide low-cost universal access to vital diagnostic care.

  7. Deep Convolutional Neural Networks Enable Discrimination of Heterogeneous Digital Pathology Images.

    Science.gov (United States)

    Khosravi, Pegah; Kazemi, Ehsan; Imielinski, Marcin; Elemento, Olivier; Hajirasouliha, Iman

    2018-01-01

    Pathological evaluation of tumor tissue is pivotal for diagnosis in cancer patients and automated image analysis approaches have great potential to increase precision of diagnosis and help reduce human error. In this study, we utilize several computational methods based on convolutional neural networks (CNN) and build a stand-alone pipeline to effectively classify different histopathology images across different types of cancer. In particular, we demonstrate the utility of our pipeline to discriminate between two subtypes of lung cancer, four biomarkers of bladder cancer, and five biomarkers of breast cancer. In addition, we apply our pipeline to discriminate among four immunohistochemistry (IHC) staining scores of bladder and breast cancers. Our classification pipeline includes a basic CNN architecture, Google's Inceptions with three training strategies, and an ensemble of two state-of-the-art algorithms, Inception and ResNet. Training strategies include training the last layer of Google's Inceptions, training the network from scratch, and fine-tunning the parameters for our data using two pre-trained version of Google's Inception architectures, Inception-V1 and Inception-V3. We demonstrate the power of deep learning approaches for identifying cancer subtypes, and the robustness of Google's Inceptions even in presence of extensive tumor heterogeneity. On average, our pipeline achieved accuracies of 100%, 92%, 95%, and 69% for discrimination of various cancer tissues, subtypes, biomarkers, and scores, respectively. Our pipeline and related documentation is freely available at https://github.com/ih-_lab/CNN_Smoothie. Copyright © 2017 The Authors. Published by Elsevier B.V. All rights reserved.

  8. Localization and diagnosis framework for pediatric cataracts based on slit-lamp images using deep features of a convolutional neural network.

    Directory of Open Access Journals (Sweden)

    Xiyang Liu

    Full Text Available Slit-lamp images play an essential role for diagnosis of pediatric cataracts. We present a computer vision-based framework for the automatic localization and diagnosis of slit-lamp images by identifying the lens region of interest (ROI and employing a deep learning convolutional neural network (CNN. First, three grading degrees for slit-lamp images are proposed in conjunction with three leading ophthalmologists. The lens ROI is located in an automated manner in the original image using two successive applications of Candy detection and the Hough transform, which are cropped, resized to a fixed size and used to form pediatric cataract datasets. These datasets are fed into the CNN to extract high-level features and implement automatic classification and grading. To demonstrate the performance and effectiveness of the deep features extracted in the CNN, we investigate the features combined with support vector machine (SVM and softmax classifier and compare these with the traditional representative methods. The qualitative and quantitative experimental results demonstrate that our proposed method offers exceptional mean accuracy, sensitivity and specificity: classification (97.07%, 97.28%, and 96.83% and a three-degree grading area (89.02%, 86.63%, and 90.75%, density (92.68%, 91.05%, and 93.94% and location (89.28%, 82.70%, and 93.08%. Finally, we developed and deployed a potential automatic diagnostic software for ophthalmologists and patients in clinical applications to implement the validated model.

  9. Deep Auto-context Convolutional Neural Networks for Standard-Dose PET Image Estimation from Low-Dose PET/MRI.

    Science.gov (United States)

    Xiang, Lei; Qiao, Yu; Nie, Dong; An, Le; Wang, Qian; Shen, Dinggang

    2017-12-06

    Positron emission tomography (PET) is an essential technique in many clinical applications such as tumor detection and brain disorder diagnosis. In order to obtain high-quality PET images, a standard-dose radioactive tracer is needed, which inevitably causes the risk of radiation exposure damage. For reducing the patient's exposure to radiation and maintaining the high quality of PET images, in this paper, we propose a deep learning architecture to estimate the high-quality standard-dose PET (SPET) image from the combination of the low-quality low-dose PET (LPET) image and the accompanying T1-weighted acquisition from magnetic resonance imaging (MRI). Specifically, we adapt the convolutional neural network (CNN) to account for the two channel inputs of LPET and T1, and directly learn the end-to-end mapping between the inputs and the SPET output. Then, we integrate multiple CNN modules following the auto-context strategy, such that the tentatively estimated SPET of an early CNN can be iteratively refined by subsequent CNNs. Validations on real human brain PET/MRI data show that our proposed method can provide competitive estimation quality of the PET images, compared to the state-of-the-art methods. Meanwhile, our method is highly efficient to test on a new subject, e.g., spending ~2 seconds for estimating an entire SPET image in contrast to ~16 minutes by the state-of-the-art method. The results above demonstrate the potential of our method in real clinical applications.

  10. Localization and diagnosis framework for pediatric cataracts based on slit-lamp images using deep features of a convolutional neural network

    Science.gov (United States)

    Zhang, Kai; Long, Erping; Cui, Jiangtao; Zhu, Mingmin; An, Yingying; Zhang, Jia; Liu, Zhenzhen; Lin, Zhuoling; Li, Xiaoyan; Chen, Jingjing; Cao, Qianzhong; Li, Jing; Wu, Xiaohang; Wang, Dongni

    2017-01-01

    Slit-lamp images play an essential role for diagnosis of pediatric cataracts. We present a computer vision-based framework for the automatic localization and diagnosis of slit-lamp images by identifying the lens region of interest (ROI) and employing a deep learning convolutional neural network (CNN). First, three grading degrees for slit-lamp images are proposed in conjunction with three leading ophthalmologists. The lens ROI is located in an automated manner in the original image using two successive applications of Candy detection and the Hough transform, which are cropped, resized to a fixed size and used to form pediatric cataract datasets. These datasets are fed into the CNN to extract high-level features and implement automatic classification and grading. To demonstrate the performance and effectiveness of the deep features extracted in the CNN, we investigate the features combined with support vector machine (SVM) and softmax classifier and compare these with the traditional representative methods. The qualitative and quantitative experimental results demonstrate that our proposed method offers exceptional mean accuracy, sensitivity and specificity: classification (97.07%, 97.28%, and 96.83%) and a three-degree grading area (89.02%, 86.63%, and 90.75%), density (92.68%, 91.05%, and 93.94%) and location (89.28%, 82.70%, and 93.08%). Finally, we developed and deployed a potential automatic diagnostic software for ophthalmologists and patients in clinical applications to implement the validated model. PMID:28306716

  11. Estimating Full Regional Skeletal Muscle Fibre Orientation from B-Mode Ultrasound Images Using Convolutional, Residual, and Deconvolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Ryan Cunningham

    2018-01-01

    Full Text Available This paper presents an investigation into the feasibility of using deep learning methods for developing arbitrary full spatial resolution regression analysis of B-mode ultrasound images of human skeletal muscle. In this study, we focus on full spatial analysis of muscle fibre orientation, since there is an existing body of work with which to compare results. Previous attempts to automatically estimate fibre orientation from ultrasound are not adequate, often requiring manual region selection, feature engineering, providing low-resolution estimations (one angle per muscle and deep muscles are often not attempted. We build upon our previous work in which automatic segmentation was used with plain convolutional neural network (CNN and deep residual convolutional network (ResNet architectures, to predict a low-resolution map of fibre orientation in extracted muscle regions. Here, we use deconvolutions and max-unpooling (DCNN to regularise and improve predicted fibre orientation maps for the entire image, including deep muscles, removing the need for automatic segmentation and we compare our results with the CNN and ResNet, as well as a previously established feature engineering method, on the same task. Dynamic ultrasound images sequences of the calf muscles were acquired (25 Hz from 8 healthy volunteers (4 male, ages: 25–36, median 30. A combination of expert annotation and interpolation/extrapolation provided labels of regional fibre orientation for each image. Neural networks (CNN, ResNet, DCNN were then trained both with and without dropout using leave one out cross-validation. Our results demonstrated robust estimation of full spatial fibre orientation within approximately 6° error, which was an improvement on previous methods.

  12. Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI.

    Science.gov (United States)

    Yang, Xin; Liu, Chaoyue; Wang, Zhiwei; Yang, Jun; Min, Hung Le; Wang, Liang; Cheng, Kwang-Ting Tim

    2017-12-01

    Multi-parameter magnetic resonance imaging (mp-MRI) is increasingly popular for prostate cancer (PCa) detection and diagnosis. However, interpreting mp-MRI data which typically contains multiple unregistered 3D sequences, e.g. apparent diffusion coefficient (ADC) and T2-weighted (T2w) images, is time-consuming and demands special expertise, limiting its usage for large-scale PCa screening. Therefore, solutions to computer-aided detection of PCa in mp-MRI images are highly desirable. Most recent advances in automated methods for PCa detection employ a handcrafted feature based two-stage classification flow, i.e. voxel-level classification followed by a region-level classification. This work presents an automated PCa detection system which can concurrently identify the presence of PCa in an image and localize lesions based on deep convolutional neural network (CNN) features and a single-stage SVM classifier. Specifically, the developed co-trained CNNs consist of two parallel convolutional networks for ADC and T2w images respectively. Each network is trained using images of a single modality in a weakly-supervised manner by providing a set of prostate images with image-level labels indicating only the presence of PCa without priors of lesions' locations. Discriminative visual patterns of lesions can be learned effectively from clutters of prostate and surrounding tissues. A cancer response map with each pixel indicating the likelihood to be cancerous is explicitly generated at the last convolutional layer of the network for each modality. A new back-propagated error E is defined to enforce both optimized classification results and consistent cancer response maps for different modalities, which help capture highly representative PCa-relevant features during the CNN feature learning process. The CNN features of each modality are concatenated and fed into a SVM classifier. For images which are classified to contain cancers, non-maximum suppression and adaptive

  13. Using convolutional neural networks to estimate time-of-flight from PET detector waveforms

    Science.gov (United States)

    Berg, Eric; Cherry, Simon R.

    2018-01-01

    Although there have been impressive strides in detector development for time-of-flight positron emission tomography, most detectors still make use of simple signal processing methods to extract the time-of-flight information from the detector signals. In most cases, the timing pick-off for each waveform is computed using leading edge discrimination or constant fraction discrimination, as these were historically easily implemented with analog pulse processing electronics. However, now with the availability of fast waveform digitizers, there is opportunity to make use of more of the timing information contained in the coincident detector waveforms with advanced signal processing techniques. Here we describe the application of deep convolutional neural networks (CNNs), a type of machine learning, to estimate time-of-flight directly from the pair of digitized detector waveforms for a coincident event. One of the key features of this approach is the simplicity in obtaining ground-truth-labeled data needed to train the CNN: the true time-of-flight is determined from the difference in path length between the positron emission and each of the coincident detectors, which can be easily controlled experimentally. The experimental setup used here made use of two photomultiplier tube-based scintillation detectors, and a point source, stepped in 5 mm increments over a 15 cm range between the two detectors. The detector waveforms were digitized at 10 GS s‑1 using a bench-top oscilloscope. The results shown here demonstrate that CNN-based time-of-flight estimation improves timing resolution by 20% compared to leading edge discrimination (231 ps versus 185 ps), and 23% compared to constant fraction discrimination (242 ps versus 185 ps). By comparing several different CNN architectures, we also showed that CNN depth (number of convolutional and fully connected layers) had the largest impact on timing resolution, while the exact network parameters, such as convolutional

  14. Toward content-based image retrieval with deep convolutional neural networks

    Science.gov (United States)

    Sklan, Judah E. S.; Plassard, Andrew J.; Fabbri, Daniel; Landman, Bennett A.

    2015-03-01

    Content-based image retrieval (CBIR) offers the potential to identify similar case histories, understand rare disorders, and eventually, improve patient care. Recent advances in database capacity, algorithm efficiency, and deep Convolutional Neural Networks (dCNN), a machine learning technique, have enabled great CBIR success for general photographic images. Here, we investigate applying the leading ImageNet CBIR technique to clinically acquired medical images captured by the Vanderbilt Medical Center. Briefly, we (1) constructed a dCNN with four hidden layers, reducing dimensionality of an input scaled to 128x128 to an output encoded layer of 4x384, (2) trained the network using back-propagation 1 million random magnetic resonance (MR) and computed tomography (CT) images, (3) labeled an independent set of 2100 images, and (4) evaluated classifiers on the projection of the labeled images into manifold space. Quantitative results were disappointing (averaging a true positive rate of only 20%); however, the data suggest that improvements would be possible with more evenly distributed sampling across labels and potential re-grouping of label structures. This preliminary effort at automated classification of medical images with ImageNet is promising, but shows that more work is needed beyond direct adaptation of existing techniques.

  15. Squeezeposenet: Image Based Pose Regression with Small Convolutional Neural Networks for Real Time Uas Navigation

    Science.gov (United States)

    Müller, M. S.; Urban, S.; Jutzi, B.

    2017-08-01

    The number of unmanned aerial vehicles (UAVs) is increasing since low-cost airborne systems are available for a wide range of users. The outdoor navigation of such vehicles is mostly based on global navigation satellite system (GNSS) methods to gain the vehicles trajectory. The drawback of satellite-based navigation are failures caused by occlusions and multi-path interferences. Beside this, local image-based solutions like Simultaneous Localization and Mapping (SLAM) and Visual Odometry (VO) can e.g. be used to support the GNSS solution by closing trajectory gaps but are computationally expensive. However, if the trajectory estimation is interrupted or not available a re-localization is mandatory. In this paper we will provide a novel method for a GNSS-free and fast image-based pose regression in a known area by utilizing a small convolutional neural network (CNN). With on-board processing in mind, we employ a lightweight CNN called SqueezeNet and use transfer learning to adapt the network to pose regression. Our experiments show promising results for GNSS-free and fast localization.

  16. Detection of Informal Settlements from VHR Images Using Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Nicholus Mboga

    2017-10-01

    Full Text Available Information about the location and extent of informal settlements is necessary to guide decision making and resource allocation for their upgrading. Very high resolution (VHR satellite images can provide this useful information, however, different urban settlement types are hard to be automatically discriminated and extracted from VHR imagery, because of their abstract semantic class definition. State-of-the-art classification techniques rely on hand-engineering spatial-contextual features to improve the classification results of pixel-based methods. In this paper, we propose to use convolutional neural networks (CNNs for learning discriminative spatial features, and perform automatic detection of informal settlements. The experimental analysis is carried out on a QuickBird image acquired over Dar es Salaam, Tanzania. The proposed technique is compared against support vector machines (SVMs using texture features extracted from grey level co-occurrence matrix (GLCM and local binary patterns (LBP, which result in accuracies of 86.65% and 90.48%, respectively. CNN leads to better classification, resulting in an overall accuracy of 91.71%. A sensitivity analysis shows that deeper networks result in higher accuracies when large training sets are used. The study concludes that training CNN in an end-to-end fashion can automatically learn spatial features from the data that are capable of discriminating complex urban land use classes.

  17. Yarn-dyed fabric defect classification based on convolutional neural network

    Science.gov (United States)

    Jing, Junfeng; Dong, Amei; Li, Pengfei; Zhang, Kaibing

    2017-09-01

    Considering that manual inspection of the yarn-dyed fabric can be time consuming and inefficient, we propose a yarn-dyed fabric defect classification method by using a convolutional neural network (CNN) based on a modified AlexNet. CNN shows powerful ability in performing feature extraction and fusion by simulating the learning mechanism of human brain. The local response normalization layers in AlexNet are replaced by the batch normalization layers, which can enhance both the computational efficiency and classification accuracy. In the training process of the network, the characteristics of the defect are extracted step by step and the essential features of the image can be obtained from the fusion of the edge details with several convolution operations. Then the max-pooling layers, the dropout layers, and the fully connected layers are employed in the classification model to reduce the computation cost and extract more precise features of the defective fabric. Finally, the results of the defect classification are predicted by the softmax function. The experimental results show promising performance with an acceptable average classification rate and strong robustness on yarn-dyed fabric defect classification.

  18. Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization.

    Science.gov (United States)

    Kainz, Philipp; Pfeiffer, Michael; Urschler, Martin

    2017-01-01

    Segmentation of histopathology sections is a necessary preprocessing step for digital pathology. Due to the large variability of biological tissue, machine learning techniques have shown superior performance over conventional image processing methods. Here we present our deep neural network-based approach for segmentation and classification of glands in tissue of benign and malignant colorectal cancer, which was developed to participate in the GlaS@MICCAI2015 colon gland segmentation challenge. We use two distinct deep convolutional neural networks (CNN) for pixel-wise classification of Hematoxylin-Eosin stained images. While the first classifier separates glands from background, the second classifier identifies gland-separating structures. In a subsequent step, a figure-ground segmentation based on weighted total variation produces the final segmentation result by regularizing the CNN predictions. We present both quantitative and qualitative segmentation results on the recently released and publicly available Warwick-QU colon adenocarcinoma dataset associated with the GlaS@MICCAI2015 challenge and compare our approach to the simultaneously developed other approaches that participated in the same challenge. On two test sets, we demonstrate our segmentation performance and show that we achieve a tissue classification accuracy of 98% and 95%, making use of the inherent capability of our system to distinguish between benign and malignant tissue. Our results show that deep learning approaches can yield highly accurate and reproducible results for biomedical image analysis, with the potential to significantly improve the quality and speed of medical diagnoses.

  19. Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization

    Directory of Open Access Journals (Sweden)

    Philipp Kainz

    2017-10-01

    Full Text Available Segmentation of histopathology sections is a necessary preprocessing step for digital pathology. Due to the large variability of biological tissue, machine learning techniques have shown superior performance over conventional image processing methods. Here we present our deep neural network-based approach for segmentation and classification of glands in tissue of benign and malignant colorectal cancer, which was developed to participate in the GlaS@MICCAI2015 colon gland segmentation challenge. We use two distinct deep convolutional neural networks (CNN for pixel-wise classification of Hematoxylin-Eosin stained images. While the first classifier separates glands from background, the second classifier identifies gland-separating structures. In a subsequent step, a figure-ground segmentation based on weighted total variation produces the final segmentation result by regularizing the CNN predictions. We present both quantitative and qualitative segmentation results on the recently released and publicly available Warwick-QU colon adenocarcinoma dataset associated with the GlaS@MICCAI2015 challenge and compare our approach to the simultaneously developed other approaches that participated in the same challenge. On two test sets, we demonstrate our segmentation performance and show that we achieve a tissue classification accuracy of 98% and 95%, making use of the inherent capability of our system to distinguish between benign and malignant tissue. Our results show that deep learning approaches can yield highly accurate and reproducible results for biomedical image analysis, with the potential to significantly improve the quality and speed of medical diagnoses.

  20. A pre-trained convolutional neural network based method for thyroid nodule diagnosis.

    Science.gov (United States)

    Ma, Jinlian; Wu, Fa; Zhu, Jiang; Xu, Dong; Kong, Dexing

    2017-01-01

    In ultrasound images, most thyroid nodules are in heterogeneous appearances with various internal components and also have vague boundaries, so it is difficult for physicians to discriminate malignant thyroid nodules from benign ones. In this study, we propose a hybrid method for thyroid nodule diagnosis, which is a fusion of two pre-trained convolutional neural networks (CNNs) with different convolutional layers and fully-connected layers. Firstly, the two networks pre-trained with ImageNet database are separately trained. Secondly, we fuse feature maps learned by trained convolutional filters, pooling and normalization operations of the two CNNs. Finally, with the fused feature maps, a softmax classifier is used to diagnose thyroid nodules. The proposed method is validated on 15,000 ultrasound images collected from two local hospitals. Experiment results show that the proposed CNN based methods can accurately and effectively diagnose thyroid nodules. In addition, the fusion of the two CNN based models lead to significant performance improvement, with an accuracy of 83.02%±0.72%. These demonstrate the potential clinical applications of this method. Copyright © 2016 Elsevier B.V. All rights reserved.

  1. Toward an optimal convolutional neural network for traffic sign recognition

    Science.gov (United States)

    Habibi Aghdam, Hamed; Jahani Heravi, Elnaz; Puig, Domenec

    2015-12-01

    Convolutional Neural Networks (CNN) beat the human performance on German Traffic Sign Benchmark competition. Both the winner and the runner-up teams trained CNNs to recognize 43 traffic signs. However, both networks are not computationally efficient since they have many free parameters and they use highly computational activation functions. In this paper, we propose a new architecture that reduces the number of the parameters 27% and 22% compared with the two networks. Furthermore, our network uses Leaky Rectified Linear Units (ReLU) as the activation function that only needs a few operations to produce the result. Specifically, compared with the hyperbolic tangent and rectified sigmoid activation functions utilized in the two networks, Leaky ReLU needs only one multiplication operation which makes it computationally much more efficient than the two other functions. Our experiments on the Gertman Traffic Sign Benchmark dataset shows 0:6% improvement on the best reported classification accuracy while it reduces the overall number of parameters 85% compared with the winner network in the competition.

  2. Cascade convolutional neural networks for automatic detection of thyroid nodules in ultrasound images.

    Science.gov (United States)

    Ma, Jinlian; Wu, Fa; Jiang, Tian'an; Zhu, Jiang; Kong, Dexing

    2017-05-01

    It is very important for calculation of clinical indices and diagnosis to detect thyroid nodules from ultrasound images. However, this task is a challenge mainly due to heterogeneous thyroid nodules with distinct components are similar to background in ultrasound images. In this study, we employ cascade deep convolutional neural networks (CNNs) to develop and evaluate a fully automatic detection of thyroid nodules from 2D ultrasound images. Our cascade CNNs are a type of hybrid model, consisting of two different CNNs and a new splitting method. Specifically, it employs a deep CNN to learn the segmentation probability maps from the ground true data. Then, all the segmentation probability maps are split into different connected regions by the splitting method. Finally, another deep CNN is used to automatically detect the thyroid nodules from ultrasound thyroid images. Experiment results illustrate the cascade CNNs are very effective in detection of thyroid nodules. Specially, the value of area under the curve of receiver operating characteristic is 98.51%. The Free-response receiver operating characteristic (FROC) and jackknife alternative FROC (JAFROC) analyses show a significant improvement in the performance of our cascade CNNs compared to that of other methods. The multi-view strategy can improve the performance of cascade CNNs. Moreover, our special splitting method can effectively separate different connected regions so that the second CNN can correctively gain the positive and negative samples according to the automatic labels. The experiment results demonstrate the potential clinical applications of this proposed method. This technique can offer physicians an objective second opinion, and reduce their heavy workload so as to avoid misdiagnosis causes because of excessive fatigue. In addition, it is easy and reproducible for a person without medical expertise to diagnose thyroid nodules. © 2017 American Association of Physicists in Medicine.

  3. Deep-cascade: Cascading 3D Deep Neural Networks for Fast Anomaly Detection and Localization in Crowded Scenes.

    Science.gov (United States)

    Sabokrou, Mohammad; Fayyaz, Mohsen; Fathy, Mahmood; Klette, Reinhard

    2017-02-17

    This paper proposes a fast and reliable method for anomaly detection and localization in video data showing crowded scenes. Time-efficient anomaly localization is an ongoing challenge and subject of this paper. We propose a cubicpatch- based method, characterised by a cascade of classifiers, which makes use of an advanced feature-learning approach. Our cascade of classifiers has two main stages. First, a light but deep 3D auto-encoder is used for early identification of "many" normal cubic patches. This deep network operates on small cubic patches as being the first stage, before carefully resizing remaining candidates of interest, and evaluating those at the second stage using a more complex and deeper 3D convolutional neural network (CNN). We divide the deep autoencoder and the CNN into multiple sub-stages which operate as cascaded classifiers. Shallow layers of the cascaded deep networks (designed as Gaussian classifiers, acting as weak single-class classifiers) detect "simple" normal patches such as background patches, and more complex normal patches are detected at deeper layers. It is shown that the proposed novel technique (a cascade of two cascaded classifiers) performs comparable to current top-performing detection and localization methods on standard benchmarks, but outperforms those in general with respect to required computation time.

  4. Chaotic neural network for learnable associative memory recall

    Science.gov (United States)

    Hsu, Charles C.; Szu, Harold H.

    2003-04-01

    We show that the Fuzzy Membership Function (FMF) is learnable with underlying chaotic neural networks for the open set probability. A sigmoid N-shaped function is used to generate chaotic signals. We postulate that such a chaotic set of innumerable realization forms a FMF exemplified by fuzzy feature maps of eyes, nose, etc., for the invariant face classification. The CNN with FMF plays an important role for fast pattern recognition capability in examples of both habituation and novelty detections. In order to reduce the computation complexity, the nearest-neighborhood weight connection is proposed. In addition, a novel timing-sequence weight-learning algorithm is introduced to increase the capacity and recall of the associative memory. For simplicity, a piece-wise-linear (PWL) N-shaped function was designed and implemented and fabricated in a CMOS chip.

  5. Rationale-Augmented Convolutional Neural Networks for Text Classification.

    Science.gov (United States)

    Zhang, Ye; Marshall, Iain; Wallace, Byron C

    2016-11-01

    We present a new Convolutional Neural Network (CNN) model for text classification that jointly exploits labels on documents and their constituent sentences. Specifically, we consider scenarios in which annotators explicitly mark sentences (or snippets) that support their overall document categorization, i.e., they provide rationales. Our model exploits such supervision via a hierarchical approach in which each document is represented by a linear combination of the vector representations of its component sentences. We propose a sentence-level convolutional model that estimates the probability that a given sentence is a rationale, and we then scale the contribution of each sentence to the aggregate document representation in proportion to these estimates. Experiments on five classification datasets that have document labels and associated rationales demonstrate that our approach consistently outperforms strong baselines. Moreover, our model naturally provides explanations for its predictions.

  6. Spatio-Temporal Dynamics in Cellular Neural Networks

    Directory of Open Access Journals (Sweden)

    Liviu GORAS

    2009-07-01

    Full Text Available Analog Parallel Architectures like Cellular Neural Networks (CNN’s have been thoroughly studied not only for their potential in high-speed image processing applications but also for their rich and exciting spatio-temporal dynamics. An interesting behavior such architectures can exhibit is spatio-temporal filtering and pattern formation, aspects that will be discussed in this work for a general structure consisting of linear cells locally and homogeneously connected within a specified neighborhood. The results are generalizations of those regarding Turing pattern formation in CNN’s. Using linear cells (or piecewise linear cells working in the central linear part of their characteristic allows the use of the decoupling technique – a powerful technique that gives significant insight into the dynamics of the CNN. The roles of the cell structure as well as that of the connection template are discussed and models for the spatial modes dynamics are made as well.

  7. Deep multi-scale location-aware 3D convolutional neural networks for automated detection of lacunes of presumed vascular origin

    Directory of Open Access Journals (Sweden)

    Mohsen Ghafoorian

    2017-01-01

    In this paper, we propose an automated two-stage method using deep convolutional neural networks (CNN. We show that this method has good performance and can considerably benefit readers. We first use a fully convolutional neural network to detect initial candidates. In the second step, we employ a 3D CNN as a false positive reduction tool. As the location information is important to the analysis of candidate structures, we further equip the network with contextual information using multi-scale analysis and integration of explicit location features. We trained, validated and tested our networks on a large dataset of 1075 cases obtained from two different studies. Subsequently, we conducted an observer study with four trained observers and compared our method with them using a free-response operating characteristic analysis. Shown on a test set of 111 cases, the resulting CAD system exhibits performance similar to the trained human observers and achieves a sensitivity of 0.974 with 0.13 false positives per slice. A feasibility study also showed that a trained human observer would considerably benefit once aided by the CAD system.

  8. Socialising journalist trainees in the newsroom

    DEFF Research Database (Denmark)

    Gravengaard, Gitte; Rimestad, Lene

    2014-01-01

    play a key role in the socialisation process as important loci for learning about the craft because of the constant reinforcement of competent practice which takes place here. Thus, these interactions are important sites for cultural production and reproduction supporting the construction of the craft...

  9. The status of translation in media newsrooms

    OpenAIRE

    van Doorslaer, Luc

    2010-01-01

    This presentation deals with some 'classical' topics and approaches in journalism studies and how they can be applied in translation studies. It takes a double extension of the translation concept as a starting point for a case study on global news selection in translation.

  10. Learning Networks, Networked Learning

    NARCIS (Netherlands)

    Sloep, Peter; Berlanga, Adriana

    2010-01-01

    Sloep, P. B., & Berlanga, A. J. (2011). Learning Networks, Networked Learning [Redes de Aprendizaje, Aprendizaje en Red]. Comunicar, XIX(37), 55-63. Retrieved from http://dx.doi.org/10.3916/C37-2011-02-05

  11. A network of networks.

    Science.gov (United States)

    Iedema, Rick; Verma, Raj; Wutzke, Sonia; Lyons, Nigel; McCaughan, Brian

    2017-04-10

    Purpose To further our insight into the role of networks in health system reform, the purpose of this paper is to investigate how one agency, the NSW Agency for Clinical Innovation (ACI), and the multiple networks and enabling resources that it encompasses, govern, manage and extend the potential of networks for healthcare practice improvement. Design/methodology/approach This is a case study investigation which took place over ten months through the first author's participation in network activities and discussions with the agency's staff about their main objectives, challenges and achievements, and with selected services around the state of New South Wales to understand the agency's implementation and large system transformation activities. Findings The paper demonstrates that ACI accommodates multiple networks whose oversight structures, self-organisation and systems change approaches combined in dynamic ways, effectively yield a diversity of network governances. Further, ACI bears out a paradox of "centralised decentralisation", co-locating agents of innovation with networks of implementation and evaluation expertise. This arrangement strengthens and legitimates the role of the strategic hybrid - the healthcare professional in pursuit of change and improvement, and enhances their influence and impact on the wider system. Research limitations/implications While focussing the case study on one agency only, this study is unique as it highlights inter-network connections. Contributing to the literature on network governance, this paper identifies ACI as a "network of networks" through which resources, expectations and stakeholder dynamics are dynamically and flexibly mediated and enhanced. Practical implications The co-location of and dynamic interaction among clinical networks may create synergies among networks, nurture "strategic hybrids", and enhance the impact of network activities on health system reform. Social implications Network governance requires more

  12. ELHnet: a convolutional neural network for classifying cochlear endolymphatic hydrops imaged with optical coherence tomography.

    Science.gov (United States)

    Liu, George S; Zhu, Michael H; Kim, Jinkyung; Raphael, Patrick; Applegate, Brian E; Oghalai, John S

    2017-10-01

    Detection of endolymphatic hydrops is important for diagnosing Meniere's disease, and can be performed non-invasively using optical coherence tomography (OCT) in animal models as well as potentially in the clinic. Here, we developed ELHnet, a convolutional neural network to classify endolymphatic hydrops in a mouse model using learned features from OCT images of mice cochleae. We trained ELHnet on 2159 training and validation images from 17 mice, using only the image pixels and observer-determined labels of endolymphatic hydrops as the inputs. We tested ELHnet on 37 images from 37 mice that were previously not used, and found that the neural network correctly classified 34 of the 37 mice. This demonstrates an improvement in performance from previous work on computer-aided classification of endolymphatic hydrops. To the best of our knowledge, this is the first deep CNN designed for endolymphatic hydrops classification.

  13. Fluid region segmentation in OCT images based on convolution neural network

    Science.gov (United States)

    Liu, Dong; Liu, Xiaoming; Fu, Tianyu; Yang, Zhou

    2017-07-01

    In the retinal image, characteristics of fluid have great significance for diagnosis in eye disease. In the clinical, the segmentation of fluid is usually conducted manually, but is time-consuming and the accuracy is highly depend on the expert's experience. In this paper, we proposed a segmentation method based on convolution neural network (CNN) for segmenting the fluid from fundus image. The B-scans of OCT are segmented into layers, and patches from specific region with annotation are used for training. After the data set being divided into training set and test set, network training is performed and a good segmentation result is obtained, which has a significant advantage over traditional methods such as threshold method.

  14. Detection and recognition of bridge crack based on convolutional neural network

    Directory of Open Access Journals (Sweden)

    Honggong LIU

    2016-10-01

    Full Text Available Aiming at the backward artificial visual detection status of bridge crack in China, which has a great danger coefficient, a digital and intelligent detection method of improving the diagnostic efficiency and reducing the risk coefficient is studied. Combing with machine vision and convolutional neural network technology, Raspberry Pi is used to acquire and pre-process image, and the crack image is analyzed; the processing algorithm which has the best effect in detecting and recognizing is selected; the convolutional neural network(CNN for crack classification is optimized; finally, a new intelligent crack detection method is put forward. The experimental result shows that the system can find all cracks beyond the maximum limit, and effectively identify the type of fracture, and the recognition rate is above 90%. The study provides reference data for engineering detection.

  15. Age, Gender, and Fine-Grained Ethnicity Prediction using Convolutional Neural Networks for the East Asian Face Dataset

    Energy Technology Data Exchange (ETDEWEB)

    Srinivas, Nisha [ORNL; Rose, Derek C [ORNL; Bolme, David S [ORNL; Mahalingam, Gayathri [ORNL; Atwal, Harleen [ORNL; Ricanek, Karl [ORNL

    2017-01-01

    This paper examines the difficulty associated with performing machine-based automatic demographic prediction on a sub-population of Asian faces. We introduce the Wild East Asian Face dataset (WEAFD), a new and unique dataset to the research community. This dataset consists primarily of labeled face images of individuals from East Asian countries, including Vietnam, Burma, Thailand, China, Korea, Japan, Indonesia, and Malaysia. East Asian turk annotators were uniquely used to judge the age and fine grain ethnicity attributes to reduce the impact of the other race effect and improve quality of annotations. We focus on predicting age, gender and fine-grained ethnicity of an individual by providing baseline results with a convolutional neural network (CNN). Finegrained ethnicity prediction refers to predicting ethnicity of an individual by country or sub-region (Chinese, Japanese, Korean, etc.) of the East Asian continent. Performance for two CNN architectures is presented, highlighting the difficulty of these tasks and showcasing potential design considerations that ease network optimization by promoting region based feature extraction.

  16. A Convolutional Neural Network Approach for Assisting Avalanche Search and Rescue Operations with UAV Imagery

    Directory of Open Access Journals (Sweden)

    Mesay Belete Bejiga

    2017-01-01

    Full Text Available Following an avalanche, one of the factors that affect victims’ chance of survival is the speed with which they are located and dug out. Rescue teams use techniques like trained rescue dogs and electronic transceivers to locate victims. However, the resources and time required to deploy rescue teams are major bottlenecks that decrease a victim’s chance of survival. Advances in the field of Unmanned Aerial Vehicles (UAVs have enabled the use of flying robots equipped with sensors like optical cameras to assess the damage caused by natural or manmade disasters and locate victims in the debris. In this paper, we propose assisting avalanche search and rescue (SAR operations with UAVs fitted with vision cameras. The sequence of images of the avalanche debris captured by the UAV is processed with a pre-trained Convolutional Neural Network (CNN to extract discriminative features. A trained linear Support Vector Machine (SVM is integrated at the top of the CNN to detect objects of interest. Moreover, we introduce a pre-processing method to increase the detection rate and a post-processing method based on a Hidden Markov Model to improve the prediction performance of the classifier. Experimental results conducted on two different datasets at different levels of resolution show that the detection performance increases with an increase in resolution, while the computation time increases. Additionally, they also suggest that a significant decrease in processing time can be achieved thanks to the pre-processing step.

  17. Image Classification Using Biomimetic Pattern Recognition with Convolutional Neural Networks Features

    Directory of Open Access Journals (Sweden)

    Liangji Zhou

    2017-01-01

    Full Text Available As a typical deep-learning model, Convolutional Neural Networks (CNNs can be exploited to automatically extract features from images using the hierarchical structure inspired by mammalian visual system. For image classification tasks, traditional CNN models employ the softmax function for classification. However, owing to the limited capacity of the softmax function, there are some shortcomings of traditional CNN models in image classification. To deal with this problem, a new method combining Biomimetic Pattern Recognition (BPR with CNNs is proposed for image classification. BPR performs class recognition by a union of geometrical cover sets in a high-dimensional feature space and therefore can overcome some disadvantages of traditional pattern recognition. The proposed method is evaluated on three famous image classification benchmarks, that is, MNIST, AR, and CIFAR-10. The classification accuracies of the proposed method for the three datasets are 99.01%, 98.40%, and 87.11%, respectively, which are much higher in comparison with the other four methods in most cases.

  18. 2D image classification for 3D anatomy localization: employing deep convolutional neural networks

    Science.gov (United States)

    de Vos, Bob D.; Wolterink, Jelmer M.; de Jong, Pim A.; Viergever, Max A.; Išgum, Ivana

    2016-03-01

    Localization of anatomical regions of interest (ROIs) is a preprocessing step in many medical image analysis tasks. While trivial for humans, it is complex for automatic methods. Classic machine learning approaches require the challenge of hand crafting features to describe differences between ROIs and background. Deep convolutional neural networks (CNNs) alleviate this by automatically finding hierarchical feature representations from raw images. We employ this trait to detect anatomical ROIs in 2D image slices in order to localize them in 3D. In 100 low-dose non-contrast enhanced non-ECG synchronized screening chest CT scans, a reference standard was defined by manually delineating rectangular bounding boxes around three anatomical ROIs -- heart, aortic arch, and descending aorta. Every anatomical ROI was automatically identified using a combination of three CNNs, each analyzing one orthogonal image plane. While single CNNs predicted presence or absence of a specific ROI in the given plane, the combination of their results provided a 3D bounding box around it. Classification performance of each CNN, expressed in area under the receiver operating characteristic curve, was >=0.988. Additionally, the performance of ROI localization was evaluated. Median Dice scores for automatically determined bounding boxes around the heart, aortic arch, and descending aorta were 0.89, 0.70, and 0.85 respectively. The results demonstrate that accurate automatic 3D localization of anatomical structures by CNN-based 2D image classification is feasible.

  19. Digital mammographic tumor classification using transfer learning from deep convolutional neural networks.

    Science.gov (United States)

    Huynh, Benjamin Q; Li, Hui; Giger, Maryellen L

    2016-07-01

    Convolutional neural networks (CNNs) show potential for computer-aided diagnosis (CADx) by learning features directly from the image data instead of using analytically extracted features. However, CNNs are difficult to train from scratch for medical images due to small sample sizes and variations in tumor presentations. Instead, transfer learning can be used to extract tumor information from medical images via CNNs originally pretrained for nonmedical tasks, alleviating the need for large datasets. Our database includes 219 breast lesions (607 full-field digital mammographic images). We compared support vector machine classifiers based on the CNN-extracted image features and our prior computer-extracted tumor features in the task of distinguishing between benign and malignant breast lesions. Five-fold cross validation (by lesion) was conducted with the area under the receiver operating characteristic (ROC) curve as the performance metric. Results show that classifiers based on CNN-extracted features (with transfer learning) perform comparably to those using analytically extracted features [area under the ROC curve [Formula: see text

  20. Lumen-based detection of prostate cancer via convolutional neural networks

    Science.gov (United States)

    Kwak, Jin Tae; Hewitt, Stephen M.

    2017-03-01

    We present a deep learning approach for detecting prostate cancers. The approach consists of two steps. In the first step, we perform tissue segmentation that identifies lumens within digitized prostate tissue specimen images. Intensity- and texture-based image features are computed at five different scales, and a multiview boosting method is adopted to cooperatively combine the image features from differing scales and to identify lumens. In the second step, we utilize convolutional neural networks (CNN) to automatically extract high-level image features of lumens and to predict cancers. The segmented lumens are rescaled to reduce computational complexity and data augmentation by scaling, rotating, and flipping the rescaled image is applied to avoid overfitting. We evaluate the proposed method using two tissue microarrays (TMA) - TMA1 includes 162 tissue specimens (73 Benign and 89 Cancer) and TMA2 comprises 185 tissue specimens (70 Benign and 115 Cancer). In cross-validation on TMA1, the proposed method achieved an AUC of 0.95 (CI: 0.93-0.98). Trained on TMA1 and tested on TMA2, CNN obtained an AUC of 0.95 (CI: 0.92-0.98). This demonstrates that the proposed method can potentially improve prostate cancer pathology.

  1. Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images †

    Science.gov (United States)

    Ran, Lingyan; Zhang, Yanning; Zhang, Qilin; Yang, Tao

    2017-01-01

    Vision-based mobile robot navigation is a vibrant area of research with numerous algorithms having been developed, the vast majority of which either belong to the scene-oriented simultaneous localization and mapping (SLAM) or fall into the category of robot-oriented lane-detection/trajectory tracking. These methods suffer from high computational cost and require stringent labelling and calibration efforts. To address these challenges, this paper proposes a lightweight robot navigation framework based purely on uncalibrated spherical images. To simplify the orientation estimation, path prediction and improve computational efficiency, the navigation problem is decomposed into a series of classification tasks. To mitigate the adverse effects of insufficient negative samples in the “navigation via classification” task, we introduce the spherical camera for scene capturing, which enables 360° fisheye panorama as training samples and generation of sufficient positive and negative heading directions. The classification is implemented as an end-to-end Convolutional Neural Network (CNN), trained on our proposed Spherical-Navi image dataset, whose category labels can be efficiently collected. This CNN is capable of predicting potential path directions with high confidence levels based on a single, uncalibrated spherical image. Experimental results demonstrate that the proposed framework outperforms competing ones in realistic applications. PMID:28604624

  2. Scene text detection via extremal region based double threshold convolutional network classification.

    Directory of Open Access Journals (Sweden)

    Wei Zhu

    Full Text Available In this paper, we present a robust text detection approach in natural images which is based on region proposal mechanism. A powerful low-level detector named saliency enhanced-MSER extended from the widely-used MSER is proposed by incorporating saliency detection methods, which ensures a high recall rate. Given a natural image, character candidates are extracted from three channels in a perception-based illumination invariant color space by saliency-enhanced MSER algorithm. A discriminative convolutional neural network (CNN is jointly trained with multi-level information including pixel-level and character-level information as character candidate classifier. Each image patch is classified as strong text, weak text and non-text by double threshold filtering instead of conventional one-step classification, leveraging confident scores obtained via CNN. To further prune non-text regions, we develop a recursive neighborhood search algorithm to track credible texts from weak text set. Finally, characters are grouped into text lines using heuristic features such as spatial location, size, color, and stroke width. We compare our approach with several state-of-the-art methods, and experiments show that our method achieves competitive performance on public datasets ICDAR 2011 and ICDAR 2013.

  3. Scene text detection via extremal region based double threshold convolutional network classification.

    Science.gov (United States)

    Zhu, Wei; Lou, Jing; Chen, Longtao; Xia, Qingyuan; Ren, Mingwu

    2017-01-01

    In this paper, we present a robust text detection approach in natural images which is based on region proposal mechanism. A powerful low-level detector named saliency enhanced-MSER extended from the widely-used MSER is proposed by incorporating saliency detection methods, which ensures a high recall rate. Given a natural image, character candidates are extracted from three channels in a perception-based illumination invariant color space by saliency-enhanced MSER algorithm. A discriminative convolutional neural network (CNN) is jointly trained with multi-level information including pixel-level and character-level information as character candidate classifier. Each image patch is classified as strong text, weak text and non-text by double threshold filtering instead of conventional one-step classification, leveraging confident scores obtained via CNN. To further prune non-text regions, we develop a recursive neighborhood search algorithm to track credible texts from weak text set. Finally, characters are grouped into text lines using heuristic features such as spatial location, size, color, and stroke width. We compare our approach with several state-of-the-art methods, and experiments show that our method achieves competitive performance on public datasets ICDAR 2011 and ICDAR 2013.

  4. Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network.

    Science.gov (United States)

    Zhai, Xiaolong; Jelfs, Beth; Chan, Rosa H M; Tin, Chung

    2017-01-01

    Hand movement classification based on surface electromyography (sEMG) pattern recognition is a promising approach for upper limb neuroprosthetic control. However, maintaining day-to-day performance is challenged by the non-stationary nature of sEMG in real-life operation. In this study, we propose a self-recalibrating classifier that can be automatically updated to maintain a stable performance over time without the need for user retraining. Our classifier is based on convolutional neural network (CNN) using short latency dimension-reduced sEMG spectrograms as inputs. The pretrained classifier is recalibrated routinely using a corrected version of the prediction results from recent testing sessions. Our proposed system was evaluated with the NinaPro database comprising of hand movement data of 40 intact and 11 amputee subjects. Our system was able to achieve ~10.18% (intact, 50 movement types) and ~2.99% (amputee, 10 movement types) increase in classification accuracy averaged over five testing sessions with respect to the unrecalibrated classifier. When compared with a support vector machine (SVM) classifier, our CNN-based system consistently showed higher absolute performance and larger improvement as well as more efficient training. These results suggest that the proposed system can be a useful tool to facilitate long-term adoption of prosthetics for amputees in real-life applications.

  5. Guided filter and convolutional network based tracking for infrared dim moving target

    Science.gov (United States)

    Qian, Kun; Zhou, Huixin; Qin, Hanlin; Rong, Shenghui; Zhao, Dong; Du, Juan

    2017-09-01

    The dim moving target usually submerges in strong noise, and its motion observability is debased by numerous false alarms for low signal-to-noise ratio. A tracking algorithm that integrates the Guided Image Filter (GIF) and the Convolutional neural network (CNN) into the particle filter framework is presented to cope with the uncertainty of dim targets. First, the initial target template is treated as a guidance to filter incoming templates depending on similarities between the guidance and candidate templates. The GIF algorithm utilizes the structure in the guidance and performs as an edge-preserving smoothing operator. Therefore, the guidance helps to preserve the detail of valuable templates and makes inaccurate ones blurry, alleviating the tracking deviation effectively. Besides, the two-layer CNN method is adopted to obtain a powerful appearance representation. Subsequently, a Bayesian classifier is trained with these discriminative yet strong features. Moreover, an adaptive learning factor is introduced to prevent the update of classifier's parameters when a target undergoes sever background. At last, classifier responses of particles are utilized to generate particle importance weights and a re-sample procedure preserves samples according to the weight. In the predication stage, a 2-order transition model considers the target velocity to estimate current position. Experimental results demonstrate that the presented algorithm outperforms several relative algorithms in the accuracy.

  6. Dynamic frame resizing with convolutional neural network for efficient video compression

    Science.gov (United States)

    Kim, Jaehwan; Park, Youngo; Choi, Kwang Pyo; Lee, JongSeok; Jeon, Sunyoung; Park, JeongHoon

    2017-09-01

    In the past, video codecs such as vc-1 and H.263 used a technique to encode reduced-resolution video and restore original resolution from the decoder for improvement of coding efficiency. The techniques of vc-1 and H.263 Annex Q are called dynamic frame resizing and reduced-resolution update mode, respectively. However, these techniques have not been widely used due to limited performance improvements that operate well only under specific conditions. In this paper, video frame resizing (reduced/restore) technique based on machine learning is proposed for improvement of coding efficiency. The proposed method features video of low resolution made by convolutional neural network (CNN) in encoder and reconstruction of original resolution using CNN in decoder. The proposed method shows improved subjective performance over all the high resolution videos which are dominantly consumed recently. In order to assess subjective quality of the proposed method, Video Multi-method Assessment Fusion (VMAF) which showed high reliability among many subjective measurement tools was used as subjective metric. Moreover, to assess general performance, diverse bitrates are tested. Experimental results showed that BD-rate based on VMAF was improved by about 51% compare to conventional HEVC. Especially, VMAF values were significantly improved in low bitrate. Also, when the method is subjectively tested, it had better subjective visual quality in similar bit rate.

  7. Automatic Gleason grading of H and E stained microscopic prostate images using deep convolutional neural networks

    Science.gov (United States)

    Gummeson, Anna; Arvidsson, Ida; Ohlsson, Mattias; Overgaard, Niels C.; Krzyzanowska, Agnieszka; Heyden, Anders; Bjartell, Anders; Aström, Kalle

    2017-03-01

    Prostate cancer is the most diagnosed cancer in men. The diagnosis is confirmed by pathologists based on ocular inspection of prostate biopsies in order to classify them according to Gleason score. The main goal of this paper is to automate the classification using convolutional neural networks (CNNs). The introduction of CNNs has broadened the field of pattern recognition. It replaces the classical way of designing and extracting hand-made features used for classification with the substantially different strategy of letting the computer itself decide which features are of importance. For automated prostate cancer classification into the classes: Benign, Gleason grade 3, 4 and 5 we propose a CNN with small convolutional filters that has been trained from scratch using stochastic gradient descent with momentum. The input consists of microscopic images of haematoxylin and eosin stained tissue, the output is a coarse segmentation into regions of the four different classes. The dataset used consists of 213 images, each considered to be of one class only. Using four-fold cross-validation we obtained an error rate of 7.3%, which is significantly better than previous state of the art using the same dataset. Although the dataset was rather small, good results were obtained. From this we conclude that CNN is a promising method for this problem. Future work includes obtaining a larger dataset, which potentially could diminish the error margin.

  8. BrainSegNet: a convolutional neural network architecture for automated segmentation of human brain structures.

    Science.gov (United States)

    Mehta, Raghav; Majumdar, Aabhas; Sivaswamy, Jayanthi

    2017-04-01

    Automated segmentation of cortical and noncortical human brain structures has been hitherto approached using nonrigid registration followed by label fusion. We propose an alternative approach for this using a convolutional neural network (CNN) which classifies a voxel into one of many structures. Four different kinds of two-dimensional and three-dimensional intensity patches are extracted for each voxel, providing local and global (context) information to the CNN. The proposed approach is evaluated on five different publicly available datasets which differ in the number of labels per volume. The obtained mean Dice coefficient varied according to the number of labels, for example, it is [Formula: see text] and [Formula: see text] for datasets with the least (32) and the most (134) number of labels, respectively. These figures are marginally better or on par with those obtained with the current state-of-the-art methods on nearly all datasets, at a reduced computational time. The consistently good performance of the proposed method across datasets and no requirement for registration make it attractive for many applications where reduced computational time is necessary.

  9. Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network

    Directory of Open Access Journals (Sweden)

    Xiaolong Zhai

    2017-07-01

    Full Text Available Hand movement classification based on surface electromyography (sEMG pattern recognition is a promising approach for upper limb neuroprosthetic control. However, maintaining day-to-day performance is challenged by the non-stationary nature of sEMG in real-life operation. In this study, we propose a self-recalibrating classifier that can be automatically updated to maintain a stable performance over time without the need for user retraining. Our classifier is based on convolutional neural network (CNN using short latency dimension-reduced sEMG spectrograms as inputs. The pretrained classifier is recalibrated routinely using a corrected version of the prediction results from recent testing sessions. Our proposed system was evaluated with the NinaPro database comprising of hand movement data of 40 intact and 11 amputee subjects. Our system was able to achieve ~10.18% (intact, 50 movement types and ~2.99% (amputee, 10 movement types increase in classification accuracy averaged over five testing sessions with respect to the unrecalibrated classifier. When compared with a support vector machine (SVM classifier, our CNN-based system consistently showed higher absolute performance and larger improvement as well as more efficient training. These results suggest that the proposed system can be a useful tool to facilitate long-term adoption of prosthetics for amputees in real-life applications.

  10. Convolutional neural network classifier for distinguishing Barrett's esophagus and neoplasia endomicroscopy images.

    Science.gov (United States)

    Jisu Hong; Bo-Yong Park; Hyunjin Park

    2017-07-01

    Barrett's esophagus is a diseased condition with abnormal changes of the cells in the esophagus. Intestinal metaplasia (IM) and gastric metaplasia (GM) are two sub-classes of Barrett's esophagus. As IM can progress to the esophageal cancer, the neoplasia (NPL), developing methods for classifying between IM and GM are important issues in clinical practice. We adopted a deep learning (DL) algorithm to classify three conditions of IM, GM, and NPL based on endimicroscopy images. We constructed a convolutional neural network (CNN) architecture to distinguish among three classes. A total of 262 endomicroscopy imaging data of Barrett's esophagus were obtained from the international symposium on biomedical imaging (ISBI) 2016 challenge. 155 IM, 26 GM and 55 NPL cases were used to train the architecture. We implemented image distortion to augment the sample size of the training data. We tested our proposed architecture using the 26 test images that include 17 IM, 4 GM and 5 NPL cases. The classification accuracy was 80.77%. Our results suggest that CNN architecture could be used as a good classifier for distinguishing endomicroscopy imaging data of Barrett's esophagus.

  11. Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images.

    Science.gov (United States)

    Ran, Lingyan; Zhang, Yanning; Zhang, Qilin; Yang, Tao

    2017-06-12

    Vision-based mobile robot navigation is a vibrant area of research with numerous algorithms having been developed, the vast majority of which either belong to the scene-oriented simultaneous localization and mapping (SLAM) or fall into the category of robot-oriented lane-detection/trajectory tracking. These methods suffer from high computational cost and require stringent labelling and calibration efforts. To address these challenges, this paper proposes a lightweight robot navigation framework based purely on uncalibrated spherical images. To simplify the orientation estimation, path prediction and improve computational efficiency, the navigation problem is decomposed into a series of classification tasks. To mitigate the adverse effects of insufficient negative samples in the "navigation via classification" task, we introduce the spherical camera for scene capturing, which enables 360° fisheye panorama as training samples and generation of sufficient positive and negative heading directions. The classification is implemented as an end-to-end Convolutional Neural Network (CNN), trained on our proposed Spherical-Navi image dataset, whose category labels can be efficiently collected. This CNN is capable of predicting potential path directions with high confidence levels based on a single, uncalibrated spherical image. Experimental results demonstrate that the proposed framework outperforms competing ones in realistic applications.

  12. Image Classification Using Biomimetic Pattern Recognition with Convolutional Neural Networks Features

    Science.gov (United States)

    Huo, Guanying

    2017-01-01

    As a typical deep-learning model, Convolutional Neural Networks (CNNs) can be exploited to automatically extract features from images using the hierarchical structure inspired by mammalian visual system. For image classification tasks, traditional CNN models employ the softmax function for classification. However, owing to the limited capacity of the softmax function, there are some shortcomings of traditional CNN models in image classification. To deal with this problem, a new method combining Biomimetic Pattern Recognition (BPR) with CNNs is proposed for image classification. BPR performs class recognition by a union of geometrical cover sets in a high-dimensional feature space and therefore can overcome some disadvantages of traditional pattern recognition. The proposed method is evaluated on three famous image classification benchmarks, that is, MNIST, AR, and CIFAR-10. The classification accuracies of the proposed method for the three datasets are 99.01%, 98.40%, and 87.11%, respectively, which are much higher in comparison with the other four methods in most cases. PMID:28316614

  13. A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery.

    Science.gov (United States)

    Liu, Yan; Stojadinovic, Strahinja; Hrycushko, Brian; Wardak, Zabi; Lau, Steven; Lu, Weiguo; Yan, Yulong; Jiang, Steve B; Zhen, Xin; Timmerman, Robert; Nedzi, Lucien; Gu, Xuejun

    2017-01-01

    Accurate and automatic brain metastases target delineation is a key step for efficient and effective stereotactic radiosurgery (SRS) treatment planning. In this work, we developed a deep learning convolutional neural network (CNN) algorithm for segmenting brain metastases on contrast-enhanced T1-weighted magnetic resonance imaging (MRI) datasets. We integrated the CNN-based algorithm into an automatic brain metastases segmentation workflow and validated on both Multimodal Brain Tumor Image Segmentation challenge (BRATS) data and clinical patients' data. Validation on BRATS data yielded average DICE coefficients (DCs) of 0.75±0.07 in the tumor core and 0.81±0.04 in the enhancing tumor, which outperformed most techniques in the 2015 BRATS challenge. Segmentation results of patient cases showed an average of DCs 0.67±0.03 and achieved an area under the receiver operating characteristic curve of 0.98±0.01. The developed automatic segmentation strategy surpasses current benchmark levels and offers a promising tool for SRS treatment planning for multiple brain metastases.

  14. Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images

    Directory of Open Access Journals (Sweden)

    Lingyan Ran

    2017-06-01

    Full Text Available Vision-based mobile robot navigation is a vibrant area of research with numerous algorithms having been developed, the vast majority of which either belong to the scene-oriented simultaneous localization and mapping (SLAM or fall into the category of robot-oriented lane-detection/trajectory tracking. These methods suffer from high computational cost and require stringent labelling and calibration efforts. To address these challenges, this paper proposes a lightweight robot navigation framework based purely on uncalibrated spherical images. To simplify the orientation estimation, path prediction and improve computational efficiency, the navigation problem is decomposed into a series of classification tasks. To mitigate the adverse effects of insufficient negative samples in the “navigation via classification” task, we introduce the spherical camera for scene capturing, which enables 360° fisheye panorama as training samples and generation of sufficient positive and negative heading directions. The classification is implemented as an end-to-end Convolutional Neural Network (CNN, trained on our proposed Spherical-Navi image dataset, whose category labels can be efficiently collected. This CNN is capable of predicting potential path directions with high confidence levels based on a single, uncalibrated spherical image. Experimental results demonstrate that the proposed framework outperforms competing ones in realistic applications.

  15. A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery.

    Directory of Open Access Journals (Sweden)

    Yan Liu

    Full Text Available Accurate and automatic brain metastases target delineation is a key step for efficient and effective stereotactic radiosurgery (SRS treatment planning. In this work, we developed a deep learning convolutional neural network (CNN algorithm for segmenting brain metastases on contrast-enhanced T1-weighted magnetic resonance imaging (MRI datasets. We integrated the CNN-based algorithm into an automatic brain metastases segmentation workflow and validated on both Multimodal Brain Tumor Image Segmentation challenge (BRATS data and clinical patients' data. Validation on BRATS data yielded average DICE coefficients (DCs of 0.75±0.07 in the tumor core and 0.81±0.04 in the enhancing tumor, which outperformed most techniques in the 2015 BRATS challenge. Segmentation results of patient cases showed an average of DCs 0.67±0.03 and achieved an area under the receiver operating characteristic curve of 0.98±0.01. The developed automatic segmentation strategy surpasses current benchmark levels and offers a promising tool for SRS treatment planning for multiple brain metastases.

  16. Detection of retinal changes from illumination normalized fundus images using convolutional neural networks

    Science.gov (United States)

    Adal, Kedir M.; van Etten, Peter G.; Martinez, Jose P.; Rouwen, Kenneth; Vermeer, Koenraad A.; van Vliet, Lucas J.

    2017-03-01

    Automated detection and quantification of spatio-temporal retinal changes is an important step to objectively assess disease progression and treatment effects for dynamic retinal diseases such as diabetic retinopathy (DR). However, detecting retinal changes caused by early DR lesions such as microaneurysms and dot hemorrhages from longitudinal pairs of fundus images is challenging due to intra and inter-image illumination variation between fundus images. This paper explores a method for automated detection of retinal changes from illumination normalized fundus images using a deep convolutional neural network (CNN), and compares its performance with two other CNNs trained separately on color and green channel fundus images. Illumination variation was addressed by correcting for the variability in the luminosity and contrast estimated from a large scale retinal regions. The CNN models were trained and evaluated on image patches extracted from a registered fundus image set collected from 51 diabetic eyes that were screened at two different time-points. The results show that using normalized images yield better performance than color and green channel images, suggesting that illumination normalization greatly facilitates CNNs to quickly and correctly learn distinctive local image features of DR related retinal changes.

  17. White blood cell differential count of maturation stages in bone marrow smear using dual-stage convolutional neural networks.

    Directory of Open Access Journals (Sweden)

    Jin Woo Choi

    Full Text Available The white blood cell differential count of the bone marrow provides information concerning the distribution of immature and mature cells within maturation stages. The results of such examinations are important for the diagnosis of various diseases and for follow-up care after chemotherapy. However, manual, labor-intensive methods to determine the differential count lead to inter- and intra-variations among the results obtained by hematologists. Therefore, an automated system to conduct the white blood cell differential count is highly desirable, but several difficulties hinder progress. There are variations in the white blood cells of each maturation stage, small inter-class differences within each stage, and variations in images because of the different acquisition and staining processes. Moreover, a large number of classes need to be classified for bone marrow smear analysis, and the high density of touching cells in bone marrow smears renders difficult the segmentation of single cells, which is crucial to traditional image processing and machine learning. Few studies have attempted to discriminate bone marrow cells, and even these have either discriminated only a few classes or yielded insufficient performance. In this study, we propose an automated white blood cell differential counting system from bone marrow smear images using a dual-stage convolutional neural network (CNN. A total of 2,174 patch images were collected for training and testing. The dual-stage CNN classified images into 10 classes of the myeloid and erythroid maturation series, and achieved an accuracy of 97.06%, a precision of 97.13%, a recall of 97.06%, and an F-1 score of 97.1%. The proposed method not only showed high classification performance, but also successfully classified raw images without single cell segmentation and manual feature extraction by implementing CNN. Moreover, it demonstrated rotation and location invariance. These results highlight the promise of

  18. White blood cell differential count of maturation stages in bone marrow smear using dual-stage convolutional neural networks.

    Science.gov (United States)

    Choi, Jin Woo; Ku, Yunseo; Yoo, Byeong Wook; Kim, Jung-Ah; Lee, Dong Soon; Chai, Young Jun; Kong, Hyoun-Joong; Kim, Hee Chan

    2017-01-01

    The white blood cell differential count of the bone marrow provides information concerning the distribution of immature and mature cells within maturation stages. The results of such examinations are important for the diagnosis of various diseases and for follow-up care after chemotherapy. However, manual, labor-intensive methods to determine the differential count lead to inter- and intra-variations among the results obtained by hematologists. Therefore, an automated system to conduct the white blood cell differential count is highly desirable, but several difficulties hinder progress. There are variations in the white blood cells of each maturation stage, small inter-class differences within each stage, and variations in images because of the different acquisition and staining processes. Moreover, a large number of classes need to be classified for bone marrow smear analysis, and the high density of touching cells in bone marrow smears renders difficult the segmentation of single cells, which is crucial to traditional image processing and machine learning. Few studies have attempted to discriminate bone marrow cells, and even these have either discriminated only a few classes or yielded insufficient performance. In this study, we propose an automated white blood cell differential counting system from bone marrow smear images using a dual-stage convolutional neural network (CNN). A total of 2,174 patch images were collected for training and testing. The dual-stage CNN classified images into 10 classes of the myeloid and erythroid maturation series, and achieved an accuracy of 97.06%, a precision of 97.13%, a recall of 97.06%, and an F-1 score of 97.1%. The proposed method not only showed high classification performance, but also successfully classified raw images without single cell segmentation and manual feature extraction by implementing CNN. Moreover, it demonstrated rotation and location invariance. These results highlight the promise of the proposed method

  19. Segmentation of inner and outer bladder wall using deep-learning convolutional neural network in CT urography

    Science.gov (United States)

    Gordon, Marshall; Hadjiiski, Lubomir; Cha, Kenny; Chan, Heang-Ping; Samala, Ravi; Cohan, Richard H.; Caoili, Elaine M.

    2017-03-01

    We are developing a computerized system for detection of bladder cancer in CT urography. In this study, we used a deep-learning convolutional neural network (DL-CNN) to segment the bladder wall. This task is challenging due to differences in the wall between the contrast and non-contrast-filled regions, significant variations in appearance, size, and shape of the bladder among cases, overlap of the prostate with the bladder wall, and the wall being extremely thin compared to the overall size of the bladder. We trained a DL-CNN to estimate the likelihood that a given pixel would be inside the wall of the bladder using neighborhood information. A segmented bladder wall was then obtained using level sets with this likelihood map as a term in the level set energy formulation to obtain contours of the inner and outer bladder walls. The accuracy of the segmentation was evaluated by comparing the segmented wall outlines to hand outlines for a set of 79 training cases and 15 test cases using the average volume intersection % as the metric. For the training set, the inner wall achieved an average volume intersection of 90.0+/-8.7% and the outer wall achieved 93.7+/-3.9%. For the test set, the inner wall achieved an average volume intersection of 87.6+/-7.6% and the outer wall achieved 87.2+/-9.3%. The results show that the DL-CNN with level sets was effective in segmenting the inner and outer bladder walls.

  20. Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach.

    Science.gov (United States)

    Valverde, Sergi; Cabezas, Mariano; Roura, Eloy; González-Villà, Sandra; Pareto, Deborah; Vilanova, Joan C; Ramió-Torrentà, Lluís; Rovira, Àlex; Oliver, Arnau; Lladó, Xavier

    2017-07-15

    In this paper, we present a novel automated method for White Matter (WM) lesion segmentation of Multiple Sclerosis (MS) patient images. Our approach is based on a cascade of two 3D patch-wise convolutional neural networks (CNN). The first network is trained to be more sensitive revealing possible candidate lesion voxels while the second network is trained to reduce the number of misclassified voxels coming from the first network. This cascaded CNN architecture tends to learn well from a small (n≤35) set of labeled data of the same MRI contrast, which can be very interesting in practice, given the difficulty to obtain manual label annotations and the large amount of available unlabeled Magnetic Resonance Imaging (MRI) data. We evaluate the accuracy of the proposed method on the public MS lesion segmentation challenge MICCAI2008 dataset, comparing it with respect to other state-of-the-art MS lesion segmentation tools. Furthermore, the proposed method is also evaluated on two private MS clinical datasets, where the performance of our method is also compared with different recent public available state-of-the-art MS lesion segmentation methods. At the time of writing this paper, our method is the best ranked approach on the MICCAI2008 challenge, outperforming the rest of 60 participant methods when using all the available input modalities (T1-w, T2-w and FLAIR), while still in the top-rank (3rd position) when using only T1-w and FLAIR modalities. On clinical MS data, our approach exhibits a significant increase in the accuracy segmenting of WM lesions when compared with the rest of evaluated methods, highly correlating (r≥0.97) also with the expected lesion volume. Copyright © 2017 Elsevier Inc. All rights reserved.

  1. Convolutional neural networks for prostate cancer recurrence prediction

    Science.gov (United States)

    Kumar, Neeraj; Verma, Ruchika; Arora, Ashish; Kumar, Abhay; Gupta, Sanchit; Sethi, Amit; Gann, Peter H.

    2017-03-01

    Accurate prediction of the treatment outcome is important for cancer treatment planning. We present an approach to predict prostate cancer (PCa) recurrence after radical prostatectomy using tissue images. We used a cohort whose case vs. control (recurrent vs. non-recurrent) status had been determined using post-treatment follow up. Further, to aid the development of novel biomarkers of PCa recurrence, cases and controls were paired based on matching of other predictive clinical variables such as Gleason grade, stage, age, and race. For this cohort, tissue resection microarray with up to four cores per patient was available. The proposed approach is based on deep learning, and its novelty lies in the use of two separate convolutional neural networks (CNNs) - one to detect individual nuclei even in the crowded areas, and the other to classify them. To detect nuclear centers in an image, the first CNN predicts distance transform of the underlying (but unknown) multi-nuclear map from the input HE image. The second CNN classifies the patches centered at nuclear centers into those belonging to cases or controls. Voting across patches extracted from image(s) of a patient yields the probability of recurrence for the patient. The proposed approach gave 0.81 AUC for a sample of 30 recurrent cases and 30 non-recurrent controls, after being trained on an independent set of 80 case-controls pairs. If validated further, such an approach might help in choosing between a combination of treatment options such as active surveillance, radical prostatectomy, radiation, and hormone therapy. It can also generalize to the prediction of treatment outcomes in other cancers.

  2. Segmentation of organs-at-risks in head and neck CT images using convolutional neural networks

    Science.gov (United States)

    Ibragimov, Bulat; Xing, Lei

    2017-01-01

    Purpose Accurate segmentation of organs-at-risks (OARs) is the key step for efficient planning of radiation therapy for head and neck (HaN) cancer treatment. In the work, we proposed the first deep learning-based algorithm, for segmentation of OARs in HaN CT images, and compared its performance against state-of-the-art automated segmentation algorithms, commercial software and inter-observer variability. Methods Convolutional neural networks (CNNs) – a concept from the field of deep learning – were used to study consistent intensity patterns of OARs from training CT images and to segment the OAR in a previously unseen test CT image. For CNN training, we extracted a representative number of positive intensity patches around voxels that belong to the OAR of interest in training CT images, and negative intensity patches around voxels that belong to the surrounding structures. These patches then passed through a sequence of CNN layers that captured local image features such as corners, end-points and edges, and combined them into more complex high-order features that can efficiently describe the OAR. The trained network was applied to classify voxels in a region of interest in the test image where the corresponding OAR is expected to be located. We then smoothed the obtained classification results by using Markov random fields algorithm. We finally extracted the largest connected component of the smoothed voxels classified as the OAR by CNN, performed dilate-erode operations to remov cavities of the component, which resulted in segmentation of the OAR in the test image. Results The performance of CNNs was validated on segmentation of spinal cord, mandible, parotid glands, submandibular glands, larynx, pharynx, eye globes, optic nerves and optic chiasm using 50 CT images. The obtained segmentation results varied from 37.4% Dice coefficient (DSC) for chiasm to 89.5% DSC for mandible. We also analyzed the performance of state-of-the-art algorithms and commercial

  3. Segmentation of organs-at-risks in head and neck CT images using convolutional neural networks.

    Science.gov (United States)

    Ibragimov, Bulat; Xing, Lei

    2017-02-01

    Accurate segmentation of organs-at-risks (OARs) is the key step for efficient planning of radiation therapy for head and neck (HaN) cancer treatment. In the work, we proposed the first deep learning-based algorithm, for segmentation of OARs in HaN CT images, and compared its performance against state-of-the-art automated segmentation algorithms, commercial software, and interobserver variability. Convolutional neural networks (CNNs)-a concept from the field of deep learning-were used to study consistent intensity patterns of OARs from training CT images and to segment the OAR in a previously unseen test CT image. For CNN training, we extracted a representative number of positive intensity patches around voxels that belong to the OAR of interest in training CT images, and negative intensity patches around voxels that belong to the surrounding structures. These patches then passed through a sequence of CNN layers that captured local image features such as corners, end-points, and edges, and combined them into more complex high-order features that can efficiently describe the OAR. The trained network was applied to classify voxels in a region of interest in the test image where the corresponding OAR is expected to be located. We then smoothed the obtained classification results by using Markov random fields algorithm. We finally extracted the largest connected component of the smoothed voxels classified as the OAR by CNN, performed dilate-erode operations to remove cavities of the component, which resulted in segmentation of the OAR in the test image. The performance of CNNs was validated on segmentation of spinal cord, mandible, parotid glands, submandibular glands, larynx, pharynx, eye globes, optic nerves, and optic chiasm using 50 CT images. The obtained segmentation results varied from 37.4% Dice coefficient (DSC) for chiasm to 89.5% DSC for mandible. We also analyzed the performance of state-of-the-art algorithms and commercial software reported in the

  4. A Study of Complex Deep Learning Networks on High Performance, Neuromorphic, and Quantum Computers

    Energy Technology Data Exchange (ETDEWEB)

    Potok, Thomas E [ORNL; Schuman, Catherine D [ORNL; Young, Steven R [ORNL; Patton, Robert M [ORNL; Spedalieri, Federico [University of Southern California, Information Sciences Institute; Liu, Jeremy [University of Southern California, Information Sciences Institute; Yao, Ke-Thia [University of Southern California, Information Sciences Institute; Rose, Garrett [University of Tennessee (UT); Chakma, Gangotree [University of Tennessee (UT)

    2016-01-01

    Current Deep Learning models use highly optimized convolutional neural networks (CNN) trained on large graphical processing units (GPU)-based computers with a fairly simple layered network topology, i.e., highly connected layers, without intra-layer connections. Complex topologies have been proposed, but are intractable to train on current systems. Building the topologies of the deep learning network requires hand tuning, and implementing the network in hardware is expensive in both cost and power. In this paper, we evaluate deep learning models using three different computing architectures to address these problems: quantum computing to train complex topologies, high performance computing (HPC) to automatically determine network topology, and neuromorphic computing for a low-power hardware implementation. Due to input size limitations of current quantum computers we use the MNIST dataset for our evaluation. The results show the possibility of using the three architectures in tandem to explore complex deep learning networks that are untrainable using a von Neumann architecture. We show that a quantum computer can find high quality values of intra-layer connections and weights, while yielding a tractable time result as the complexity of the network increases; a high performance computer can find optimal layer-based topologies; and a neuromorphic computer can represent the complex topology and weights derived from the other architectures in low power memristive hardware. This represents a new capability that is not feasible with current von Neumann architecture. It potentially enables the ability to solve very complicated problems unsolvable with current computing technologies.

  5. Siamese convolutional networks for tracking the spine motion

    Science.gov (United States)

    Liu, Yuan; Sui, Xiubao; Sun, Yicheng; Liu, Chengwei; Hu, Yong

    2017-09-01

    Deep learning models have demonstrated great success in various computer vision tasks such as image classification and object tracking. However, tracking the lumbar spine by digitalized video fluoroscopic imaging (DVFI), which can quantitatively analyze the motion mode of spine to diagnose lumbar instability, has not yet been well developed due to the lack of steady and robust tracking method. In this paper, we propose a novel visual tracking algorithm of the lumbar vertebra motion based on a Siamese convolutional neural network (CNN) model. We train a full-convolutional neural network offline to learn generic image features. The network is trained to learn a similarity function that compares the labeled target in the first frame with the candidate patches in the current frame. The similarity function returns a high score if the two images depict the same object. Once learned, the similarity function is used to track a previously unseen object without any adapting online. In the current frame, our tracker is performed by evaluating the candidate rotated patches sampled around the previous frame target position and presents a rotated bounding box to locate the predicted target precisely. Results indicate that the proposed tracking method can detect the lumbar vertebra steadily and robustly. Especially for images with low contrast and cluttered background, the presented tracker can still achieve good tracking performance. Further, the proposed algorithm operates at high speed for real time tracking.

  6. Accelerating deep neural network training with inconsistent stochastic gradient descent.

    Science.gov (United States)

    Wang, Linnan; Yang, Yi; Min, Renqiang; Chakradhar, Srimat

    2017-09-01

    Stochastic Gradient Descent (SGD) updates Convolutional Neural Network (CNN) with a noisy gradient computed from a random batch, and each batch evenly updates the network once in an epoch. This model applies the same training effort to each batch, but it overlooks the fact that the gradient variance, induced by Sampling Bias and Intrinsic Image Difference, renders different training dynamics on batches. In this paper, we develop a new training strategy for SGD, referred to as Inconsistent Stochastic Gradient Descent (ISGD) to address this problem. The core concept of ISGD is the inconsistent training, which dynamically adjusts the training effort w.r.t the loss. ISGD models the training as a stochastic process that gradually reduces down the mean of batch's loss, and it utilizes a dynamic upper control limit to identify a large loss batch on the fly. ISGD stays on the identified batch to accelerate the training with additional gradient updates, and it also has a constraint to penalize drastic parameter changes. ISGD is straightforward, computationally efficient and without requiring auxiliary memories. A series of empirical evaluations on real world datasets and networks demonstrate the promising performance of inconsistent training. Copyright © 2017 Elsevier Ltd. All rights reserved.

  7. Declarative Networking

    CERN Document Server

    Loo, Boon Thau

    2012-01-01

    Declarative Networking is a programming methodology that enables developers to concisely specify network protocols and services, which are directly compiled to a dataflow framework that executes the specifications. Declarative networking proposes the use of a declarative query language for specifying and implementing network protocols, and employs a dataflow framework at runtime for communication and maintenance of network state. The primary goal of declarative networking is to greatly simplify the process of specifying, implementing, deploying and evolving a network design. In addition, decla

  8. Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: Automatic construction of onychomycosis datasets by region-based convolutional deep neural network

    Science.gov (United States)

    Lim, Woohyung; Kim, Myoung Shin; Na, Jung Im; Park, Ilwoo

    2018-01-01

    Although there have been reports of the successful diagnosis of skin disorders using deep learning, unrealistically large clinical image datasets are required for artificial intelligence (AI) training. We created datasets of standardized nail images using a region-based convolutional neural network (R-CNN) trained to distinguish the nail from the background. We used R-CNN to generate training datasets of 49,567 images, which we then used to fine-tune the ResNet-152 and VGG-19 models. The validation datasets comprised 100 and 194 images from Inje University (B1 and B2 datasets, respectively), 125 images from Hallym University (C dataset), and 939 images from Seoul National University (D dataset). The AI (ensemble model; ResNet-152 + VGG-19 + feedforward neural networks) results showed test sensitivity/specificity/ area under the curve values of (96.0 / 94.7 / 0.98), (82.7 / 96.7 / 0.95), (92.3 / 79.3 / 0.93), (87.7 / 69.3 / 0.82) for the B1, B2, C, and D datasets. With a combination of the B1 and C datasets, the AI Youden index was significantly (p = 0.01) higher than that of 42 dermatologists doing the same assessment manually. For B1+C and B2+ D dataset combinations, almost none of the dermatologists performed as well as the AI. By training with a dataset comprising 49,567 images, we achieved a diagnostic accuracy for onychomycosis using deep learning that was superior to that of most of the dermatologists who participated in this study. PMID:29352285

  9. Automated cancer stem cell recognition in H and E stained tissue using convolutional neural networks and color deconvolution

    Science.gov (United States)

    Aichinger, Wolfgang; Krappe, Sebastian; Cetin, A. Enis; Cetin-Atalay, Rengul; Üner, Aysegül; Benz, Michaela; Wittenberg, Thomas; Stamminger, Marc; Münzenmayer, Christian

    2017-03-01

    The analysis and interpretation of histopathological samples and images is an important discipline in the diagnosis of various diseases, especially cancer. An important factor in prognosis and treatment with the aim of a precision medicine is the determination of so-called cancer stem cells (CSC) which are known for their resistance to chemotherapeutic treatment and involvement in tumor recurrence. Using immunohistochemistry with CSC markers like CD13, CD133 and others is one way to identify CSC. In our work we aim at identifying CSC presence on ubiquitous Hematoxilyn and Eosin (HE) staining as an inexpensive tool for routine histopathology based on their distinct morphological features. We present initial results of a new method based on color deconvolution (CD) and convolutional neural networks (CNN). This method performs favorably (accuracy 0.936) in comparison with a state-of-the-art method based on 1DSIFT and eigen-analysis feature sets evaluated on the same image database. We also show that accuracy of the CNN is improved by the CD pre-processing.

  10. Application of Convolution Neural Network to the forecasts of flare classification and occurrence using SOHO MDI data

    Science.gov (United States)

    Park, Eunsu; Moon, Yong-Jae

    2017-08-01

    A Convolutional Neural Network(CNN) is one of the well-known deep-learning methods in image processing and computer vision area. In this study, we apply CNN to two kinds of flare forecasting models: flare classification and occurrence. For this, we consider several pre-trained models (e.g., AlexNet, GoogLeNet, and ResNet) and customize them by changing several options such as the number of layers, activation function, and optimizer. Our inputs are the same number of SOHO)/MDI images for each flare class (None, C, M and X) at 00:00 UT from Jan 1996 to Dec 2010 (total 1600 images). Outputs are the results of daily flare forecasting for flare class and occurrence. We build, train, and test the models on TensorFlow, which is well-known machine learning software library developed by Google. Our major results from this study are as follows. First, most of the models have accuracies more than 0.7. Second, ResNet developed by Microsoft has the best accuracies : 0.86 for flare classification and 0.84 for flare occurrence. Third, the accuracies of these models vary greatly with changing parameters. We discuss several possibilities to improve the models.

  11. Wearable Device-Based Gait Recognition Using Angle Embedded Gait Dynamic Images and a Convolutional Neural Network.

    Science.gov (United States)

    Zhao, Yongjia; Zhou, Suiping

    2017-02-28

    The widespread installation of inertial sensors in smartphones and other wearable devices provides a valuable opportunity to identify people by analyzing their gait patterns, for either cooperative or non-cooperative circumstances. However, it is still a challenging task to reliably extract discriminative features for gait recognition with noisy and complex data sequences collected from casually worn wearable devices like smartphones. To cope with this problem, we propose a novel image-based gait recognition approach using the Convolutional Neural Network (CNN) without the need to manually extract discriminative features. The CNN's input image, which is encoded straightforwardly from the inertial sensor data sequences, is called Angle Embedded Gait Dynamic Image (AE-GDI). AE-GDI is a new two-dimensional representation of gait dynamics, which is invariant to rotation and translation. The performance of the proposed approach in gait authentication and gait labeling is evaluated using two datasets: (1) the McGill University dataset, which is collected under realistic conditions; and (2) the Osaka University dataset with the largest number of subjects. Experimental results show that the proposed approach achieves competitive recognition accuracy over existing approaches and provides an effective parametric solution for identification among a large number of subjects by gait patterns.

  12. Global Detection of Live Virtual Machine Migration Based on Cellular Neural Networks

    Directory of Open Access Journals (Sweden)

    Kang Xie

    2014-01-01

    Full Text Available In order to meet the demands of operation monitoring of large scale, autoscaling, and heterogeneous virtual resources in the existing cloud computing, a new method of live virtual machine (VM migration detection algorithm based on the cellular neural networks (CNNs, is presented. Through analyzing the detection process, the parameter relationship of CNN is mapped as an optimization problem, in which improved particle swarm optimization algorithm based on bubble sort is used to solve the problem. Experimental results demonstrate that the proposed method can display the VM migration processing intuitively. Compared with the best fit heuristic algorithm, this approach reduces the processing time, and emerging evidence has indicated that this new approach is affordable to parallelism and analog very large scale integration (VLSI implementation allowing the VM migration detection to be performed better.

  13. An Intelligent Gear Fault Diagnosis Methodology Using a Complex Wavelet Enhanced Convolutional Neural Network.

    Science.gov (United States)

    Sun, Weifang; Yao, Bin; Zeng, Nianyin; Chen, Binqiang; He, Yuchao; Cao, Xincheng; He, Wangpeng

    2017-07-12

    As a typical example of large and complex mechanical systems, rotating machinery is prone to diversified sorts of mechanical faults. Among these faults, one of the prominent causes of malfunction is generated in gear transmission chains. Although they can be collected via vibration signals, the fault signatures are always submerged in overwhelming interfering contents. Therefore, identifying the critical fault's characteristic signal is far from an easy task. In order to improve the recognition accuracy of a fault's characteristic signal, a novel intelligent fault diagnosis method is presented. In this method, a dual-tree complex wavelet transform (DTCWT) is employed to acquire the multiscale signal's features. In addition, a convolutional neural network (CNN) approach is utilized to automatically recognise a fault feature from the multiscale signal features. The experiment results of the recognition for gear faults show the feasibility and effectiveness of the proposed method, especially in the gear's weak fault features.

  14. Can we recognize horses by their ocular biometric traits using deep convolutional neural networks?

    Science.gov (United States)

    Trokielewicz, Mateusz; Szadkowski, Mateusz

    2017-08-01

    This paper aims at determining the viability of horse recognition by the means of ocular biometrics and deep convolutional neural networks (deep CNNs). Fast and accurate identification of race horses before racing is crucial for ensuring that exactly the horses that were declared are participating, using methods that are non-invasive and friendly to these delicate animals. As typical iris recognition methods require lot of fine-tuning of the method parameters and high-quality data, CNNs seem like a natural candidate to be applied for recognition thanks to their potentially excellent abilities in describing texture, combined with ease of implementation in an end-to-end manner. Also, with such approach we can easily utilize both iris and periocular features without constructing complicated algorithms for each. We thus present a simple CNN classifier, able to correctly identify almost 80% of the samples in an identification scenario, and give equal error rate (EER) of less than 10% in a verification scenario.

  15. View-interpolation of sparsely sampled sinogram using convolutional neural network

    Science.gov (United States)

    Lee, Hoyeon; Lee, Jongha; Cho, Suengryong

    2017-02-01

    Spare-view sampling and its associated iterative image reconstruction in computed tomography have actively investigated. Sparse-view CT technique is a viable option to low-dose CT, particularly in cone-beam CT (CBCT) applications, with advanced iterative image reconstructions with varying degrees of image artifacts. One of the artifacts that may occur in sparse-view CT is the streak artifact in the reconstructed images. Another approach has been investigated for sparse-view CT imaging by use of the interpolation methods to fill in the missing view data and that reconstructs the image by an analytic reconstruction algorithm. In this study, we developed an interpolation method using convolutional neural network (CNN), which is one of the widely used deep-learning methods, to find missing projection data and compared its performances with the other interpolation techniques.

  16. Encoding physiological signals as images for affective state recognition using convolutional neural networks.

    Science.gov (United States)

    Guangliang Yu; Xiang Li; Dawei Song; Xiaozhao Zhao; Peng Zhang; Yuexian Hou; Bin Hu

    2016-08-01

    Affective state recognition based on multiple modalities of physiological signals has been a hot research topic. Traditional methods require designing hand-crafted features based on domain knowledge, which is time-consuming and has not achieved a satisfactory performance. On the other hand, conducting classification on raw signals directly can also cause some problems, such as the interference of noise and the curse of dimensionality. To address these problems, we propose a novel approach that encodes different modalities of data as images and use convolutional neural networks (CNN) to perform the affective state recognition task. We validate our aproach on the DECAF dataset in comparison with two state-of-the-art methods, i.e., the Support Vector Machines (SVM) and Random Forest (RF). Experimental results show that our aproach outperforms the baselines by 5% to 9%.

  17. First Steps Toward Incorporating Image Based Diagnostics Into Particle Accelerator Control Systems Using Convolutional Neural Networks

    Energy Technology Data Exchange (ETDEWEB)

    Edelen, A. L.; Biedron, S. G.; Milton, S. V.; Edelen, J. P.

    2016-12-16

    At present, a variety of image-based diagnostics are used in particle accelerator systems. Often times, these are viewed by a human operator who then makes appropriate adjustments to the machine. Given recent advances in using convolutional neural networks (CNNs) for image processing, it should be possible to use image diagnostics directly in control routines (NN-based or otherwise). This is especially appealing for non-intercepting diagnostics that could run continuously during beam operation. Here, we show results of a first step toward implementing such a controller: our trained CNN can predict multiple simulated downstream beam parameters at the Fermilab Accelerator Science and Technology (FAST) facility's low energy beamline using simulated virtual cathode laser images, gun phases, and solenoid strengths.

  18. Convolutional Neural Network-Based Finger-Vein Recognition Using NIR Image Sensors.

    Science.gov (United States)

    Hong, Hyung Gil; Lee, Min Beom; Park, Kang Ryoung

    2017-06-06

    Conventional finger-vein recognition systems perform recognition based on the finger-vein lines extracted from the input images or image enhancement, and texture feature extraction from the finger-vein images. In these cases, however, the inaccurate detection of finger-vein lines lowers the recognition accuracy. In the case of texture feature extraction, the developer must experimentally decide on a form of the optimal filter for extraction considering the characteristics of the image database. To address this problem, this research proposes a finger-vein recognition method that is robust to various database types and environmental changes based on the convolutional neural network (CNN). In the experiments using the two finger-vein databases constructed in this research and the SDUMLA-HMT finger-vein database, which is an open database, the method proposed in this research showed a better performance compared to the conventional methods.

  19. Multi-National Banknote Classification Based on Visible-light Line Sensor and Convolutional Neural Network.

    Science.gov (United States)

    Pham, Tuyen Danh; Lee, Dong Eun; Park, Kang Ryoung

    2017-07-08

    Automatic recognition of banknotes is applied in payment facilities, such as automated teller machines (ATMs) and banknote counters. Besides the popular approaches that focus on studying the methods applied to various individual types of currencies, there have been studies conducted on simultaneous classification of banknotes from multiple countries. However, their methods were conducted with limited numbers of banknote images, national currencies, and denominations. To address this issue, we propose a multi-national banknote classification method based on visible-light banknote images captured by a one-dimensional line sensor and classified by a convolutional neural network (CNN) considering the size information of each denomination. Experiments conducted on the combined banknote image database of six countries with 62 denominations gave a classification accuracy of 100%, and results show that our proposed algorithm outperforms previous methods.

  20. NIRFaceNet: A Convolutional Neural Network for Near-Infrared Face Identification

    Directory of Open Access Journals (Sweden)

    Min Peng

    2016-10-01

    Full Text Available Near-infrared (NIR face recognition has attracted increasing attention because of its advantage of illumination invariance. However, traditional face recognition methods based on NIR are designed for and tested in cooperative-user applications. In this paper, we present a convolutional neural network (CNN for NIR face recognition (specifically face identification in non-cooperative-user applications. The proposed NIRFaceNet is modified from GoogLeNet, but has a more compact structure designed specifically for the Chinese Academy of Sciences Institute of Automation (CASIA NIR database and can achieve higher identification rates with less training time and less processing time. The experimental results demonstrate that NIRFaceNet has an overall advantage compared to other methods in the NIR face recognition domain when image blur and noise are present. The performance suggests that the proposed NIRFaceNet method may be more suitable for non-cooperative-user applications.

  1. The network researchers' network

    DEFF Research Database (Denmark)

    Henneberg, Stephan C.; Jiang, Zhizhong; Naudé, Peter

    2009-01-01

    The Industrial Marketing and Purchasing (IMP) Group is a network of academic researchers working in the area of business-to-business marketing. The group meets every year to discuss and exchange ideas, with a conference having been held every year since 1984 (there was no meeting in 1987). In thi......The Industrial Marketing and Purchasing (IMP) Group is a network of academic researchers working in the area of business-to-business marketing. The group meets every year to discuss and exchange ideas, with a conference having been held every year since 1984 (there was no meeting in 1987......). In this paper, based upon the papers presented at the 22 conferences held to date, we undertake a Social Network Analysis in order to examine the degree of co-publishing that has taken place between this group of researchers. We identify the different components in this database, and examine the large main...

  2. Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks.

    Science.gov (United States)

    Qi Dou; Hao Chen; Lequan Yu; Lei Zhao; Jing Qin; Defeng Wang; Mok, Vincent Ct; Lin Shi; Pheng-Ann Heng

    2016-05-01

    Cerebral microbleeds (CMBs) are small haemorrhages nearby blood vessels. They have been recognized as important diagnostic biomarkers for many cerebrovascular diseases and cognitive dysfunctions. In current clinical routine, CMBs are manually labelled by radiologists but this procedure is laborious, time-consuming, and error prone. In this paper, we propose a novel automatic method to detect CMBs from magnetic resonance (MR) images by exploiting the 3D convolutional neural network (CNN). Compared with previous methods that employed either low-level hand-crafted descriptors or 2D CNNs, our method can take full advantage of spatial contextual information in MR volumes to extract more representative high-level features for CMBs, and hence achieve a much better detection accuracy. To further improve the detection performance while reducing the computational cost, we propose a cascaded framework under 3D CNNs for the task of CMB detection. We first exploit a 3D fully convolutional network (FCN) strategy to retrieve the candidates with high probabilities of being CMBs, and then apply a well-trained 3D CNN discrimination model to distinguish CMBs from hard mimics. Compared with traditional sliding window strategy, the proposed 3D FCN strategy can remove massive redundant computations and dramatically speed up the detection process. We constructed a large dataset with 320 volumetric MR scans and performed extensive experiments to validate the proposed method, which achieved a high sensitivity of 93.16% with an average number of 2.74 false positives per subject, outperforming previous methods using low-level descriptors or 2D CNNs by a significant margin. The proposed method, in principle, can be adapted to other biomarker detection tasks from volumetric medical data.

  3. Use of Gabor filters and deep networks in the segmentation of retinal vessel morphology

    Science.gov (United States)

    Leopold, Henry A.; Orchard, Jeff; Zelek, John; Lakshminarayanan, Vasudevan

    2017-02-01

    The segmentation of retinal morphology has numerous applications in assessing ophthalmologic and cardiovascular disease pathologies. The early detection of many such conditions is often the most effective method for reducing patient risk. Computer aided segmentation of the vasculature has proven to be a challenge, mainly due to inconsistencies such as noise, variations in hue and brightness that can greatly reduce the quality of fundus images. Accurate fundus and/or retinal vessel maps give rise to longitudinal studies able to utilize multimodal image registration and disease/condition status measurements, as well as applications in surgery preparation and biometrics. This paper further investigates the use of a Convolutional Neural Network as a multi-channel classifier of retinal vessels using the Digital Retinal Images for Vessel Extraction database, a standardized set of fundus images used to gauge the effectiveness of classification algorithms. The CNN has a feed-forward architecture and varies from other published architectures in its combination of: max-pooling, zero-padding, ReLU layers, batch normalization, two dense layers and finally a Softmax activation function. Notably, the use of Adam to optimize training the CNN on retinal fundus images has not been found in prior review. This work builds on prior work of the authors, exploring the use of Gabor filters to boost the accuracy of the system to 0.9478 during post processing. The mean of a series of Gabor filters with varying frequencies and sigma values are applied to the output of the network and used to determine whether a pixel represents a vessel or non-vessel.

  4. Predicting Response to Neoadjuvant Chemotherapy with PET Imaging Using Convolutional Neural Networks.

    Directory of Open Access Journals (Sweden)

    Petros-Pavlos Ypsilantis

    Full Text Available Imaging of cancer with 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET has become a standard component of diagnosis and staging in oncology, and is becoming more important as a quantitative monitor of individual response to therapy. In this article we investigate the challenging problem of predicting a patient's response to neoadjuvant chemotherapy from a single 18F-FDG PET scan taken prior to treatment. We take a "radiomics" approach whereby a large amount of quantitative features is automatically extracted from pretherapy PET images in order to build a comprehensive quantification of the tumor phenotype. While the dominant methodology relies on hand-crafted texture features, we explore the potential of automatically learning low- to high-level features directly from PET scans. We report on a study that compares the performance of two competing radiomics strategies: an approach based on state-of-the-art statistical classifiers using over 100 quantitative imaging descriptors, including texture features as well as standardized uptake values, and a convolutional neural network, 3S-CNN, trained directly from PET scans by taking sets of adjacent intra-tumor slices. Our experimental results, based on a sample of 107 patients with esophageal cancer, provide initial evidence that convolutional neural networks have the potential to extract PET imaging representations that are highly predictive of response to therapy. On this dataset, 3S-CNN achieves an average 80.7% sensitivity and 81.6% specificity in predicting non-responders, and outperforms other competing predictive models.

  5. Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery

    Directory of Open Access Journals (Sweden)

    Fan Hu

    2015-11-01

    Full Text Available Learning efficient image representations is at the core of the scene classification task of remote sensing imagery. The existing methods for solving the scene classification task, based on either feature coding approaches with low-level hand-engineered features or unsupervised feature learning, can only generate mid-level image features with limited representative ability, which essentially prevents them from achieving better performance. Recently, the deep convolutional neural networks (CNNs, which are hierarchical architectures trained on large-scale datasets, have shown astounding performance in object recognition and detection. However, it is still not clear how to use these deep convolutional neural networks for high-resolution remote sensing (HRRS scene classification. In this paper, we investigate how to transfer features from these successfully pre-trained CNNs for HRRS scene classification. We propose two scenarios for generating image features via extracting CNN features from different layers. In the first scenario, the activation vectors extracted from fully-connected layers are regarded as the final image features; in the second scenario, we extract dense features from the last convolutional layer at multiple scales and then encode the dense features into global image features through commonly used feature coding approaches. Extensive experiments on two public scene classification datasets demonstrate that the image features obtained by the two proposed scenarios, even with a simple linear classifier, can result in remarkable performance and improve the state-of-the-art by a significant margin. The results reveal that the features from pre-trained CNNs generalize well to HRRS datasets and are more expressive than the low- and mid-level features. Moreover, we tentatively combine features extracted from different CNN models for better performance.

  6. Network cosmology.

    Science.gov (United States)

    Krioukov, Dmitri; Kitsak, Maksim; Sinkovits, Robert S; Rideout, David; Meyer, David; Boguñá, Marián

    2012-01-01

    Prediction and control of the dynamics of complex networks is a central problem in network science. Structural and dynamical similarities of different real networks suggest that some universal laws might accurately describe the dynamics of these networks, albeit the nature and common origin of such laws remain elusive. Here we show that the causal network representing the large-scale structure of spacetime in our accelerating universe is a power-law graph with strong clustering, similar to many complex networks such as the Internet, social, or biological networks. We prove that this structural similarity is a consequence of the asymptotic equivalence between the large-scale growth dynamics of complex networks and causal networks. This equivalence suggests that unexpectedly similar laws govern the dynamics of complex networks and spacetime in the universe, with implications to network science and cosmology.

  7. Network Cosmology

    Science.gov (United States)

    Krioukov, Dmitri; Kitsak, Maksim; Sinkovits, Robert S.; Rideout, David; Meyer, David; Boguñá, Marián

    2012-01-01

    Prediction and control of the dynamics of complex networks is a central problem in network science. Structural and dynamical similarities of different real networks suggest that some universal laws might accurately describe the dynamics of these networks, albeit the nature and common origin of such laws remain elusive. Here we show that the causal network representing the large-scale structure of spacetime in our accelerating universe is a power-law graph with strong clustering, similar to many complex networks such as the Internet, social, or biological networks. We prove that this structural similarity is a consequence of the asymptotic equivalence between the large-scale growth dynamics of complex networks and causal networks. This equivalence suggests that unexpectedly similar laws govern the dynamics of complex networks and spacetime in the universe, with implications to network science and cosmology. PMID:23162688

  8. A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction.

    Science.gov (United States)

    Kang, Eunhee; Min, Junhong; Ye, Jong Chul

    2017-10-01

    Due to the potential risk of inducing cancer, radiation exposure by X-ray CT devices should be reduced for routine patient scanning. However, in low-dose X-ray CT, severe artifacts typically occur due to photon starvation, beam hardening, and other causes, all of which decrease the reliability of the diagnosis. Thus, a high-quality reconstruction method from low-dose X-ray CT data has become a major research topic in the CT community. Conventional model-based de-noising approaches are, however, computationally very expensive, and image-domain de-noising approaches cannot readily remove CT-specific noise patterns. To tackle these problems, we want to develop a new low-dose X-ray CT algorithm based on a deep-learning approach. We propose an algorithm which uses a deep convolutional neural network (CNN) which is applied to the wavelet transform coefficients of low-dose CT images. More specifically, using a directional wavelet transform to extract the directional component of artifacts and exploit the intra- and inter- band correlations, our deep network can effectively suppress CT-specific noise. In addition, our CNN is designed with a residual learning architecture for faster network training and better performance. Experimental results confirm that the proposed algorithm effectively removes complex noise patterns from CT images derived from a reduced X-ray dose. In addition, we show that the wavelet-domain CNN is efficient when used to remove noise from low-dose CT compared to existing approaches. Our results were rigorously evaluated by several radiologists at the Mayo Clinic and won second place at the 2016 "Low-Dose CT Grand Challenge." To the best of our knowledge, this work is the first deep-learning architecture for low-dose CT reconstruction which has been rigorously evaluated and proven to be effective. In addition, the proposed algorithm, in contrast to existing model-based iterative reconstruction (MBIR) methods, has considerable potential to benefit from

  9. Human Emotion Recognition with Electroencephalographic Multidimensional Features by Hybrid Deep Neural Networks

    Directory of Open Access Journals (Sweden)

    Youjun Li

    2017-10-01

    Full Text Available The aim of this study is to recognize human emotions by electroencephalographic (EEG signals. The innovation of our research methods involves two aspects: First, we integrate the spatial characteristics, frequency domain, and temporal characteristics of the EEG signals, and map them to a two-dimensional image. With these images, we build a series of EEG Multidimensional Feature Image (EEG MFI sequences to represent the emotion variation with EEG signals. Second, we construct a hybrid deep neural network to deal with the EEG MFI sequences to recognize human emotional states where the hybrid deep neural network combined the Convolution Neural Networks (CNN and Long Short-Term-Memory (LSTM Recurrent Neural Networks (RNN. Empirical research is carried out with the open-source dataset DEAP (a Dataset for Emotion Analysis using EEG, Physiological, and video signals using our method, and the results demonstrate the significant improvements over current state-of-the-art approaches in this field. The average emotion classification accuracy of each subject with CLRNN (the hybrid neural networks that we proposed in this study is 75.21%.

  10. Automatic localization of vertebrae based on convolutional neural networks

    Science.gov (United States)

    Shen, Wei; Yang, Feng; Mu, Wei; Yang, Caiyun; Yang, Xin; Tian, Jie

    2015-03-01

    Localization of the vertebrae is of importance in many medical applications. For example, the vertebrae can serve as the landmarks in image registration. They can also provide a reference coordinate system to facilitate the localization of other organs in the chest. In this paper, we propose a new vertebrae localization method using convolutional neural networks (CNN). The main advantage of the proposed method is the removal of hand-crafted features. We construct two training sets to train two CNNs that share the same architecture. One is used to distinguish the vertebrae from other tissues in the chest, and the other is aimed at detecting the centers of the vertebrae. The architecture contains two convolutional layers, both of which are followed by a max-pooling layer. Then the output feature vector from the maxpooling layer is fed into a multilayer perceptron (MLP) classifier which has one hidden layer. Experiments were performed on ten chest CT images. We used leave-one-out strategy to train and test the proposed method. Quantitative comparison between the predict centers and ground truth shows that our convolutional neural networks can achieve promising localization accuracy without hand-crafted features.

  11. Building Extraction from Remote Sensing Data Using Fully Convolutional Networks

    Science.gov (United States)

    Bittner, K.; Cui, S.; Reinartz, P.

    2017-05-01

    Building detection and footprint extraction are highly demanded for many remote sensing applications. Though most previous works have shown promising results, the automatic extraction of building footprints still remains a nontrivial topic, especially in complex urban areas. Recently developed extensions of the CNN framework made it possible to perform dense pixel-wise classification of input images. Based on these abilities we propose a methodology, which automatically generates a full resolution binary building mask out of a Digital Surface Model (DSM) using a Fully Convolution Network (FCN) architecture. The advantage of using the depth information is that it provides geometrical silhouettes and allows a better separation of buildings from background as well as through its invariance to illumination and color variations. The proposed framework has mainly two steps. Firstly, the FCN is trained on a large set of patches consisting of normalized DSM (nDSM) as inputs and available ground truth building mask as target outputs. Secondly, the generated predictions from FCN are viewed as unary terms for a Fully connected Conditional Random Fields (FCRF), which enables us to create a final binary building mask. A series of experiments demonstrate that our methodology is able to extract accurate building footprints which are close to the buildings original shapes to a high degree. The quantitative and qualitative analysis show the significant improvements of the results in contrast to the multy-layer fully connected network from our previous work.

  12. Classification of breast cancer histology images using Convolutional Neural Networks.

    Directory of Open Access Journals (Sweden)

    Teresa Araújo

    Full Text Available Breast cancer is one of the main causes of cancer death worldwide. The diagnosis of biopsy tissue with hematoxylin and eosin stained images is non-trivial and specialists often disagree on the final diagnosis. Computer-aided Diagnosis systems contribute to reduce the cost and increase the efficiency of this process. Conventional classification approaches rely on feature extraction methods designed for a specific problem based on field-knowledge. To overcome the many difficulties of the feature-based approaches, deep learning methods are becoming important alternatives. A method for the classification of hematoxylin and eosin stained breast biopsy images using Convolutional Neural Networks (CNNs is proposed. Images are classified in four classes, normal tissue, benign lesion, in situ carcinoma and invasive carcinoma, and in two classes, carcinoma and non-carcinoma. The architecture of the network is designed to retrieve information at different scales, including both nuclei and overall tissue organization. This design allows the extension of the proposed system to whole-slide histology images. The features extracted by the CNN are also used for training a Support Vector Machine classifier. Accuracies of 77.8% for four class and 83.3% for carcinoma/non-carcinoma are achieved. The sensitivity of our method for cancer cases is 95.6%.

  13. BUILDING EXTRACTION FROM REMOTE SENSING DATA USING FULLY CONVOLUTIONAL NETWORKS

    Directory of Open Access Journals (Sweden)

    K. Bittner

    2017-05-01

    Full Text Available Building detection and footprint extraction are highly demanded for many remote sensing applications. Though most previous works have shown promising results, the automatic extraction of building footprints still remains a nontrivial topic, especially in complex urban areas. Recently developed extensions of the CNN framework made it possible to perform dense pixel-wise classification of input images. Based on these abilities we propose a methodology, which automatically generates a full resolution binary building mask out of a Digital Surface Model (DSM using a Fully Convolution Network (FCN architecture. The advantage of using the depth information is that it provides geometrical silhouettes and allows a better separation of buildings from background as well as through its invariance to illumination and color variations. The proposed framework has mainly two steps. Firstly, the FCN is trained on a large set of patches consisting of normalized DSM (nDSM as inputs and available ground truth building mask as target outputs. Secondly, the generated predictions from FCN are viewed as unary terms for a Fully connected Conditional Random Fields (FCRF, which enables us to create a final binary building mask. A series of experiments demonstrate that our methodology is able to extract accurate building footprints which are close to the buildings original shapes to a high degree. The quantitative and qualitative analysis show the significant improvements of the results in contrast to the multy-layer fully connected network from our previous work.

  14. Multichannel Convolutional Neural Network for Biological Relation Extraction.

    Science.gov (United States)

    Quan, Chanqin; Hua, Lei; Sun, Xiao; Bai, Wenjun

    2016-01-01

    The plethora of biomedical relations which are embedded in medical logs (records) demands researchers' attention. Previous theoretical and practical focuses were restricted on traditional machine learning techniques. However, these methods are susceptible to the issues of "vocabulary gap" and data sparseness and the unattainable automation process in feature extraction. To address aforementioned issues, in this work, we propose a multichannel convolutional neural network (MCCNN) for automated biomedical relation extraction. The proposed model has the following two contributions: (1) it enables the fusion of multiple (e.g., five) versions in word embeddings; (2) the need for manual feature engineering can be obviated by automated feature learning with convolutional neural network (CNN). We evaluated our model on two biomedical relation extraction tasks: drug-drug interaction (DDI) extraction and protein-protein interaction (PPI) extraction. For DDI task, our system achieved an overall f-score of 70.2% compared to the standard linear SVM based system (e.g., 67.0%) on DDIExtraction 2013 challenge dataset. And for PPI task, we evaluated our system on Aimed and BioInfer PPI corpus; our system exceeded the state-of-art ensemble SVM system by 2.7% and 5.6% on f-scores.

  15. Multichannel Convolutional Neural Network for Biological Relation Extraction

    Directory of Open Access Journals (Sweden)

    Chanqin Quan

    2016-01-01

    Full Text Available The plethora of biomedical relations which are embedded in medical logs (records demands researchers’ attention. Previous theoretical and practical focuses were restricted on traditional machine learning techniques. However, these methods are susceptible to the issues of “vocabulary gap” and data sparseness and the unattainable automation process in feature extraction. To address aforementioned issues, in this work, we propose a multichannel convolutional neural network (MCCNN for automated biomedical relation extraction. The proposed model has the following two contributions: (1 it enables the fusion of multiple (e.g., five versions in word embeddings; (2 the need for manual feature engineering can be obviated by automated feature learning with convolutional neural network (CNN. We evaluated our model on two biomedical relation extraction tasks: drug-drug interaction (DDI extraction and protein-protein interaction (PPI extraction. For DDI task, our system achieved an overall f-score of 70.2% compared to the standard linear SVM based system (e.g., 67.0% on DDIExtraction 2013 challenge dataset. And for PPI task, we evaluated our system on Aimed and BioInfer PPI corpus; our system exceeded the state-of-art ensemble SVM system by 2.7% and 5.6% on f-scores.

  16. Shape Synthesis from Sketches via Procedural Models and Convolutional Networks.

    Science.gov (United States)

    Huang, Haibin; Kalogerakis, Evangelos; Yumer, Ersin; Mech, Radomir

    2017-08-01

    Procedural modeling techniques can produce high quality visual content through complex rule sets. However, controlling the outputs of these techniques for design purposes is often notoriously difficult for users due to the large number of parameters involved in these rule sets and also their non-linear relationship to the resulting content. To circumvent this problem, we present a sketch-based approach to procedural modeling. Given an approximate and abstract hand-drawn 2D sketch provided by a user, our algorithm automatically computes a set of procedural model parameters, which in turn yield multiple, detailed output shapes that resemble the user's input sketch. The user can then select an output shape, or further modify the sketch to explore alternative ones. At the heart of our approach is a deep Convolutional Neural Network (CNN) that is trained to map sketches to procedural model parameters. The network is trained by large amounts of automatically generated synthetic line drawings. By using an intuitive medium, i.e., freehand sketching as input, users are set free from manually adjusting procedural model parameters, yet they are still able to create high quality content. We demonstrate the accuracy and efficacy of our method in a variety of procedural modeling scenarios including design of man-made and organic shapes.

  17. Very Deep Convolutional Neural Networks for Morphologic Classification of Erythrocytes.

    Science.gov (United States)

    Durant, Thomas J S; Olson, Eben M; Schulz, Wade L; Torres, Richard

    2017-12-01

    Morphologic profiling of the erythrocyte population is a widely used and clinically valuable diagnostic modality, but one that relies on a slow manual process associated with significant labor cost and limited reproducibility. Automated profiling of erythrocytes from digital images by capable machine learning approaches would augment the throughput and value of morphologic analysis. To this end, we sought to evaluate the performance of leading implementation strategies for convolutional neural networks (CNNs) when applied to classification of erythrocytes based on morphology. Erythrocytes were manually classified into 1 of 10 classes using a custom-developed Web application. Using recent literature to guide architectural considerations for neural network design, we implemented a "very deep" CNN, consisting of >150 layers, with dense shortcut connections. The final database comprised 3737 labeled cells. Ensemble model predictions on unseen data demonstrated a harmonic mean of recall and precision metrics of 92.70% and 89.39%, respectively. Of the 748 cells in the test set, 23 misclassification errors were made, with a correct classification frequency of 90.60%, represented as a harmonic mean across the 10 morphologic classes. These findings indicate that erythrocyte morphology profiles could be measured with a high degree of accuracy with "very deep" CNNs. Further, these data support future efforts to expand classes and optimize practical performance in a clinical environment as a prelude to full implementation as a clinical tool. © 2017 American Association for Clinical Chemistry.

  18. Telecommunication networks

    CERN Document Server

    Iannone, Eugenio

    2011-01-01

    Many argue that telecommunications network infrastructure is the most impressive and important technology ever developed. Analyzing the telecom market's constantly evolving trends, research directions, infrastructure, and vital needs, Telecommunication Networks responds with revolutionized engineering strategies to optimize network construction. Omnipresent in society, telecom networks integrate a wide range of technologies. These include quantum field theory for the study of optical amplifiers, software architectures for network control, abstract algebra required to design error correction co

  19. Classifying Multi-year Land Use and Land Cover using Deep Convolutional Neural Networks

    Science.gov (United States)

    Seo, B.

    2015-12-01

    Cultivated ecosystems constitute a particularly frequent form of human land use. Long-term management of a cultivated ecosystem requires us to know temporal change of land use and land cover (LULC) of the target system. Land use and land cover changes (LUCC) in agricultural ecosystem is often rapid and unexpectedly occurs. Thus, longitudinal LULC is particularly needed to examine trends of ecosystem functions and ecosystem services of the target system. Multi-temporal classification of land use and land cover (LULC) in complex heterogeneous landscape remains a challenge. Agricultural landscapes often made up of a mosaic of numerous LULC classes, thus spatial heterogeneity is large. Moreover, temporal and spatial variation within a LULC class is also large. Under such a circumstance, standard classifiers would fail to identify the LULC classes correctly due to the heterogeneity of the target LULC classes. Because most standard classifiers search for a specific pattern of features for a class, they fail to detect classes with noisy and/or transformed feature data sets. Recently, deep learning algorithms have emerged in the machine learning communities and shown superior performance on a variety of tasks, including image classification and object recognition. In this paper, we propose to use convolutional neural networks (CNN) to learn from multi-spectral data to classify agricultural LULC types. Based on multi-spectral satellite data, we attempted to classify agricultural LULC classes in Soyang watershed, South Korea for the three years' study period (2009-2011). The classification performance of support vector machine (SVM) and CNN classifiers were compared for different years. Preliminary results demonstrate that the proposed method can improve classification performance compared to the SVM classifier. The SVM classifier failed to identify classes when trained on a year to predict another year, whilst CNN could reconstruct LULC maps of the catchment over the study

  20. Convolutional neural network for high-accuracy functional near-infrared spectroscopy in a brain-computer interface: three-class classification of rest, right-, and left-hand motor execution.

    Science.gov (United States)

    Trakoolwilaiwan, Thanawin; Behboodi, Bahareh; Lee, Jaeseok; Kim, Kyungsoo; Choi, Ji-Woong

    2018-01-01

    The aim of this work is to develop an effective brain-computer interface (BCI) method based on functional near-infrared spectroscopy (fNIRS). In order to improve the performance of the BCI system in terms of accuracy, the ability to discriminate features from input signals and proper classification are desired. Previous studies have mainly extracted features from the signal manually, but proper features need to be selected carefully. To avoid performance degradation caused by manual feature selection, we applied convolutional neural networks (CNNs) as the automatic feature extractor and classifier for fNIRS-based BCI. In this study, the hemodynamic responses evoked by performing rest, right-, and left-hand motor execution tasks were measured on eight healthy subjects to compare performances. Our CNN-based method provided improvements in classification accuracy over conventional methods employing the most commonly used features of mean, peak, slope, variance, kurtosis, and skewness, classified by support vector machine (SVM) and artificial neural network (ANN). Specifically, up to 6.49% and 3.33% improvement in classification accuracy was achieved by CNN compared with SVM and ANN, respectively.

  1. Interconnected networks

    CERN Document Server

    2016-01-01

    This volume provides an introduction to and overview of the emerging field of interconnected networks which include multi layer or multiplex networks, as well as networks of networks. Such networks present structural and dynamical features quite different from those observed in isolated networks. The presence of links between different networks or layers of a network typically alters the way such interconnected networks behave – understanding the role of interconnecting links is therefore a crucial step towards a more accurate description of real-world systems. While examples of such dissimilar properties are becoming more abundant – for example regarding diffusion, robustness and competition – the root of such differences remains to be elucidated. Each chapter in this topical collection is self-contained and can be read on its own, thus making it also suitable as reference for experienced researchers wishing to focus on a particular topic.

  2. El mundo CNN: ¿Cuál es el próximo país que Estados Unidos debe invadir? La percepción del consumidor mediático estadounidense y el triunfo de la propaganda

    Directory of Open Access Journals (Sweden)

    Doris Vizcarrondo

    2008-09-01

    Full Text Available Este artículo analiza las respuestas de ciudadanos estadounidenses respecto a la próxima invasión de los Estados Unidos. En entrevistas realizadas por la CNN se muestra cómo los medios de comunicación ejercen control sobre las percepciones e interpretaciones del consumidor mediático. Las opiniones de los entrevistados son producto de la mediatización de los grupos de poder (las opiniones, ideologías y valores de las élites militares, políticas y periodísticas estadounidenses. En este sentido, los entrevistados por la CNN reproducen una visión higienista (limpiar el mundo del mal y exenta de memoria histórica (respuestas sin reflexión. Un marco interpretativo que articula la política internacional mediante una dicotomía: un “Yo-Nosotros”, Estados Unidos-América (legalidad, moderación y un “Él-Ellos-Otro”, los árabes, los norcoreanos representantes de los valores rechazados por la sociedad (extremistas, ilegales. Estudiamos cómo la naturaleza del medio, la rapidez de las imágenes y el control de los contenidos (propaganda influyen en las respuestas de los entrevistados. Palabras clave: Prensa; mediatización; visión higienista; segregación de la memoria. Abstract This article analyzes the answers of American citizens about the next United State invasion. These interviews were realized by CNN show how the mass media control the perceptions and interpretations of the mass media consumer. The interviewer’s opinions are product the mediatization of the power groups (opinions, ideologies and values of military, political and press elites. In these sense, the interviewers by CNN reproduce a hygienist vision (clean the world of the badly and historic memory segregation (answers without reflection show a discourse about the present and the past of the international politics reduced to reproduce the. In this interpretative hegemonic frame the world identity is articulate by a dichotomy: “I-Us”, United Status – the

  3. Network maintenance

    CERN Multimedia

    IT Department

    2009-01-01

    A site wide network maintenance has been scheduled for Saturday 28 February. Most of the network devices of the General Purpose network will be upgraded to a newer software version, in order to improve our network monitoring capabilities. This will result in a series of short (2-5 minutes) random interruptions everywhere on the CERN sites along this day. This upgrade will not affect: the Computer centre itself, building 613, the Technical Network and the LHC experiments dedicated networks at the pits. Should you need more details on this intervention, please contact Netops by phone 74927 or email mailto:Netops@cern.ch. IT/CS Group

  4. Network maintenance

    CERN Multimedia

    GS Department

    2009-01-01

    A site-wide network maintenance operation has been scheduled for Saturday 28 February. Most of the network devices of the general purpose network will be upgraded to a newer software version, in order to improve our network monitoring capabilities. This will result in a series of short (2-5 minutes) random interruptions everywhere on the CERN sites throughout the day. This upgrade will not affect the Computer Centre itself, Building 613, the Technical Network and the LHC experiments, dedicated networks at the pits. For further details of this intervention, please contact Netops by phone 74927 or e-mail mailto:Netops@cern.ch. IT/CS Group

  5. Training and Validating a Deep Convolutional Neural Network for Computer-Aided Detection and Classification of Abnormalities on Frontal Chest Radiographs.

    Science.gov (United States)

    Cicero, Mark; Bilbily, Alexander; Colak, Errol; Dowdell, Tim; Gray, Bruce; Perampaladas, Kuhan; Barfett, Joseph

    2017-05-01

    Convolutional neural networks (CNNs) are a subtype of artificial neural network that have shown strong performance in computer vision tasks including image classification. To date, there has been limited application of CNNs to chest radiographs, the most frequently performed medical imaging study. We hypothesize CNNs can learn to classify frontal chest radiographs according to common findings from a sufficiently large data set. Our institution's research ethics board approved a single-center retrospective review of 35,038 adult posterior-anterior chest radiographs and final reports performed between 2005 and 2015 (56% men, average age of 56, patient type: 24% inpatient, 39% outpatient, 37% emergency department) with a waiver for informed consent. The GoogLeNet CNN was trained using 3 graphics processing units to automatically classify radiographs as normal (n = 11,702) or into 1 or more of cardiomegaly (n = 9240), consolidation (n = 6788), pleural effusion (n = 7786), pulmonary edema (n = 1286), or pneumothorax (n = 1299). The network's performance was evaluated using receiver operating curve analysis on a test set of 2443 radiographs with the criterion standard being board-certified radiologist interpretation. Using 256 × 256-pixel images as input, the network achieved an overall sensitivity and specificity of 91% with an area under the curve of 0.964 for classifying a study as normal (n = 1203). For the abnormal categories, the sensitivity, specificity, and area under the curve, respectively, were 91%, 91%, and 0.962 for pleural effusion (n = 782), 82%, 82%, and 0.868 for pulmonary edema (n = 356), 74%, 75%, and 0.850 for consolidation (n = 214), 81%, 80%, and 0.875 for cardiomegaly (n = 482), and 78%, 78%, and 0.861 for pneumothorax (n = 167). Current deep CNN architectures can be trained with modest-sized medical data sets to achieve clinically useful performance at detecting and excluding common pathology on chest radiographs.

  6. Automated diagnosis of prostate cancer in multi-parametric MRI based on multimodal convolutional neural networks

    Science.gov (United States)

    Le, Minh Hung; Chen, Jingyu; Wang, Liang; Wang, Zhiwei; Liu, Wenyu; (Tim Cheng, Kwang-Ting; Yang, Xin

    2017-08-01

    Automated methods for prostate cancer (PCa) diagnosis in multi-parametric magnetic resonance imaging (MP-MRIs) are critical for alleviating requirements for interpretation of radiographs while helping to improve diagnostic accuracy (Artan et al 2010 IEEE Trans. Image Process. 19 2444-55, Litjens et al 2014 IEEE Trans. Med. Imaging 33 1083-92, Liu et al 2013 SPIE Medical Imaging (International Society for Optics and Photonics) p 86701G, Moradi et al 2012 J. Magn. Reson. Imaging 35 1403-13, Niaf et al 2014 IEEE Trans. Image Process. 23 979-91, Niaf et al 2012 Phys. Med. Biol. 57 3833, Peng et al 2013a SPIE Medical Imaging (International Society for Optics and Photonics) p 86701H, Peng et al 2013b Radiology 267 787-96, Wang et al 2014 BioMed. Res. Int. 2014). This paper presents an automated method based on multimodal convolutional neural networks (CNNs) for two PCa diagnostic tasks: (1) distinguishing between cancerous and noncancerous tissues and (2) distinguishing between clinically significant (CS) and indolent PCa. Specifically, our multimodal CNNs effectively fuse apparent diffusion coefficients (ADCs) and T2-weighted MP-MRI images (T2WIs). To effectively fuse ADCs and T2WIs we design a new similarity loss function to enforce consistent features being extracted from both ADCs and T2WIs. The similarity loss is combined with the conventional classification loss functions and integrated into the back-propagation procedure of CNN training. The similarity loss enables better fusion results than existing methods as the feature learning processes of both modalities are mutually guided, jointly facilitating CNN to ‘see’ the true visual patterns of PCa. The classification results of multimodal CNNs are further combined with the results based on handcrafted features using a support vector machine classifier. To achieve a satisfactory accuracy for clinical use, we comprehensively investigate three critical factors which could greatly affect the performance of our

  7. Network Ambivalence

    Directory of Open Access Journals (Sweden)

    Patrick Jagoda

    2015-08-01

    Full Text Available The language of networks now describes everything from the Internet to the economy to terrorist organizations. In distinction to a common view of networks as a universal, originary, or necessary form that promises to explain everything from neural structures to online traffic, this essay emphasizes the contingency of the network imaginary. Network form, in its role as our current cultural dominant, makes scarcely imaginable the possibility of an alternative or an outside uninflected by networks. If so many things and relationships are figured as networks, however, then what is not a network? If a network points towards particular logics and qualities of relation in our historical present, what others might we envision in the future? In  many ways, these questions are unanswerable from within the contemporary moment. Instead of seeking an avant-garde approach (to move beyond networks or opting out of networks (in some cases, to recover elements of pre-networked existence, this essay proposes a third orientation: one of ambivalence that operates as a mode of extreme presence. I propose the concept of "network aesthetics," which can be tracked across artistic media and cultural forms, as a model, style, and pedagogy for approaching interconnection in the twenty-first century. The following essay is excerpted from Network Ambivalence (Forthcoming from University of Chicago Press. 

  8. End-to-End Multimodal Emotion Recognition Using Deep Neural Networks

    Science.gov (United States)

    Tzirakis, Panagiotis; Trigeorgis, George; Nicolaou, Mihalis A.; Schuller, Bjorn W.; Zafeiriou, Stefanos

    2017-12-01

    Automatic affect recognition is a challenging task due to the various modalities emotions can be expressed with. Applications can be found in many domains including multimedia retrieval and human computer interaction. In recent years, deep neural networks have been used with great success in determining emotional states. Inspired by this success, we propose an emotion recognition system using auditory and visual modalities. To capture the emotional content for various styles of speaking, robust features need to be extracted. To this purpose, we utilize a Convolutional Neural Network (CNN) to extract features from the speech, while for the visual modality a deep residual network (ResNet) of 50 layers. In addition to the importance of feature extraction, a machine learning algorithm needs also to be insensitive to outliers while being able to model the context. To tackle this problem, Long Short-Term Memory (LSTM) networks are utilized. The system is then trained in an end-to-end fashion where - by also taking advantage of the correlations of the each of the streams - we manage to significantly outperform the traditional approaches based on auditory and visual handcrafted features for the prediction of spontaneous and natural emotions on the RECOLA database of the AVEC 2016 research challenge on emotion recognition.

  9. Multi-Temporal Land Cover Classification with Long Short-Term Memory Neural Networks

    Science.gov (United States)

    Rußwurm, M.; Körner, M.

    2017-05-01

    Land cover classification (LCC) is a central and wide field of research in earth observation and has already put forth a variety of classification techniques. Many approaches are based on classification techniques considering observation at certain points in time. However, some land cover classes, such as crops, change their spectral characteristics due to environmental influences and can thus not be monitored effectively with classical mono-temporal approaches. Nevertheless, these temporal observations should be utilized to benefit the classification process. After extensive research has been conducted on modeling temporal dynamics by spectro-temporal profiles using vegetation indices, we propose a deep learning approach to utilize these temporal characteristics for classification tasks. In this work, we show how long short-term memory (LSTM) neural networks can be employed for crop identification purposes with SENTINEL 2A observations from large study areas and label information provided by local authorities. We compare these temporal neural network models, i.e., LSTM and recurrent neural network (RNN), with a classical non-temporal convolutional neural network (CNN) model and an additional support vector machine (SVM) baseline. With our rather straightforward LSTM variant, we exceeded state-of-the-art classification performance, thus opening promising potential for further research.

  10. MULTI-TEMPORAL LAND COVER CLASSIFICATION WITH LONG SHORT-TERM MEMORY NEURAL NETWORKS

    Directory of Open Access Journals (Sweden)

    M. Rußwurm

    2017-05-01

    Full Text Available Land cover classification (LCC is a central and wide field of research in earth observation and has already put forth a variety of classification techniques. Many approaches are based on classification techniques considering observation at certain points in time. However, some land cover classes, such as crops, change their spectral characteristics due to environmental influences and can thus not be monitored effectively with classical mono-temporal approaches. Nevertheless, these temporal observations should be utilized to benefit the classification process. After extensive research has been conducted on modeling temporal dynamics by spectro-temporal profiles using vegetation indices, we propose a deep learning approach to utilize these temporal characteristics for classification tasks. In this work, we show how long short-term memory (LSTM neural networks can be employed for crop identification purposes with SENTINEL 2A observations from large study areas and label information provided by local authorities. We compare these temporal neural network models, i.e., LSTM and recurrent neural network (RNN, with a classical non-temporal convolutional neural network (CNN model and an additional support vector machine (SVM baseline. With our rather straightforward LSTM variant, we exceeded state-of-the-art classification performance, thus opening promising potential for further research.

  11. ChemNet: A Transferable and Generalizable Deep Neural Network for Small-Molecule Property Prediction

    Energy Technology Data Exchange (ETDEWEB)

    Goh, Garrett B.; Siegel, Charles M.; Vishnu, Abhinav; Hodas, Nathan O.

    2017-12-08

    With access to large datasets, deep neural networks through representation learning have been able to identify patterns from raw data, achieving human-level accuracy in image and speech recognition tasks. However, in chemistry, availability of large standardized and labelled datasets is scarce, and with a multitude of chemical properties of interest, chemical data is inherently small and fragmented. In this work, we explore transfer learning techniques in conjunction with the existing Chemception CNN model, to create a transferable and generalizable deep neural network for small-molecule property prediction. Our latest model, ChemNet learns in a semi-supervised manner from inexpensive labels computed from the ChEMBL database. When fine-tuned to the Tox21, HIV and FreeSolv dataset, which are 3 separate chemical tasks that ChemNet was not originally trained on, we demonstrate that ChemNet exceeds the performance of existing Chemception models, contemporary MLP models that trains on molecular fingerprints, and it matches the performance of the ConvGraph algorithm, the current state-of-the-art. Furthermore, as ChemNet has been pre-trained on a large diverse chemical database, it can be used as a universal “plug-and-play” deep neural network, which accelerates the deployment of deep neural networks for the prediction of novel small-molecule chemical properties.

  12. Network neuroscience.

    Science.gov (United States)

    Bassett, Danielle S; Sporns, Olaf

    2017-02-23

    Despite substantial recent progress, our understanding of the principles and mechanisms underlying complex brain function and cognition remains incomplete. Network neuroscience proposes to tackle these enduring challenges. Approaching brain structure and function from an explicitly integrative perspective, network neuroscience pursues new ways to map, record, analyze and model the elements and interactions of neurobiological systems. Two parallel trends drive the approach: the availability of new empirical tools to create comprehensive maps and record dynamic patterns among molecules, neurons, brain areas and social systems; and the theoretical framework and computational tools of modern network science. The convergence of empirical and computational advances opens new frontiers of scientific inquiry, including network dynamics, manipulation and control of brain networks, and integration of network processes across spatiotemporal domains. We review emerging trends in network neuroscience and attempt to chart a path toward a better understanding of the brain as a multiscale networked system.

  13. Organizational Networks

    DEFF Research Database (Denmark)

    Grande, Bård; Sørensen, Ole Henning

    1998-01-01

    The paper focuses on the concept of organizational networks. Four different uses of the concept of organizational network are identified and critically discussed. Special focus is placed on how information and communication technologies as communication mediators and cognitive pictures influence...

  14. Network workshop

    DEFF Research Database (Denmark)

    Bruun, Jesper; Evans, Robert Harry

    2014-01-01

    This paper describes the background for, realisation of and author reflections on a network workshop held at ESERA2013. As a new research area in science education, networks offer a unique opportunity to visualise and find patterns and relationships in complicated social or academic network data...... research community. With this workshop, participants were offered a way into network science based on authentic educational research data. The workshop was constructed as an inquiry lesson with emphasis on user autonomy. Learning activities had participants choose to work with one of two cases of networks...... network methodology in one’s research might supersede the perceived benefits of doing so. As a response to that problem, we argue that workshops can act as a road towards meaningful engagement with networks and highlight that network methodology promises new ways of interpreting data to answer questions...

  15. An Ensemble of Fine-Tuned Convolutional Neural Networks for Medical Image Classification.

    Science.gov (United States)

    Kumar, Ashnil; Kim, Jinman; Lyndon, David; Fulham, Michael; Feng, Dagan

    2017-01-01

    The availability of medical imaging data from clinical archives, research literature, and clinical manuals, coupled with recent advances in computer vision offer the opportunity for image-based diagnosis, teaching, and biomedical research. However, the content and semantics of an image can vary depending on its modality and as such the identification of image modality is an important preliminary step. The key challenge for automatically classifying the modality of a medical image is due to the visual characteristics of different modalities: some are visually distinct while others may have only subtle differences. This challenge is compounded by variations in the appearance of images based on the diseases depicted and a lack of sufficient training data for some modalities. In this paper, we introduce a new method for classifying medical images that uses an ensemble of different convolutional neural network (CNN) architectures. CNNs are a state-of-the-art image classification technique that learns the optimal image features for a given classification task. We hypothesise that different CNN architectures learn different levels of semantic image representation and thus an ensemble of CNNs will enable higher quality features to be extracted. Our method develops a new feature extractor by fine-tuning CNNs that have been initialized on a large dataset of natural images. The fine-tuning process leverages the generic image features from natural images that are fundamental for all images and optimizes them for the variety of medical imaging modalities. These features are used to train numerous multiclass classifiers whose posterior probabilities are fused to predict the modalities of unseen images. Our experiments on the ImageCLEF 2016 medical image public dataset (30 modalities; 6776 training images, and 4166 test images) show that our ensemble of fine-tuned CNNs achieves a higher accuracy than established CNNs. Our ensemble also achieves a higher accuracy than methods in

  16. A deep convolutional neural network approach to single-particle recognition in cryo-electron microscopy.

    Science.gov (United States)

    Zhu, Yanan; Ouyang, Qi; Mao, Youdong

    2017-07-21

    Single-particle cryo-electron microscopy (cryo-EM) has become a mainstream tool for the structural determination of biological macromolecular complexes. However, high-resolution cryo-EM reconstruction often requires hundreds of thousands of single-particle images. Particle extraction from experimental micrographs thus can be laborious and presents a major practical bottleneck in cryo-EM structural determination. Existing computational methods for particle picking often use low-resolution templates for particle matching, making them susceptible to reference-dependent bias. It is critical to develop a highly efficient template-free method for the automatic recognition of particle images from cryo-EM micrographs. We developed a deep learning-based algorithmic framework, DeepEM, for single-particle recognition from noisy cryo-EM micrographs, enabling automated particle picking, selection and verification in an integrated fashion. The kernel of DeepEM is built upon a convolutional neural network (CNN) composed of eight layers, which can be recursively trained to be highly "knowledgeable". Our approach exhibits an improved performance and accuracy when tested on the standard KLH dataset. Application of DeepEM to several challenging experimental cryo-EM datasets demonstrated its ability to avoid the selection of un-wanted particles and non-particles even when true particles contain fewer features. The DeepEM methodology, derived from a deep CNN, allows automated particle extraction from raw cryo-EM micrographs in the absence of a template. It demonstrates an improved performance, objectivity and accuracy. Application of this novel method is expected to free the labor involved in single-particle verification, significantly improving the efficiency of cryo-EM data processing.

  17. Arabic Handwritten Digit Recognition Based on Restricted Boltzmann Machine and Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Ali A. Alani

    2017-11-01

    Full Text Available Handwritten digit recognition is an open problem in computer vision and pattern recognition, and solving this problem has elicited increasing interest. The main challenge of this problem is the design of an efficient method that can recognize the handwritten digits that are submitted by the user via digital devices. Numerous studies have been proposed in the past and in recent years to improve handwritten digit recognition in various languages. Research on handwritten digit recognition in Arabic is limited. At present, deep learning algorithms are extremely popular in computer vision and are used to solve and address important problems, such as image classification, natural language processing, and speech recognition, to provide computers with sensory capabilities that reach the ability of humans. In this study, we propose a new approach for Arabic handwritten digit recognition by use of restricted Boltzmann machine (RBM and convolutional neural network (CNN deep learning algorithms. In particular, we propose an Arabic handwritten digit recognition approach that works in two phases. First, we use the RBM, which is a deep learning technique that can extract highly useful features from raw data, and which has been utilized in several classification problems as a feature extraction technique in the feature extraction phase. Then, the extracted features are fed to an efficient CNN architecture with a deep supervised learning architecture for the training and testing process. In the experiment, we used the CMATERDB 3.3.1 Arabic handwritten digit dataset for training and testing the proposed method. Experimental results show that the proposed method significantly improves the accuracy rate, with accuracy reaching 98.59%. Finally, comparison of our results with those of other studies on the CMATERDB 3.3.1 Arabic handwritten digit dataset shows that our approach achieves the highest accuracy rate.

  18. 3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study.

    Science.gov (United States)

    Dolz, Jose; Desrosiers, Christian; Ben Ayed, Ismail

    2017-04-24

    This study investigates a 3D and fully convolutional neural network (CNN) for subcortical brain structure segmentation in MRI. 3D CNN architectures have been generally avoided due to their computational and memory requirements during inference. We address the problem via small kernels, allowing deeper architectures. We further model both local and global context by embedding intermediate-layer outputs in the final prediction, which encourages consistency between features extracted at different scales and embeds fine-grained information directly in the segmentation process. Our model is efficiently trained end-to-end on a graphics processing unit (GPU), in a single stage, exploiting the dense inference capabilities of fully CNNs. We performed comprehensive experiments over two publicly available datasets. First, we demonstrate a state-of-the-art performance on the ISBR dataset. Then, we report a large-scale multi-site evaluation over 1112 unregistered subject datasets acquired from 17 different sites (ABIDE dataset), with ages ranging from 7 to 64 years, showing that our method is robust to various acquisition protocols, demographics and clinical factors. Our method yielded segmentations that are highly consistent with a standard atlas-based approach, while running in a fraction of the time needed by atlas-based methods and avoiding registration/normalization steps. This makes it convenient for massive multi-site neuroanatomical imaging studies. To the best of our knowledge, our work is the first to study subcortical structure segmentation on such large-scale and heterogeneous data. Copyright © 2017 Elsevier Inc. All rights reserved.

  19. Deep MRI brain extraction: A 3D convolutional neural network for skull stripping.

    Science.gov (United States)

    Kleesiek, Jens; Urban, Gregor; Hubert, Alexander; Schwarz, Daniel; Maier-Hein, Klaus; Bendszus, Martin; Biller, Armin

    2016-04-01

    Brain extraction from magnetic resonance imaging (MRI) is crucial for many neuroimaging workflows. Current methods demonstrate good results on non-enhanced T1-weighted images, but struggle when confronted with other modalities and pathologically altered tissue. In this paper we present a 3D convolutional deep learning architecture to address these shortcomings. In contrast to existing methods, we are not limited to non-enhanced T1w images. When trained appropriately, our approach handles an arbitrary number of modalities including contrast-enhanced scans. Its applicability to MRI data, comprising four channels: non-enhanced and contrast-enhanced T1w, T2w and FLAIR contrasts, is demonstrated on a challenging clinical data set containing brain tumors (N=53), where our approach significantly outperforms six commonly used tools with a mean Dice score of 95.19. Further, the proposed method at least matches state-of-the-art performance as demonstrated on three publicly available data sets: IBSR, LPBA40 and OASIS, totaling N=135 volumes. For the IBSR (96.32) and LPBA40 (96.96) data set the convolutional neuronal network (CNN) obtains the highest average Dice scores, albeit not being significantly different from the second best performing method. For the OASIS data the second best Dice (95.02) results are achieved, with no statistical difference in comparison to the best performing tool. For all data sets the highest average specificity measures are evaluated, whereas the sensitivity displays about average results. Adjusting the cut-off threshold for generating the binary masks from the CNN's probability output can be used to increase the sensitivity of the method. Of course, this comes at the cost of a decreased specificity and has to be decided application specific. Using an optimized GPU implementation predictions can be achieved in less than one minute. The proposed method may prove useful for large-scale studies and clinical trials. Copyright © 2016 Elsevier Inc. All

  20. SINGLE-IMAGE SUPER RESOLUTION FOR MULTISPECTRAL REMOTE SENSING DATA USING CONVOLUTIONAL NEURAL NETWORKS

    Directory of Open Access Journals (Sweden)

    L. Liebel

    2016-06-01

    Full Text Available In optical remote sensing, spatial resolution of images is crucial for numerous applications. Space-borne systems are most likely to be affected by a lack of spatial resolution, due to their natural disadvantage of a large distance between the sensor and the sensed object. Thus, methods for single-image super resolution are desirable to exceed the limits of the sensor. Apart from assisting visual inspection of datasets, post-processing operations—e.g., segmentation or feature extraction—can benefit from detailed and distinguishable structures. In this paper, we show that recently introduced state-of-the-art approaches for single-image super resolution of conventional photographs, making use of deep learning techniques, such as convolutional neural networks (CNN, can successfully be applied to remote sensing data. With a huge amount of training data available, end-to-end learning is reasonably easy to apply and can achieve results unattainable using conventional handcrafted algorithms. We trained our CNN on a specifically designed, domain-specific dataset, in order to take into account the special characteristics of multispectral remote sensing data. This dataset consists of publicly available SENTINEL-2 images featuring 13 spectral bands, a ground resolution of up to 10m, and a high radiometric resolution and thus satisfying our requirements in terms of quality and quantity. In experiments, we obtained results superior compared to competing approaches trained on generic image sets, which failed to reasonably scale satellite images with a high radiometric resolution, as well as conventional interpolation methods.

  1. A deep convolutional neural network for classification of red blood cells in sickle cell anemia.

    Directory of Open Access Journals (Sweden)

    Mengjia Xu

    2017-10-01

    Full Text Available Sickle cell disease (SCD is a hematological disorder leading to blood vessel occlusion accompanied by painful episodes and even death. Red blood cells (RBCs of SCD patients have diverse shapes that reveal important biomechanical and bio-rheological characteristics, e.g. their density, fragility, adhesive properties, etc. Hence, having an objective and effective way of RBC shape quantification and classification will lead to better insights and eventual better prognosis of the disease. To this end, we have developed an automated, high-throughput, ex-vivo RBC shape classification framework that consists of three stages. First, we present an automatic hierarchical RBC extraction method to detect the RBC region (ROI from the background, and then separate touching RBCs in the ROI images by applying an improved random walk method based on automatic seed generation. Second, we apply a mask-based RBC patch-size normalization method to normalize the variant size of segmented single RBC patches into uniform size. Third, we employ deep convolutional neural networks (CNNs to realize RBC classification; the alternating convolution and pooling operations can deal with non-linear and complex patterns. Furthermore, we investigate the specific shape factor quantification for the classified RBC image data in order to develop a general multiscale shape analysis. We perform several experiments on raw microscopy image datasets from 8 SCD patients (over 7,000 single RBC images through a 5-fold cross validation method both for oxygenated and deoxygenated RBCs. We demonstrate that the proposed framework can successfully classify sickle shape RBCs in an automated manner with high accuracy, and we also provide the corresponding shape factor analysis, which can be used synergistically with the CNN analysis for more robust predictions. Moreover, the trained deep CNN exhibits good performance even for a deoxygenated dataset and distinguishes the subtle differences in

  2. A deep convolutional neural network for classification of red blood cells in sickle cell anemia.

    Science.gov (United States)

    Xu, Mengjia; Papageorgiou, Dimitrios P; Abidi, Sabia Z; Dao, Ming; Zhao, Hong; Karniadakis, George Em

    2017-10-01

    Sickle cell disease (SCD) is a hematological disorder leading to blood vessel occlusion accompanied by painful episodes and even death. Red blood cells (RBCs) of SCD patients have diverse shapes that reveal important biomechanical and bio-rheological characteristics, e.g. their density, fragility, adhesive properties, etc. Hence, having an objective and effective way of RBC shape quantification and classification will lead to better insights and eventual better prognosis of the disease. To this end, we have developed an automated, high-throughput, ex-vivo RBC shape classification framework that consists of three stages. First, we present an automatic hierarchical RBC extraction method to detect the RBC region (ROI) from the background, and then separate touching RBCs in the ROI images by applying an improved random walk method based on automatic seed generation. Second, we apply a mask-based RBC patch-size normalization method to normalize the variant size of segmented single RBC patches into uniform size. Third, we employ deep convolutional neural networks (CNNs) to realize RBC classification; the alternating convolution and pooling operations can deal with non-linear and complex patterns. Furthermore, we investigate the specific shape factor quantification for the classified RBC image data in order to develop a general multiscale shape analysis. We perform several experiments on raw microscopy image datasets from 8 SCD patients (over 7,000 single RBC images) through a 5-fold cross validation method both for oxygenated and deoxygenated RBCs. We demonstrate that the proposed framework can successfully classify sickle shape RBCs in an automated manner with high accuracy, and we also provide the corresponding shape factor analysis, which can be used synergistically with the CNN analysis for more robust predictions. Moreover, the trained deep CNN exhibits good performance even for a deoxygenated dataset and distinguishes the subtle differences in texture alteration

  3. Social Networks

    OpenAIRE

    Martí, Joan; Zenou, Yves

    2009-01-01

    We survey the literature on social networks by putting together the economics, sociological and physics/applied mathematics approaches, showing their similarities and differences. We expose, in particular, the two main ways of modeling network formation. While the physics/applied mathematics approach is capable of reproducing most observed networks, it does not explain why they emerge. On the contrary, the economics approach is very precise in explaining why networks emerge but does a poor jo...

  4. Network Coding

    Indian Academy of Sciences (India)

    Network coding is a technique to increase the amount of information °ow in a network by mak- ing the key observation that information °ow is fundamentally different from commodity °ow. Whereas, under traditional methods of opera- tion of data networks, intermediate nodes are restricted to simply forwarding their incoming.

  5. Discriminating between benign and malignant breast tumors using 3D convolutional neural network in dynamic contrast enhanced-MR images

    Science.gov (United States)

    Li, Jing; Fan, Ming; Zhang, Juan; Li, Lihua

    2017-03-01

    Convolutional neural networks (CNNs) are the state-of-the-art deep learning network architectures that can be used in a range of applications, including computer vision and medical image analysis. It exhibits a powerful representation learning mechanism with an automated design to learn features directly from the data. However, the common 2D CNNs only use the two dimension spatial information without evaluating the correlation between the adjoin slices. In this study, we established a method of 3D CNNs to discriminate between malignant and benign breast tumors. To this end, 143 patients were enrolled which include 66 benign and 77 malignant instances. The MRI images were pre-processed for noise reduction and breast tumor region segmentation. Data augmentation by spatial translating, rotating and vertical and horizontal flipping is applied to the cases to reduce possible over-fitting. A region-of-interest (ROI) and a volume-of-interest (VOI) were segmented in 2D and 3D DCE-MRI, respectively. The enhancement ratio for each MR series was calculated for the 2D and 3D images. The results for the enhancement ratio images in the two series are integrated for classification. The results of the area under the ROC curve(AUC) values are 0.739 and 0.801 for 2D and 3D methods, respectively. The results for 3D CNN which combined 5 slices for each enhancement ratio images achieved a high accuracy(Acc), sensitivity(Sens) and specificity(Spec) of 0.781, 0.744 and 0.823, respectively. This study indicates that 3D CNN deep learning methods can be a promising technology for breast tumor classification without manual feature extraction.

  6. Technical Network

    CERN Multimedia

    2007-01-01

    In order to optimise the management of the Technical Network (TN), to facilitate understanding of the purpose of devices connected to the TN and to improve security incident handling, the Technical Network Administrators and the CNIC WG have asked IT/CS to verify the "description" and "tag" fields of devices connected to the TN. Therefore, persons responsible for systems connected to the TN will receive e-mails from IT/CS asking them to add the corresponding information in the network database at "network-cern-ch". Thank you very much for your cooperation. The Technical Network Administrators & the CNIC WG

  7. Network science

    CERN Document Server

    Barabasi, Albert-Laszlo

    2016-01-01

    Networks are everywhere, from the Internet, to social networks, and the genetic networks that determine our biological existence. Illustrated throughout in full colour, this pioneering textbook, spanning a wide range of topics from physics to computer science, engineering, economics and the social sciences, introduces network science to an interdisciplinary audience. From the origins of the six degrees of separation to explaining why networks are robust to random failures, the author explores how viruses like Ebola and H1N1 spread, and why it is that our friends have more friends than we do. Using numerous real-world examples, this innovatively designed text includes clear delineation between undergraduate and graduate level material. The mathematical formulas and derivations are included within Advanced Topics sections, enabling use at a range of levels. Extensive online resources, including films and software for network analysis, make this a multifaceted companion for anyone with an interest in network sci...

  8. Vulnerability of network of networks

    Science.gov (United States)

    Havlin, S.; Kenett, D. Y.; Bashan, A.; Gao, J.; Stanley, H. E.

    2014-10-01

    Our dependence on networks - be they infrastructure, economic, social or others - leaves us prone to crises caused by the vulnerabilities of these networks. There is a great need to develop new methods to protect infrastructure networks and prevent cascade of failures (especially in cases of coupled networks). Terrorist attacks on transportation networks have traumatized modern societies. With a single blast, it has become possible to paralyze airline traffic, electric power supply, ground transportation or Internet communication. How, and at which cost can one restructure the network such that it will become more robust against malicious attacks? The gradual increase in attacks on the networks society depends on - Internet, mobile phone, transportation, air travel, banking, etc. - emphasize the need to develop new strategies to protect and defend these crucial networks of communication and infrastructure networks. One example is the threat of liquid explosives a few years ago, which completely shut down air travel for days, and has created extreme changes in regulations. Such threats and dangers warrant the need for new tools and strategies to defend critical infrastructure. In this paper we review recent advances in the theoretical understanding of the vulnerabilities of interdependent networks with and without spatial embedding, attack strategies and their affect on such networks of networks as well as recently developed strategies to optimize and repair failures caused by such attacks.

  9. Image aesthetic quality evaluation using convolution neural network embedded learning

    Science.gov (United States)

    Li, Yu-xin; Pu, Yuan-yuan; Xu, Dan; Qian, Wen-hua; Wang, Li-peng

    2017-11-01

    A way of embedded learning convolution neural network (ELCNN) based on the image content is proposed to evaluate the image aesthetic quality in this paper. Our approach can not only solve the problem of small-scale data but also score the image aesthetic quality. First, we chose Alexnet and VGG_S to compare for confirming which is more suitable for this image aesthetic quality evaluation task. Second, to further boost the image aesthetic quality classification performance, we employ the image content to train aesthetic quality classification models. But the training samples become smaller and only using once fine-tuning cannot make full use of the small-scale data set. Third, to solve the problem in second step, a way of using twice fine-tuning continually based on the aesthetic quality label and content label respective is proposed, the classification probability of the trained CNN models is used to evaluate the image aesthetic quality. The experiments are carried on the small-scale data set of Photo Quality. The experiment results show that the classification accuracy rates of our approach are higher than the existing image aesthetic quality evaluation approaches.

  10. Classification of breast cancer cytological specimen using convolutional neural network

    Science.gov (United States)

    Żejmo, Michał; Kowal, Marek; Korbicz, Józef; Monczak, Roman

    2017-01-01

    The paper presents a deep learning approach for automatic classification of breast tumors based on fine needle cytology. The main aim of the system is to distinguish benign from malignant cases based on microscopic images. Experiment was carried out on cytological samples derived from 50 patients (25 benign cases + 25 malignant cases) diagnosed in Regional Hospital in Zielona Góra. To classify microscopic images, we used convolutional neural networks (CNN) of two types: GoogLeNet and AlexNet. Due to the very large size of images of cytological specimen (on average 200000 × 100000 pixels), they were divided into smaller patches of size 256 × 256 pixels. Breast cancer classification usually is based on morphometric features of nuclei. Therefore, training and validation patches were selected using Support Vector Machine (SVM) so that suitable amount of cell material was depicted. Neural classifiers were tuned using GPU accelerated implementation of gradient descent algorithm. Training error was defined as a cross-entropy classification loss. Classification accuracy was defined as the percentage ratio of successfully classified validation patches to the total number of validation patches. The best accuracy rate of 83% was obtained by GoogLeNet model. We observed that more misclassified patches belong to malignant cases.

  11. Gearbox Fault Identification and Classification with Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    ZhiQiang Chen

    2015-01-01

    Full Text Available Vibration signals of gearbox are sensitive to the existence of the fault. Based on vibration signals, this paper presents an implementation of deep learning algorithm convolutional neural network (CNN used for fault identification and classification in gearboxes. Different combinations of condition patterns based on some basic fault conditions are considered. 20 test cases with different combinations of condition patterns are used, where each test case includes 12 combinations of different basic condition patterns. Vibration signals are preprocessed using statistical measures from the time domain signal such as standard deviation, skewness, and kurtosis. In the frequency domain, the spectrum obtained with FFT is divided into multiple bands, and the root mean square (RMS value is calculated for each one so the energy maintains its shape at the spectrum peaks. The achieved accuracy indicates that the proposed approach is highly reliable and applicable in fault diagnosis of industrial reciprocating machinery. Comparing with peer algorithms, the present method exhibits the best performance in the gearbox fault diagnosis.

  12. Coronary artery calcification (CAC) classification with deep convolutional neural networks

    Science.gov (United States)

    Liu, Xiuming; Wang, Shice; Deng, Yufeng; Chen, Kuan

    2017-03-01

    Coronary artery calcification (CAC) is a typical marker of the coronary artery disease, which is one of the biggest causes of mortality in the U.S. This study evaluates the feasibility of using a deep convolutional neural network (DCNN) to automatically detect CAC in X-ray images. 1768 posteroanterior (PA) view chest X-Ray images from Sichuan Province Peoples Hospital, China were collected retrospectively. Each image is associated with a corresponding diagnostic report written by a trained radiologist (907 normal, 861 diagnosed with CAC). Onequarter of the images were randomly selected as test samples; the rest were used as training samples. DCNN models consisting of 2,4,6 and 8 convolutional layers were designed using blocks of pre-designed CNN layers. Each block was implemented in Theano with Graphics Processing Units (GPU). Human-in-the-loop learning was also performed on a subset of 165 images with framed arteries by trained physicians. The results from the DCNN models were compared to the diagnostic reports. The average diagnostic accuracies for models with 2,4,6,8 layers were 0.85, 0.87, 0.88, and 0.89 respectively. The areas under the curve (AUC) were 0.92, 0.95, 0.95, and 0.96. As the model grows deeper, the AUC or diagnostic accuracies did not have statistically significant changes. The results of this study indicate that DCNN models have promising potential in the field of intelligent medical image diagnosis practice.

  13. Skin Lesion Analysis towards Melanoma Detection Using Deep Learning Network.

    Science.gov (United States)

    Li, Yuexiang; Shen, Linlin

    2018-02-11

    Skin lesions are a severe disease globally. Early detection of melanoma in dermoscopy images significantly increases the survival rate. However, the accurate recognition of melanoma is extremely challenging due to the following reasons: low contrast between lesions and skin, visual similarity between melanoma and non-melanoma lesions, etc. Hence, reliable automatic detection of skin tumors is very useful to increase the accuracy and efficiency of pathologists. In this paper, we proposed two deep learning methods to address three main tasks emerging in the area of skin lesion image processing, i.e., lesion segmentation (task 1), lesion dermoscopic feature extraction (task 2) and lesion classification (task 3). A deep learning framework consisting of two fully convolutional residual networks (FCRN) is proposed to simultaneously produce the segmentation result and the coarse classification result. A lesion index calculation unit (LICU) is developed to refine the coarse classification results by calculating the distance heat-map. A straight-forward CNN is proposed for the dermoscopic feature extraction task. The proposed deep learning frameworks were evaluated on the ISIC 2017 dataset. Experimental results show the promising accuracies of our frameworks, i.e., 0.753 for task 1, 0.848 for task 2 and 0.912 for task 3 were achieved.

  14. Convolutional Neural Networks for Inverse Problems in Imaging: A Review

    Science.gov (United States)

    McCann, Michael T.; Jin, Kyong Hwan; Unser, Michael

    2017-11-01

    In this survey paper, we review recent uses of convolution neural networks (CNNs) to solve inverse problems in imaging. It has recently become feasible to train deep CNNs on large databases of images, and they have shown outstanding performance on object classification and segmentation tasks. Motivated by these successes, researchers have begun to apply CNNs to the resolution of inverse problems such as denoising, deconvolution, super-resolution, and medical image reconstruction, and they have started to report improvements over state-of-the-art methods, including sparsity-based techniques such as compressed sensing. Here, we review the recent experimental work in these areas, with a focus on the critical design decisions: Where does the training data come from? What is the architecture of the CNN? and How is the learning problem formulated and solved? We also bring together a few key theoretical papers that offer perspective on why CNNs are appropriate for inverse problems and point to some next steps in the field.

  15. Network Coded Software Defined Networking

    DEFF Research Database (Denmark)

    Hansen, Jonas; Roetter, Daniel Enrique Lucani; Krigslund, Jeppe

    2015-01-01

    . The inherent flexibility of both SDN and NC provides fertile ground to envision more efficient, robust, and secure networking designs, which may also incorporate content caching and storage, all of which are key challenges of the upcoming 5G networks. This article not only proposes the fundamentals......Software defined networking has garnered large attention due to its potential to virtualize services in the Internet, introducing flexibility in the buffering, scheduling, processing, and routing of data in network routers. SDN breaks the deadlock that has kept Internet network protocols stagnant...... for decades, while applications and physical links have evolved. This article advocates for the use of SDN to bring about 5G network services by incorporating network coding (NC) functionalities. The latter constitutes a major leap forward compared to the state-of-the- art store and forward Internet paradigm...

  16. Network Coded Software Defined Networking

    DEFF Research Database (Denmark)

    Krigslund, Jeppe; Hansen, Jonas; Roetter, Daniel Enrique Lucani

    2015-01-01

    Software Defined Networking (SDN) and Network Coding (NC) are two key concepts in networking that have garnered a large attention in recent years. On the one hand, SDN's potential to virtualize services in the Internet allows a large flexibility not only for routing data, but also to manage....... This paper advocates for the use of SDN to bring about future Internet and 5G network services by incorporating network coding (NC) functionalities. The inherent flexibility of both SDN and NC provides a fertile ground to envision more efficient, robust, and secure networking designs, that may also...... incorporate content caching and storage, all of which are key challenges of the future Internet and the upcoming 5G networks. This paper proposes some of the keys behind this intersection and supports it with use cases as well as a an implementation that integrated the Kodo library (NC) into OpenFlow (SDN...

  17. Deep architecture neural network-based real-time image processing for image-guided radiotherapy.

    Science.gov (United States)

    Mori, Shinichiro

    2017-08-01

    To develop real-time image processing for image-guided radiotherapy, we evaluated several neural network models for use with different imaging modalities, including X-ray fluoroscopic image denoising. Setup images of prostate cancer patients were acquired with two oblique X-ray fluoroscopic units. Two types of residual network were designed: a convolutional autoencoder (rCAE) and a convolutional neural network (rCNN). We changed the convolutional kernel size and number of convolutional layers for both networks, and the number of pooling and upsampling layers for rCAE. The ground-truth image was applied to the contrast-limited adaptive histogram equalization (CLAHE) method of image processing. Network models were trained to keep the quality of the output image close to that of the ground-truth image from the input image without image processing. For image denoising evaluation, noisy input images were used for the training. More than 6 convolutional layers with convolutional kernels >5×5 improved image quality. However, this did not allow real-time imaging. After applying a pair of pooling and upsampling layers to both networks, rCAEs with >3 convolutions each and rCNNs with >12 convolutions with a pair of pooling and upsampling layers achieved real-time processing at 30 frames per second (fps) with acceptable image quality. Use of our suggested network achieved real-time image processing for contrast enhancement and image denoising by the use of a conventional modern personal computer. Copyright © 2017 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.

  18. Telecommunication Networks

    DEFF Research Database (Denmark)

    Olsen, Rasmus Løvenstein; Balachandran, Kartheepan; Hald, Sara Ligaard

    2014-01-01

    In this chapter, we look into the role of telecommunication networks and their capability of supporting critical infrastructure systems and applications. The focus is on smart grids as the key driving example, bearing in mind that other such systems do exist, e.g., water management, traffic control......, etc. First, the role of basic communication is examined with a focus on critical infrastructures. We look at heterogenic networks and standards for smart grids, to give some insight into what has been done to ensure inter-operability in this direction. We then go to the physical network, and look...... at the deployment of the physical layout of the communication network and the related costs. This is an important aspect as one option to use existing networks is to deploy dedicated networks. Following this, we look at some generic models that describe reliability for accessing dynamic information. This part...

  19. Networked Identities

    DEFF Research Database (Denmark)

    Ryberg, Thomas; Larsen, Malene Charlotte

    2008-01-01

    In this article we take up a critique of the concept of Communities of Practice (CoP) voiced by several authors, who suggest that networks may provide a better metaphor to understand social forms of organisation and learning. Through a discussion of the notion of networked learning and the critique...... of CoPs we shall argue that the metaphor or theory of networked learning is itself confronted with some central tensions and challenges that need to be addressed. We then explore these theoretical and analytic challenges to the network metaphor, through an analysis of a Danish social networking site. We...... argue that understanding meaning-making and ‘networked identities’ may be relevant analytic entry points in navigating the challenges....

  20. REAL-TIME VIDEO SCALING BASED ON CONVOLUTION NEURAL NETWORK ARCHITECTURE

    Directory of Open Access Journals (Sweden)

    S Safinaz

    2017-08-01

    Full Text Available In recent years, video super resolution techniques becomes mandatory requirements to get high resolution videos. Many super resolution techniques researched but still video super resolution or scaling is a vital challenge. In this paper, we have presented a real-time video scaling based on convolution neural network architecture to eliminate the blurriness in the images and video frames and to provide better reconstruction quality while scaling of large datasets from lower resolution frames to high resolution frames. We compare our outcomes with multiple exiting algorithms. Our extensive results of proposed technique RemCNN (Reconstruction error minimization Convolution Neural Network shows that our model outperforms the existing technologies such as bicubic, bilinear, MCResNet and provide better reconstructed motioning images and video frames. The experimental results shows that our average PSNR result is 47.80474 considering upscale-2, 41.70209 for upscale-3 and 36.24503 for upscale-4 for Myanmar dataset which is very high in contrast to other existing techniques. This results proves our proposed model real-time video scaling based on convolution neural network architecture’s high efficiency and better performance.

  1. Accurate segmentation of lung fields on chest radiographs using deep convolutional networks

    Science.gov (United States)

    Arbabshirani, Mohammad R.; Dallal, Ahmed H.; Agarwal, Chirag; Patel, Aalpan; Moore, Gregory

    2017-02-01

    Accurate segmentation of lung fields on chest radiographs is the primary step for computer-aided detection of various conditions such as lung cancer and tuberculosis. The size, shape and texture of lung fields are key parameters for chest X-ray (CXR) based lung disease diagnosis in which the lung field segmentation is a significant primary step. Although many methods have been proposed for this problem, lung field segmentation remains as a challenge. In recent years, deep learning has shown state of the art performance in many visual tasks such as object detection, image classification and semantic image segmentation. In this study, we propose a deep convolutional neural network (CNN) framework for segmentation of lung fields. The algorithm was developed and tested on 167 clinical posterior-anterior (PA) CXR images collected retrospectively from picture archiving and communication system (PACS) of Geisinger Health System. The proposed multi-scale network is composed of five convolutional and two fully connected layers. The framework achieved IOU (intersection over union) of 0.96 on the testing dataset as compared to manual segmentation. The suggested framework outperforms state of the art registration-based segmentation by a significant margin. To our knowledge, this is the first deep learning based study of lung field segmentation on CXR images developed on a heterogeneous clinical dataset. The results suggest that convolutional neural networks could be employed reliably for lung field segmentation.

  2. Local Tiled Deep Networks for Recognition of Vehicle Make and Model

    Science.gov (United States)

    Gao, Yongbin; Lee, Hyo Jong

    2016-01-01

    Vehicle analysis involves license-plate recognition (LPR), vehicle-type classification (VTC), and vehicle make and model recognition (MMR). Among these tasks, MMR plays an important complementary role in respect to LPR. In this paper, we propose a novel framework for MMR using local tiled deep networks. The frontal views of vehicle images are first extracted and fed into the local tiled deep networks for training and testing. A local tiled convolutional neural network (LTCNN) is proposed to alter the weight sharing scheme of CNN with local tiled structure. The LTCNN unties the weights of adjacent units and then ties the units k steps from each other within a local map. This architecture provides the translational, rotational, and scale invariance as well as locality. In addition, to further deal with the colour and illumination variation, we applied the histogram oriented gradient (HOG) to the frontal view of images prior to the LTCNN. The experimental results show that our LTCNN framework achieved a 98% accuracy rate in terms of vehicle MMR. PMID:26875983

  3. Local Tiled Deep Networks for Recognition of Vehicle Make and Model

    Directory of Open Access Journals (Sweden)

    Yongbin Gao

    2016-02-01

    Full Text Available Vehicle analysis involves license-plate recognition (LPR, vehicle-type classification (VTC, and vehicle make and model recognition (MMR. Among these tasks, MMR plays an important complementary role in respect to LPR. In this paper, we propose a novel framework for MMR using local tiled deep networks. The frontal views of vehicle images are first extracted and fed into the local tiled deep networks for training and testing. A local tiled convolutional neural network (LTCNN is proposed to alter the weight sharing scheme of CNN with local tiled structure. The LTCNN unties the weights of adjacent units and then ties the units k steps from each other within a local map. This architecture provides the translational, rotational, and scale invariance as well as locality. In addition, to further deal with the colour and illumination variation, we applied the histogram oriented gradient (HOG to the frontal view of images prior to the LTCNN. The experimental results show that our LTCNN framework achieved a 98% accuracy rate in terms of vehicle MMR.

  4. Wireless Networks

    OpenAIRE

    Samaka, Mohammed; Khan, Khaled M.D.

    2007-01-01

    Wireless communication is the fastest-growing field in the telecommunication industry. Wireless networks have grown significantly as an important segment of the communications industry. They have become popular networks with the potential to provide high-speed, high-quality information exchange between two or more portable devices without any wire or conductors. Wireless networks can simply be characterized as the technology that provides seamless access to information, anywhere, anyplace, an...

  5. Enterpreneurial network

    OpenAIRE

    Thoma, Antonela; Nguyen, Lien; Kupsyte, Valdone

    2014-01-01

    Network has become more and more indispensable in the entrepreneurial world. Especially in startup businesses, network is crucial for new entrepreneurs. This project looks at how entrepreneurs in different sectors use network to become successful. We chose to work with three entrepreneurs from three companies that have been operational for a few years and conducted face to face interviews with them. Through the data from the interviews, we analyzed firstly what type of entrepreneurs they are,...

  6. Network security

    CERN Document Server

    Perez, André

    2014-01-01

    This book introduces the security mechanisms deployed in Ethernet, Wireless-Fidelity (Wi-Fi), Internet Protocol (IP) and MultiProtocol Label Switching (MPLS) networks. These mechanisms are grouped throughout the book according to the following four functions: data protection, access control, network isolation, and data monitoring. Data protection is supplied by data confidentiality and integrity control services. Access control is provided by a third-party authentication service. Network isolation is supplied by the Virtual Private Network (VPN) service. Data monitoring consists of applying

  7. Networking Japan

    DEFF Research Database (Denmark)

    Hansen, Annette Skovsted

    HIDA). Many of these alumni have and will in the future exchange ideas and keep contact not only to Japan, but also to fellow alumni around the globe and, thereby, practice south-south exchanges, which are made possible and traceable by their established alumni network and the World Network of Friends...... (WNF). Through the alumni network, Japan continues to infuse ideas to participants and alumni, who interpret and disseminate these ideas through alumni society networks and activities, but their discussions nationally and regionally also get reported back to Japan and affect future policies...

  8. Technical Network

    CERN Multimedia

    2007-01-01

    In order to optimize the management of the Technical Network (TN), to ease the understanding and purpose of devices connected to the TN, and to improve security incident handling, the Technical Network Administrators and the CNIC WG have asked IT/CS to verify the "description" and "tag" fields of devices connected to the TN. Therefore, persons responsible for systems connected to the TN will receive email notifications from IT/CS asking them to add the corresponding information in the network database. Thank you very much for your cooperation. The Technical Network Administrators & the CNIC WG

  9. Overlay networks toward information networking

    CERN Document Server

    Tarkoma, Sasu

    2010-01-01

    With their ability to solve problems in massive information distribution and processing, while keeping scaling costs low, overlay systems represent a rapidly growing area of R&D with important implications for the evolution of Internet architecture. Inspired by the author's articles on content based routing, Overlay Networks: Toward Information Networking provides a complete introduction to overlay networks. Examining what they are and what kind of structures they require, the text covers the key structures, protocols, and algorithms used in overlay networks. It reviews the current state of th

  10. Heterodox networks

    DEFF Research Database (Denmark)

    Lala, Purnima; Kumar, Ambuj

    2016-01-01

    It is imperative for the service providers to bring innovation in the network design to meet the exponential growth of mobile subscribers for multi-technology future wireless networks. As a matter of research, studies on providing services to moving subscriber groups aka ‘Place Time Capacity (PTC...

  11. Sensor networks

    NARCIS (Netherlands)

    Chatterjea, Supriyo; Thurston, J.; Kininmonth, S.; Havinga, Paul J.M.

    2006-01-01

    This article describes the details of a sensor network that is currently being deployed at the Great Barrier Reef in Australia. The sensor network allows scientists to retrieve sensor data that has a high spatial and temporal resolution. We give an overview of the energy-efficient data aggregation

  12. Network Protocols

    NARCIS (Netherlands)

    Tanenbaum, A.S.

    1981-01-01

    Dunng the last ten years, many computer networks have been designed, implemented, and put into service in the United States, Canada, Europe, Japan, and elsewhere. From the experience obtamed with these networks, certain key design principles have begun to emerge, principles that can be used to

  13. Probabilistic Networks

    DEFF Research Database (Denmark)

    Jensen, Finn Verner; Lauritzen, Steffen Lilholt

    2001-01-01

    This article describes the basic ideas and algorithms behind specification and inference in probabilistic networks based on directed acyclic graphs, undirected graphs, and chain graphs.......This article describes the basic ideas and algorithms behind specification and inference in probabilistic networks based on directed acyclic graphs, undirected graphs, and chain graphs....

  14. Organizational Networks

    DEFF Research Database (Denmark)

    Sørensen, Ole Henning; Grande, Bård

    1996-01-01

    The paper focuses on the concept of organizational networks. Four different uses of the concept are identified and critically discussed.......The paper focuses on the concept of organizational networks. Four different uses of the concept are identified and critically discussed....

  15. Affective Networks

    OpenAIRE

    Jodi Dean

    2010-01-01

    This article sets out the idea of affective networks as a constitutive feature of communicative capitalism. It explores the circulation of intensities in contemporary information and communication networks, arguing that this circulation should be theorized in terms of the psychoanalytic notion of the drive. The article includes critical engagements with theorists such as Guy Debord, Jacques Lacan, Tiziana Terranova, and Slavoj Zizek.

  16. Network chemistry, network toxicology, network informatics, and network behavioristics: A scientific outline

    OpenAIRE

    WenJun Zhang

    2016-01-01

    In present study, I proposed some new sciences: network chemistry, network toxicology, network informatics, and network behavioristics. The aims, scope and scientific foundation of these sciences are outlined.

  17. Network Affordances

    DEFF Research Database (Denmark)

    Samson, Audrey; Soon, Winnie

    2015-01-01

    This paper examines the notion of network affordance within the context of network art. Building on Gibson's theory (Gibson, 1979) we understand affordance as the perceived and actual parameters of a thing. We expand on Gaver's affordance of predictability (Gaver, 1996) to include ecological...... and computational parameters of unpredictability. We illustrate the notion of unpredictability by considering four specific works that were included in a network art exhibiton, SPEED SHOW [2.0] Hong Kong. The paper discusses how the artworks are contingent upon the parameteric relations (Parisi, 2013......), of the network. We introduce network affordance as a dynamic framework that could articulate the experienced tension arising from the (visible) symbolic representation of computational processes and its hidden occurrences. We base our proposal on the experience of both organising the SPEED SHOW and participating...

  18. Deep learning in breast cancer risk assessment: evaluation of convolutional neural networks on a clinical dataset of full-field digital mammograms.

    Science.gov (United States)

    Li, Hui; Giger, Maryellen L; Huynh, Benjamin Q; Antropova, Natalia O

    2017-10-01

    To evaluate deep learning in the assessment of breast cancer risk in which convolutional neural networks (CNNs) with transfer learning are used to extract parenchymal characteristics directly from full-field digital mammographic (FFDM) images instead of using computerized radiographic texture analysis (RTA), 456 clinical FFDM cases were included: a "high-risk" BRCA1/2 gene-mutation carriers dataset (53 cases), a "high-risk" unilateral cancer patients dataset (75 cases), and a "low-risk dataset" (328 cases). Deep learning was compared to the use of features from RTA, as well as to a combination of both in the task of distinguishing between high- and low-risk subjects. Similar classification performances were obtained using CNN [area under the curve [Formula: see text]; standard error [Formula: see text

  19. Auto-context Convolutional Neural Network (Auto-Net) for Brain Extraction in Magnetic Resonance Imaging.

    Science.gov (United States)

    Salehi, Seyed Sadegh Mohseni; Erdogmus, Deniz; Gholipour, Ali

    2017-06-28

    Brain extraction or whole brain segmentation is an important first step in many of the neuroimage analysis pipelines. The accuracy and robustness of brain extraction, therefore, is crucial for the accuracy of the entire brain analysis process. State-of-the-art brain extraction techniques rely heavily on the accuracy of alignment or registration between brain atlases and query brain anatomy, and/or make assumptions about the image geometry; therefore have limited success when these assumptions do not hold or image registration fails. With the aim of designing an accurate, learning-based, geometry-independent and registration-free brain extraction tool in this study, we present a technique based on an auto-context convolutional neural network (CNN), in which intrinsic local and global image features are learned through 2D patches of different window sizes. We consider two different architectures: 1) a voxelwise approach based on three parallel 2D convolutional pathways for three different directions (axial, coronal, and sagittal) that implicitly learn 3D image information without the need for computationally expensive 3D convolutions, and 2) a fully convolutional network based on the U-net architecture. Posterior probability maps generated by the networks are used iteratively as context information along with the original image patches to learn the local shape and connectedness of the brain to extract it from non-brain tissue. The brain extraction results we have obtained from our CNNs are superior to the recently reported results in the literature on two publicly available benchmark datasets, namely LPBA40 and OASIS, in which we obtained Dice overlap coefficients of 97.73% and 97.62%, respectively. Significant improvement was achieved via our auto-context algorithm. Furthermore, we evaluated the performance of our algorithm in the challenging problem of extracting arbitrarily-oriented fetal brains in reconstructed fetal brain magnetic resonance imaging (MRI

  20. Automated segmentation of 3D anatomical structures on CT images by using a deep convolutional network based on end-to-end learning approach

    Science.gov (United States)

    Zhou, Xiangrong; Takayama, Ryosuke; Wang, Song; Zhou, Xinxin; Hara, Takeshi; Fujita, Hiroshi

    2017-02-01

    We have proposed an end-to-end learning approach that trained a deep convolutional neural network (CNN) for automatic CT image segmentation, which accomplished a voxel-wised multiple classification to directly map each voxel on 3D CT images to an anatomical label automatically. The novelties of our proposed method were (1) transforming the anatomical structures segmentation on 3D CT images into a majority voting of the results of 2D semantic image segmentation on a number of 2D-slices from different image orientations, and (2) using "convolution" and "deconvolution" networks to achieve the conventional "coarse recognition" and "fine extraction" functions which were integrated into a compact all-in-one deep CNN for CT image segmentation. The advantage comparing to previous works was its capability to accomplish real-time image segmentations on 2D slices of arbitrary CT-scan-range (e.g. body, chest, abdomen) and produced correspondingly-sized output. In this paper, we propose an improvement of our proposed approach by adding an organ localization module to limit CT image range for training and testing deep CNNs. A database consisting of 240 3D CT scans and a human annotated ground truth was used for training (228 cases) and testing (the remaining 12 cases). We applied the improved method to segment pancreas and left kidney regions, respectively. The preliminary results showed that the accuracies of the segmentation results were improved significantly (pancreas was 34% and kidney was 8% increased in Jaccard index from our previous results). The effectiveness and usefulness of proposed improvement for CT image segmentations were confirmed.

  1. Social networks

    CERN Document Server

    Etaner-Uyar, A Sima

    2014-01-01

    The present volume provides a comprehensive resource for practitioners and researchers alike-both those new to the field as well as those who already have some experience. The work covers Social Network Analysis theory and methods with a focus on current applications and case studies applied in various domains such as mobile networks, security, machine learning and health. With the increasing popularity of Web 2.0, social media has become a widely used communication platform. Parallel to this development, Social Network Analysis gained in importance as a research field, while opening up many

  2. Network Warrior

    CERN Document Server

    Donahue, Gary

    2011-01-01

    Pick up where certification exams leave off. With this practical, in-depth guide to the entire network infrastructure, you'll learn how to deal with real Cisco networks, rather than the hypothetical situations presented on exams like the CCNA. Network Warrior takes you step by step through the world of routers, switches, firewalls, and other technologies based on the author's extensive field experience. You'll find new content for MPLS, IPv6, VoIP, and wireless in this completely revised second edition, along with examples of Cisco Nexus 5000 and 7000 switches throughout. Topics include: An

  3. Stepwise association of hydrogen cyanide and acetonitrile with the benzene radical cation: structures and binding energies of (C6H6•+)(HCN)n, n = 1-6, and (C6H6•+)(CH3CN)n, n = 1-4, clusters.

    Science.gov (United States)

    Hamid, Ahmed M; Soliman, Abdel-Rahman; El-Shall, M Samy

    2013-02-14

    Equilibrium thermochemical measurements using the ion mobility drift cell technique have been utilized to investigate the binding energies and entropy changes associated with the stepwise association of HCN and CH(3)CN molecules with the benzene radical cation in the C(6)H(6)(•+)(HCN)(n) and C(6)H(6)(•+)(CH(3)CN)(n) clusters with n = 1-6 and 1-4, respectively. The binding energy of CH(3)CN to the benzene cation (14 kcal/mol) is stronger than that of HCN (9 kcal/mol) mostly due to a stronger ion-dipole interaction because of the large dipole moment of acetonitrile (3.9 D). However, HCN can form hydrogen bonds with the hydrogen atoms of the benzene cation (CH(δ+)···NCH) and linear hydrogen bonding chains involving HCN···HCN interaction. HCN molecules tend to form externally solvated structures with the benzene cation where the ion is hydrogen bonded to the exterior of HCN chains. For the C(6)H(6)(•+)(CH(3)CN)(n) clusters, internally solvated structures are formed where the acetonitrile molecules are directly interacting with the benzene cation through ion-dipole and hydrogen bonding interactions. The lack of formation of higher clusters with n > 4, in contrast to HCN, suggests the formation of a solvent shell at n = 4, which is attributed to steric interactions among the acetonitrile molecules attached to the benzene cation and to the presence of the blocking CH(3) groups, both effects make the addition of more than four acetonitrile molecules less favorable.

  4. Classifying Radio Galaxies with the Convolutional Neural Network

    Science.gov (United States)

    Aniyan, A. K.; Thorat, K.

    2017-06-01

    We present the application of a deep machine learning technique to classify radio images of extended sources on a morphological basis using convolutional neural networks (CNN). In this study, we have taken the case of the Fanaroff-Riley (FR) class of radio galaxies as well as radio galaxies with bent-tailed morphology. We have used archival data from the Very Large Array (VLA)—Faint Images of the Radio Sky at Twenty Centimeters survey and existing visually classified samples available in the literature to train a neural network for morphological classification of these categories of radio sources. Our training sample size for each of these categories is ˜200 sources, which has been augmented by rotated versions of the same. Our study shows that CNNs can classify images of the FRI and FRII and bent-tailed radio galaxies with high accuracy (maximum precision at 95%) using well-defined samples and a “fusion classifier,” which combines the results of binary classifications, while allowing for a mechanism to find sources with unusual morphologies. The individual precision is highest for bent-tailed radio galaxies at 95% and is 91% and 75% for the FRI and FRII classes, respectively, whereas the recall is highest for FRI and FRIIs at 91% each, while the bent-tailed class has a recall of 79%. These results show that our results are comparable to that of manual classification, while being much faster. Finally, we discuss the computational and data-related challenges associated with the morphological classification of radio galaxies with CNNs.

  5. Discriminating solitary cysts from soft tissue lesions in mammography using a pretrained deep convolutional neural network.

    Science.gov (United States)

    Kooi, Thijs; van Ginneken, Bram; Karssemeijer, Nico; den Heeten, Ard

    2017-03-01

    It is estimated that 7% of women in the western world will develop palpable breast cysts in their lifetime. Even though cysts have been correlated with risk of developing breast cancer, many of them are benign and do not require follow-up. We develop a method to discriminate benign solitary cysts from malignant masses in digital mammography. We think a system like this can have merit in the clinic as a decision aid or complementary to specialized modalities. We employ a deep convolutional neural network (CNN) to classify cyst and mass patches. Deep CNNs have been shown to be powerful classifiers, but need a large amount of training data for which medical problems are often difficult to come by. The key contribution of this paper is that we show good performance can be obtained on a small dataset by pretraining the network on a large dataset of a related task. We subsequently investigate the following: (a) when a mammographic exam is performed, two different views of the same breast are recorded. We investigate the merit of combining the output of the classifier from these two views. (b) We evaluate the importance of the resolution of the patches fed to the network. (c) A method dubbed tissue augmentation is subsequently employed, where we extract normal tissue from normal patches and superimpose this onto the actual samples aiming for a classifier invariant to occluding tissue. (d) We combine the representation extracted using the deep CNN with our previously developed features. We show that using the proposed deep learning method, an area under the ROC curve (AUC) value of 0.80 can be obtained on a set of benign solitary cysts and malignant mass findings recalled in screening. We find that it works significantly better than our previously developed approach by comparing the AUC of the ROC using bootstrapping. By combining views, the results can be further improved, though this difference was not found to be significant. We find no significant difference between

  6. Managing Networks

    DEFF Research Database (Denmark)

    Jørgensen, Heidi; Vintergaard, Christian

    Logically it seems that companies pursuing different business strategies wouldalso manage their relationships with other firms accordingly. Nevertheless, due tothe lack of research in the field of network strategies, this link still remainsinadequately examined. Based on the well-known framework...... isprovided, that the relation between a company's strategy, structure and processesin fact have a considerable influence on its pattern of network behaviour. Threecase studies from the Danish biotech industry exemplify and illustrate how acompany's strategy is directly correlated with how it manages its...... of organisationalbehaviour developed by Miles and Snow (1978), this paper argues that thepatterns of network behaviour practiced by firms greatly depend on the businesstypology of the company. That is, a company's business typology will to a certaindegree dictate the network identity of the company. In this paper evidence...

  7. Heterodox networks

    DEFF Research Database (Denmark)

    Lala, Purnima; Kumar, Ambuj

    2016-01-01

    architecture of ‘Hovering Ad-hoc Network (HANET)’ for the latter will be deployed to assist and manage the overloaded primary base stations enhancing the on-demand coverage and capacity of the entire system. Proposed modes can either operate independently or as a cascaded architecture to form a Heterodox......It is imperative for the service providers to bring innovation in the network design to meet the exponential growth of mobile subscribers for multi-technology future wireless networks. As a matter of research, studies on providing services to moving subscriber groups aka ‘Place Time Capacity (PTC......)’ have not been considered much in the literature. In this article we present Heterodox networks as an innovative and alternate approach to handle the PTC congestion. We describe two different approaches to combat the PTC congestion where the traditional terrestrial infrastructure fails to provide...

  8. Exchange Network

    Science.gov (United States)

    The Environmental Information Exchange Network (EIEN) is an Internet-based system used by state, tribal and territorial partners to securely share environmental and health information with one another and EPA.

  9. Sentinel Network

    Science.gov (United States)

    The Sentinel Network is an integrated, electronic, national medical product safety initiative that compiles information about the safe and effective use of medical products accessible to patients and healthcare practitioners.

  10. computer networks

    Directory of Open Access Journals (Sweden)

    N. U. Ahmed

    2002-01-01

    Full Text Available In this paper, we construct a new dynamic model for the Token Bucket (TB algorithm used in computer networks and use systems approach for its analysis. This model is then augmented by adding a dynamic model for a multiplexor at an access node where the TB exercises a policing function. In the model, traffic policing, multiplexing and network utilization are formally defined. Based on the model, we study such issues as (quality of service QoS, traffic sizing and network dimensioning. Also we propose an algorithm using feedback control to improve QoS and network utilization. Applying MPEG video traces as the input traffic to the model, we verify the usefulness and effectiveness of our model.

  11. Affective Networks

    Directory of Open Access Journals (Sweden)

    Jodi Dean

    2010-02-01

    Full Text Available This article sets out the idea of affective networks as a constitutive feature of communicative capitalism. It explores the circulation of intensities in contemporary information and communication networks, arguing that this circulation should be theorized in terms of the psychoanalytic notion of the drive. The article includes critical engagements with theorists such as Guy Debord, Jacques Lacan, Tiziana Terranova, and Slavoj Zizek.

  12. Friendship Networks

    OpenAIRE

    Jan K. Brueckner

    2004-01-01

    Building upon a long tradition in sociology, economists have recently turned their attention to the analysis of social networks. The present paper adds to this emerging literature by proposing a different approach to social-network formation. As in the model of Jackson and Wolinsky (1996), formation of a link between two individuals requires two-sided investments in the present framework. But in contrast to their approach, where the required investments are exogenously specified and link form...

  13. Developer Network

    Energy Technology Data Exchange (ETDEWEB)

    2012-08-21

    NREL's Developer Network, developer.nrel.gov, provides data that users can access to provide data to their own analyses, mobile and web applications. Developers can retrieve the data through a Web services API (application programming interface). The Developer Network handles overhead of serving up web services such as key management, authentication, analytics, reporting, documentation standards, and throttling in a common architecture, while allowing web services and APIs to be maintained and managed independently.

  14. Network Power Fault Detection

    OpenAIRE

    Siviero, Claudio

    2013-01-01

    Network power fault detection. At least one first network device is instructed to temporarily disconnect from a power supply path of a network, and at least one characteristic of the power supply path of the network is measured at a second network device connected to the network while the at least one first network device is temporarily disconnected from the network

  15. Complex Networks

    CERN Document Server

    Evsukoff, Alexandre; González, Marta

    2013-01-01

    In the last decade we have seen the emergence of a new inter-disciplinary field focusing on the understanding of networks which are dynamic, large, open, and have a structure sometimes called random-biased. The field of Complex Networks is helping us better understand many complex phenomena such as the spread of  deseases, protein interactions, social relationships, to name but a few. Studies in Complex Networks are gaining attention due to some major scientific breakthroughs proposed by network scientists helping us understand and model interactions contained in large datasets. In fact, if we could point to one event leading to the widespread use of complex network analysis is the availability of online databases. Theories of Random Graphs from Erdös and Rényi from the late 1950s led us to believe that most networks had random characteristics. The work on large online datasets told us otherwise. Starting with the work of Barabási and Albert as well as Watts and Strogatz in the late 1990s, we now know th...

  16. Sentient networks

    Energy Technology Data Exchange (ETDEWEB)

    Chapline, G.

    1998-03-01

    The engineering problems of constructing autonomous networks of sensors and data processors that can provide alerts for dangerous situations provide a new context for debating the question whether man-made systems can emulate the cognitive capabilities of the mammalian brain. In this paper we consider the question whether a distributed network of sensors and data processors can form ``perceptions`` based on sensory data. Because sensory data can have exponentially many explanations, the use of a central data processor to analyze the outputs from a large ensemble of sensors will in general introduce unacceptable latencies for responding to dangerous situations. A better idea is to use a distributed ``Helmholtz machine`` architecture in which the sensors are connected to a network of simple processors, and the collective state of the network as a whole provides an explanation for the sensory data. In general communication within such a network will require time division multiplexing, which opens the door to the possibility that with certain refinements to the Helmholtz machine architecture it may be possible to build sensor networks that exhibit a form of artificial consciousness.

  17. Cellular Nonlinear Networks for the emergence of perceptual states: application to robot navigation control.

    Science.gov (United States)

    Arena, Paolo; De Fiore, Sebastiano; Patané, Luca

    2009-01-01

    In this paper a new general purpose perceptual control architecture, based on nonlinear neural lattices, is presented and applied to solve robot navigation tasks. Insects show the ability to react to certain stimuli with simple reflexes, using direct sensory-motor pathways, which can be considered as basic behaviors, inherited and pre-wired. Relevant brain centres, known as Mushroom Bodies (MB) and Central Complex (CX) were recently identified in insects: though their functional details are not yet fully understood, it is known that they provide secondary pathways allowing the emergence of cognitive behaviors. These are gained through the coordination of the basic abilities to satisfy the insect's needs. Taking inspiration from this evidence, our architecture modulates, through a reinforcement learning, a set of competitive and concurrent basic behaviors in order to accomplish the task assigned through a reward function. The core of the architecture is constituted by the so-called Representation layer, used to create a concise picture of the current environment situation, fusing together different stimuli for the emergence of perceptual states. These perceptual states are steady state solutions of lattices of Reaction-Diffusion Cellular Nonlinear Networks (RD-CNN), designed to show Turing patterns. The exploitation of the dynamics of the multiple equilibria of the network is emphasized through the adaptive shaping of the basins of attraction for each emerged pattern. New experimental campaigns on standard robotic platforms are reported to demonstrate the potentiality and the effectiveness of the approach.

  18. Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks

    Directory of Open Access Journals (Sweden)

    Liang Chen

    2017-01-01

    Full Text Available Stroke is an acute cerebral vascular disease, which is likely to cause long-term disabilities and death. Acute ischemic lesions occur in most stroke patients. These lesions are treatable under accurate diagnosis and treatments. Although diffusion-weighted MR imaging (DWI is sensitive to these lesions, localizing and quantifying them manually is costly and challenging for clinicians. In this paper, we propose a novel framework to automatically segment stroke lesions in DWI. Our framework consists of two convolutional neural networks (CNNs: one is an ensemble of two DeconvNets (Noh et al., 2015, which is the EDD Net; the second CNN is the multi-scale convolutional label evaluation net (MUSCLE Net, which aims to evaluate the lesions detected by the EDD Net in order to remove potential false positives. To the best of our knowledge, it is the first attempt to solve this problem and using both CNNs achieves very good results. Furthermore, we study the network architectures and key configurations in detail to ensure the best performance. It is validated on a large dataset comprising clinical acquired DW images from 741 subjects. A mean accuracy of Dice coefficient obtained is 0.67 in total. The mean Dice scores based on subjects with only small and large lesions are 0.61 and 0.83, respectively. The lesion detection rate achieved is 0.94.

  19. Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification

    Directory of Open Access Journals (Sweden)

    Srdjan Sladojevic

    2016-01-01

    Full Text Available The latest generation of convolutional neural networks (CNNs has achieved impressive results in the field of image classification. This paper is concerned with a new approach to the development of plant disease recognition model, based on leaf image classification, by the use of deep convolutional networks. Novel way of training and the methodology used facilitate a quick and easy system implementation in practice. The developed model is able to recognize 13 different types of plant diseases out of healthy leaves, with the ability to distinguish plant leaves from their surroundings. According to our knowledge, this method for plant disease recognition has been proposed for the first time. All essential steps required for implementing this disease recognition model are fully described throughout the paper, starting from gathering images in order to create a database, assessed by agricultural experts. Caffe, a deep learning framework developed by Berkley Vision and Learning Centre, was used to perform the deep CNN training. The experimental results on the developed model achieved precision between 91% and 98%, for separate class tests, on average 96.3%.

  20. Pelvic artery calcification detection on CT scans using convolutional neural networks

    Science.gov (United States)

    Liu, Jiamin; Lu, Le; Yao, Jianhua; Bagheri, Mohammadhadi; Summers, Ronald M.

    2017-03-01

    Artery calcification is observed commonly in elderly patients, especially in patients with chronic kidney disease, and may affect coronary, carotid and peripheral arteries. Vascular calcification has been associated with many clinical outcomes. Manual identification of calcification in CT scans requires substantial expert interaction, which makes it time-consuming and infeasible for large-scale studies. Many works have been proposed for coronary artery calcification detection in cardiac CT scans. In these works, coronary artery extraction is commonly required for calcification detection. However, there are few works about abdominal or pelvic artery calcification detection. In this work, we present a method for automatic pelvic artery calcification detection on CT scan. This method uses the recent advanced faster region-based convolutional neural network (R-CNN) to directly identify artery calcification without a need for artery extraction since pelvic artery extraction itself is challenging. Our method first generates category-independent region proposals for each slice of the input CT scan using region proposal networks (RPN). Then, each region proposal is jointly classified and refined by softmax classifier and bounding box regressor. We applied the detection method to 500 images from 20 CT scans of patients for evaluation. The detection system achieved a 77.4% average precision and a 85% sensitivity at 1 false positive per image.