Understanding Intra-Class Knowledge Inside CNN

OpenAIRE

Wei, Donglai; Zhou, Bolei; Torrabla, Antonio; Freeman, William

2015-01-01

Convolutional Neural Network (CNN) has been successful in image recognition tasks, and recent works shed lights on how CNN separates different classes with the learned inter-class knowledge through visualization. In this work, we instead visualize the intra-class knowledge inside CNN to better understand how an object class is represented in the fully-connected layers. To invert the intra-class knowledge into more interpretable images, we propose a non-parametric patch prior upon previous CNN...

Real-time emulation of neural images in the outer retinal circuit.

Science.gov (United States)

Hasegawa, Jun; Yagi, Tetsuya

2008-12-01

We describe a novel real-time system that emulates the architecture and functionality of the vertebrate retina. This system reconstructs the neural images formed by the retinal neurons in real time by using a combination of analog and digital systems consisting of a neuromorphic silicon retina chip, a field-programmable gate array, and a digital computer. While the silicon retina carries out the spatial filtering of input images instantaneously, using the embedded resistive networks that emulate the receptive field structure of the outer retinal neurons, the digital computer carries out the temporal filtering of the spatially filtered images to emulate the dynamical properties of the outer retinal circuits. The emulations of the neural image, including 128 x 128 bipolar cells, are carried out at a frame rate of 62.5 Hz. The emulation of the response to the Hermann grid and a spot of light and an annulus of lights has demonstrated that the system responds as expected by previous physiological and psychophysical observations. Furthermore, the emulated dynamics of neural images in response to natural scenes revealed the complex nature of retinal neuron activity. We have concluded that the system reflects the spatiotemporal responses of bipolar cells in the vertebrate retina. The proposed emulation system is expected to aid in understanding the visual computation in the retina and the brain.

A Field Programmable Gate Array-Based Reconfigurable Smart-Sensor Network for Wireless Monitoring of New Generation Computer Numerically Controlled Machines

Directory of Open Access Journals (Sweden)

Ion Stiharu

2010-08-01

Full Text Available Computer numerically controlled (CNC machines have evolved to adapt to increasing technological and industrial requirements. To cover these needs, new generation machines have to perform monitoring strategies by incorporating multiple sensors. Since in most of applications the online Processing of the variables is essential, the use of smart sensors is necessary. The contribution of this work is the development of a wireless network platform of reconfigurable smart sensors for CNC machine applications complying with the measurement requirements of new generation CNC machines. Four different smart sensors are put under test in the network and their corresponding signal processing techniques are implemented in a Field Programmable Gate Array (FPGA-based sensor node.

A Field Programmable Gate Array-Based Reconfigurable Smart-Sensor Network for Wireless Monitoring of New Generation Computer Numerically Controlled Machines

Science.gov (United States)

Moreno-Tapia, Sandra Veronica; Vera-Salas, Luis Alberto; Osornio-Rios, Roque Alfredo; Dominguez-Gonzalez, Aurelio; Stiharu, Ion; de Jesus Romero-Troncoso, Rene

2010-01-01

Computer numerically controlled (CNC) machines have evolved to adapt to increasing technological and industrial requirements. To cover these needs, new generation machines have to perform monitoring strategies by incorporating multiple sensors. Since in most of applications the online Processing of the variables is essential, the use of smart sensors is necessary. The contribution of this work is the development of a wireless network platform of reconfigurable smart sensors for CNC machine applications complying with the measurement requirements of new generation CNC machines. Four different smart sensors are put under test in the network and their corresponding signal processing techniques are implemented in a Field Programmable Gate Array (FPGA)-based sensor node. PMID:22163602

Cellular neural networks (CNN) simulation for the TN approximation of the time dependent neutron transport equation in slab geometry

International Nuclear Information System (INIS)

Hadad, Kamal; Pirouzmand, Ahmad; Ayoobian, Navid

2008-01-01

This paper describes the application of a multilayer cellular neural network (CNN) to model and solve the time dependent one-speed neutron transport equation in slab geometry. We use a neutron angular flux in terms of the Chebyshev polynomials (T N ) of the first kind and then we attempt to implement the equations in an equivalent electrical circuit. We apply this equivalent circuit to analyze the T N moments equation in a uniform finite slab using Marshak type vacuum boundary condition. The validity of the CNN results is evaluated with numerical solution of the steady state T N moments equations by MATLAB. Steady state, as well as transient simulations, shows a very good comparison between the two methods. We used our CNN model to simulate space-time response of total flux and its moments for various c (where c is the mean number of secondary neutrons per collision). The complete algorithm could be implemented using very large-scale integrated circuit (VLSI) circuitry. The efficiency of the calculation method makes it useful for neutron transport calculations

Filtering and spectral processing of 1-D signals using cellular neural networks

NARCIS (Netherlands)

Moreira-Tamayo, O.; Pineda de Gyvez, J.

1996-01-01

This paper presents cellular neural networks (CNN) for one-dimensional discrete signal processing. Although CNN has been extensively used in image processing applications, little has been done for 1-dimensional signal processing. We propose a novel CNN architecture to carry out these tasks. This

Gas Sensors Characterization and Multilayer Perceptron (MLP) Hardware Implementation for Gas Identification Using a Field Programmable Gate Array (FPGA)

Science.gov (United States)

Benrekia, Fayçal; Attari, Mokhtar; Bouhedda, Mounir

2013-01-01

This paper develops a primitive gas recognition system for discriminating between industrial gas species. The system under investigation consists of an array of eight micro-hotplate-based SnO2 thin film gas sensors with different selectivity patterns. The output signals are processed through a signal conditioning and analyzing system. These signals feed a decision-making classifier, which is obtained via a Field Programmable Gate Array (FPGA) with Very High-Speed Integrated Circuit Hardware Description Language. The classifier relies on a multilayer neural network based on a back propagation algorithm with one hidden layer of four neurons and eight neurons at the input and five neurons at the output. The neural network designed after implementation consists of twenty thousand gates. The achieved experimental results seem to show the effectiveness of the proposed classifier, which can discriminate between five industrial gases. PMID:23529119

A CNN Based Approach for Garments Texture Design Classification

Directory of Open Access Journals (Sweden)

S.M. Sofiqul Islam

2017-05-01

Full Text Available Identifying garments texture design automatically for recommending the fashion trends is important nowadays because of the rapid growth of online shopping. By learning the properties of images efficiently, a machine can give better accuracy of classification. Several Hand-Engineered feature coding exists for identifying garments design classes. Recently, Deep Convolutional Neural Networks (CNNs have shown better performances for different object recognition. Deep CNN uses multiple levels of representation and abstraction that helps a machine to understand the types of data more accurately. In this paper, a CNN model for identifying garments design classes has been proposed. Experimental results on two different datasets show better results than existing two well-known CNN models (AlexNet and VGGNet and some state-of-the-art Hand-Engineered feature extraction methods.

Cellular neural networks for the stereo matching problem

International Nuclear Information System (INIS)

Taraglio, S.; Zanela, A.

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

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.

CNN-BLPred: a Convolutional neural network based predictor for β-Lactamases (BL) and their classes.

Science.gov (United States)

White, Clarence; Ismail, Hamid D; Saigo, Hiroto; Kc, Dukka B

2017-12-28

The β-Lactamase (BL) enzyme family is an important class of enzymes that plays a key role in bacterial resistance to antibiotics. As the newly identified number of BL enzymes is increasing daily, it is imperative to develop a computational tool to classify the newly identified BL enzymes into one of its classes. There are two types of classification of BL enzymes: Molecular Classification and Functional Classification. Existing computational methods only address Molecular Classification and the performance of these existing methods is unsatisfactory. We addressed the unsatisfactory performance of the existing methods by implementing a Deep Learning approach called Convolutional Neural Network (CNN). We developed CNN-BLPred, an approach for the classification of BL proteins. The CNN-BLPred uses Gradient Boosted Feature Selection (GBFS) in order to select the ideal feature set for each BL classification. Based on the rigorous benchmarking of CCN-BLPred using both leave-one-out cross-validation and independent test sets, CCN-BLPred performed better than the other existing algorithms. Compared with other architectures of CNN, Recurrent Neural Network, and Random Forest, the simple CNN architecture with only one convolutional layer performs the best. After feature extraction, we were able to remove ~95% of the 10,912 features using Gradient Boosted Trees. During 10-fold cross validation, we increased the accuracy of the classic BL predictions by 7%. We also increased the accuracy of Class A, Class B, Class C, and Class D performance by an average of 25.64%. The independent test results followed a similar trend. We implemented a deep learning algorithm known as Convolutional Neural Network (CNN) to develop a classifier for BL classification. Combined with feature selection on an exhaustive feature set and using balancing method such as Random Oversampling (ROS), Random Undersampling (RUS) and Synthetic Minority Oversampling Technique (SMOTE), CNN-BLPred performs

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. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

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.

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.

New Digital Approach to CNN On-chip Implementation for Pattern Recognition

OpenAIRE

Durackova, Daniela

2008-01-01

We developed a novel simulator for the CNN using the program tool Visual Basic for Application. Its algorithm is based on the same principle as the planned designed circuit. The network can process the patterns with 400 point recognition. The created universal simulator can change various simulation parameters. We found that the rounding at multiplication is not as important as we previously expected. On the basis of the simulations we designed a novel digital CNN cell implemented on a chip. ...

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

International Nuclear Information System (INIS)

Taraglio, S.; Zanela, A.

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

Optical Doppler tomography based on a field programmable gate array

DEFF Research Database (Denmark)

Larsen, Henning Engelbrecht; Nilsson, Ronnie Thorup; Thrane, Lars

2008-01-01

We report the design of and results obtained by using a field programmable gate array (FPGA) to digitally process optical Doppler tomography signals. The processor fits into the analog signal path in an existing optical coherence tomography setup. We demonstrate both Doppler frequency and envelope...... extraction using the Hilbert transform, all in a single FPGA. An FPGA implementation has certain advantages over general purpose digital signal processor (DSP) due to the fact that the processing elements operate in parallel as opposed to the DSP. which is primarily a sequential processor....

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.

Region Based CNN for Foreign Object Debris Detection on Airfield Pavement.

Science.gov (United States)

Cao, Xiaoguang; Wang, Peng; Meng, Cai; Bai, Xiangzhi; Gong, Guoping; Liu, Miaoming; Qi, Jun

2018-03-01

In this paper, a novel algorithm based on convolutional neural network (CNN) is proposed to detect foreign object debris (FOD) based on optical imaging sensors. It contains two modules, the improved region proposal network (RPN) and spatial transformer network (STN) based CNN classifier. In the improved RPN, some extra select rules are designed and deployed to generate high quality candidates with fewer numbers. Moreover, the efficiency of CNN detector is significantly improved by introducing STN layer. Compared to faster R-CNN and single shot multiBox detector (SSD), the proposed algorithm achieves better result for FOD detection on airfield pavement in the experiment.

GPU Boosted CNN Simulator Library for Graphical Flow-Based Programmability

Directory of Open Access Journals (Sweden)

Balázs Gergely Soós

2009-01-01

Full Text Available A graphical environment for CNN algorithm development is presented. The new generation of graphical cards with many general purpose processing units introduces the massively parallel computing into PC environment. Universal Machine on Flows- (UMF like notation, highlighting image flows and operations, is a useful tool to describe image processing algorithms. This documentation step can be turned into modeling using our framework backed with MATLAB Simulink and the power of a video card. This latter relatively cheap extension enables a convenient and fast analysis of CNN dynamics and complex algorithms. Comparison with other PC solutions is also presented. For single template execution, our approach yields run times 40x faster than that of the widely used Candy simulator. In the case of simpler algorithms, real-time execution is also possible.

Applications of field-programmable gate arrays in scientific research

CERN Document Server

Sadrozinski, Hartmut F W

2011-01-01

Focusing on resource awareness in field-programmable gate array (FPGA) design, Applications of Field-Programmable Gate Arrays in Scientific Research covers the principle of FPGAs and their functionality. It explores a host of applications, ranging from small one-chip laboratory systems to large-scale applications in ""big science."" The book first describes various FPGA resources, including logic elements, RAM, multipliers, microprocessors, and content-addressable memory. It then presents principles and methods for controlling resources, such as process sequencing, location constraints, and in

Introduction to embedded system design using field programmable gate arrays

CERN Document Server

Dubey, Rahul

2009-01-01

Offers information on the use of field programmable gate arrays (FPGAs) in the design of embedded systems. This text considers a hypothetical robot controller as an embedded application and weaves around it related concepts of FPGA-based digital design. It is suitable for both students and designers who have worked with microprocessors.

DeepSAT's CloudCNN: A Deep Neural Network for Rapid Cloud Detection from Geostationary Satellites

Science.gov (United States)

Kalia, S.; Li, S.; Ganguly, S.; Nemani, R. R.

2017-12-01

Cloud and cloud shadow detection has important applications in weather and climate studies. It is even more crucial when we introduce geostationary satellites into the field of terrestrial remotesensing. With the challenges associated with data acquired in very high frequency (10-15 mins per scan), the ability to derive an accurate cloud/shadow mask from geostationary satellite data iscritical. The key to the success for most of the existing algorithms depends on spatially and temporally varying thresholds, which better capture local atmospheric and surface effects.However, the selection of proper threshold is difficult and may lead to erroneous results. In this work, we propose a deep neural network based approach called CloudCNN to classifycloud/shadow from Himawari-8 AHI and GOES-16 ABI multispectral data. DeepSAT's CloudCNN consists of an encoder-decoder based architecture for binary-class pixel wise segmentation. We train CloudCNN on multi-GPU Nvidia Devbox cluster, and deploy the prediction pipeline on NASA Earth Exchange (NEX) Pleiades supercomputer. We achieved an overall accuracy of 93.29% on test samples. Since, the predictions take only a few seconds to segment a full multi-spectral GOES-16 or Himawari-8 Full Disk image, the developed framework can be used for real-time cloud detection, cyclone detection, or extreme weather event predictions.

New second-order difference algorithm for image segmentation based on cellular neural networks (CNNs)

Science.gov (United States)

Meng, Shukai; Mo, Yu L.

2001-09-01

Image segmentation is one of the most important operations in many image analysis problems, which is the process that subdivides an image into its constituents and extracts those parts of interest. In this paper, we present a new second order difference gray-scale image segmentation algorithm based on cellular neural networks. A 3x3 CNN cloning template is applied, which can make smooth processing and has a good ability to deal with the conflict between the capability of noise resistance and the edge detection of complex shapes. We use second order difference operator to calculate the coefficients of the control template, which are not constant but rather depend on the input gray-scale values. It is similar to Contour Extraction CNN in construction, but there are some different in algorithm. The result of experiment shows that the second order difference CNN has a good capability in edge detection. It is better than Contour Extraction CNN in detail detection and more effective than the Laplacian of Gauss (LOG) algorithm.

Implementation of data acquisition interface using on-board field-programmable gate array (FPGA) universal serial bus (USB) link

International Nuclear Information System (INIS)

Nolida Yussup; Maslina Mohd Ibrahim; Lojius Lombigit; Nur Aira Abdul Rahman; Muhammad Rawi Mohamed Zin

2013-01-01

Full-text: Typically a system consists of hardware as the controller and software which is installed in the personal computer (PC). In the effective nuclear detection, the hardware involves the detection setup and the electronics used, with the software consisting of analysis tools and graphical display on PC. A data acquisition interface is necessary to enable the communication between the controller hardware and PC. Nowadays, Universal Serial Bus (USB) has become a standard connection method for computer peripherals and has replaced many varieties of serial and parallel ports. However the implementation of USB is complex. This paper describes the implementation of data acquisition interface between a field-programmable gate array (FPGA) board and a PC by exploiting the USB link of the FPGA board. The USB link is based on an FTDI chip which allows direct access of input and output to the Joint Test Action Group (JTAG) signals from a USB host and a complex programmable logic device (CPLD) with a 24 MHz clock input to the USB link. The implementation and results of using the USB link of FPGA board as the data interfacing are discussed. (author)

Implementation of data acquisition interface using on-board field-programmable gate array (FPGA) universal serial bus (USB) link

International Nuclear Information System (INIS)

Yussup, N.; Ibrahim, M. M.; Lombigit, L.; Rahman, N. A. A.; Zin, M. R. M.

2014-01-01

Typically a system consists of hardware as the controller and software which is installed in the personal computer (PC). In the effective nuclear detection, the hardware involves the detection setup and the electronics used, with the software consisting of analysis tools and graphical display on PC. A data acquisition interface is necessary to enable the communication between the controller hardware and PC. Nowadays, Universal Serial Bus (USB) has become a standard connection method for computer peripherals and has replaced many varieties of serial and parallel ports. However the implementation of USB is complex. This paper describes the implementation of data acquisition interface between a field-programmable gate array (FPGA) board and a PC by exploiting the USB link of the FPGA board. The USB link is based on an FTDI chip which allows direct access of input and output to the Joint Test Action Group (JTAG) signals from a USB host and a complex programmable logic device (CPLD) with a 24 MHz clock input to the USB link. The implementation and results of using the USB link of FPGA board as the data interfacing are discussed

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

Case for a field-programmable gate array multicore hybrid machine for an image-processing application

Science.gov (United States)

Rakvic, Ryan N.; Ives, Robert W.; Lira, Javier; Molina, Carlos

2011-01-01

General purpose computer designers have recently begun adding cores to their processors in order to increase performance. For example, Intel has adopted a homogeneous quad-core processor as a base for general purpose computing. PlayStation3 (PS3) game consoles contain a multicore heterogeneous processor known as the Cell, which is designed to perform complex image processing algorithms at a high level. Can modern image-processing algorithms utilize these additional cores? On the other hand, modern advancements in configurable hardware, most notably field-programmable gate arrays (FPGAs) have created an interesting question for general purpose computer designers. Is there a reason to combine FPGAs with multicore processors to create an FPGA multicore hybrid general purpose computer? Iris matching, a repeatedly executed portion of a modern iris-recognition algorithm, is parallelized on an Intel-based homogeneous multicore Xeon system, a heterogeneous multicore Cell system, and an FPGA multicore hybrid system. Surprisingly, the cheaper PS3 slightly outperforms the Intel-based multicore on a core-for-core basis. However, both multicore systems are beaten by the FPGA multicore hybrid system by >50%.

Tectonic modeling of Konya-Beysehir Region (Turkey using cellular neural networks

Directory of Open Access Journals (Sweden)

D. Aydogan

2007-06-01

Full Text Available In this paper, to separate regional-residual anomaly maps and to detect borders of buried geological bodies, we applied the Cellular Neural Network (CNN approach to gravity and magnetic anomaly maps. CNN is a stochastic image processing technique, based optimization of templates, which imply relationships of neighborhood pixels in 2-Dimensional (2D potential anomalies. Here, CNN performance in geophysics, tested by various synthetic examples and the results are compared to classical methods such as boundary analysis and second vertical derivatives. After we obtained satisfactory results in synthetic models, we applied CNN to Bouguer anomaly map of Konya-Beysehir Region, which has complex tectonic structure with various fault combinations. We evaluated CNN outputs and 2D/3D models, which are constructed using forward and inversion methods. Then we presented a new tectonic structure of Konya-Beysehir Region. We have denoted (F1, F2, …, F7 and (Konya1, Konya2 faults according to our evaluations of CNN outputs. Thus, we have concluded that CNN is a compromising stochastic image processing technique in geophysics.

Understanding of Object Detection Based on CNN Family and YOLO

Science.gov (United States)

Du, Juan

2018-04-01

As a key use of image processing, object detection has boomed along with the unprecedented advancement of Convolutional Neural Network (CNN) and its variants since 2012. When CNN series develops to Faster Region with CNN (R-CNN), the Mean Average Precision (mAP) has reached 76.4, whereas, the Frame Per Second (FPS) of Faster R-CNN remains 5 to 18 which is far slower than the real-time effect. Thus, the most urgent requirement of object detection improvement is to accelerate the speed. Based on the general introduction to the background and the core solution CNN, this paper exhibits one of the best CNN representatives You Only Look Once (YOLO), which breaks through the CNN family’s tradition and innovates a complete new way of solving the object detection with most simple and high efficient way. Its fastest speed has achieved the exciting unparalleled result with FPS 155, and its mAP can also reach up to 78.6, both of which have surpassed the performance of Faster R-CNN greatly. Additionally, compared with the latest most advanced solution, YOLOv2 achieves an excellent tradeoff between speed and accuracy as well as an object detector with strong generalization ability to represent the whole image.

SAR image classification based on CNN in real and simulation datasets

Science.gov (United States)

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

2018-04-01

Convolution neural network (CNN) has made great success in image classification tasks. Even in the field of synthetic aperture radar automatic target recognition (SAR-ATR), state-of-art results has been obtained by learning deep representation of features on the MSTAR benchmark. However, the raw data of MSTAR have shortcomings in training a SAR-ATR model because of high similarity in background among the SAR images of each kind. This indicates that the CNN would learn the hierarchies of features of backgrounds as well as the targets. To validate the influence of the background, some other SAR images datasets have been made which contains the simulation SAR images of 10 manufactured targets such as tank and fighter aircraft, and the backgrounds of simulation SAR images are sampled from the whole original MSTAR data. The simulation datasets contain the dataset that the backgrounds of each kind images correspond to the one kind of backgrounds of MSTAR targets or clutters and the dataset that each image shares the random background of whole MSTAR targets or clutters. In addition, mixed datasets of MSTAR and simulation datasets had been made to use in the experiments. The CNN architecture proposed in this paper are trained on all datasets mentioned above. The experimental results shows that the architecture can get high performances on all datasets even the backgrounds of the images are miscellaneous, which indicates the architecture can learn a good representation of the targets even though the drastic changes on background.

Automatic recognition of holistic functional brain networks using iteratively optimized convolutional neural networks (IO-CNN) with weak label initialization.

Science.gov (United States)

Zhao, Yu; Ge, Fangfei; Liu, Tianming

2018-07-01

fMRI data decomposition techniques have advanced significantly from shallow models such as Independent Component Analysis (ICA) and Sparse Coding and Dictionary Learning (SCDL) to deep learning models such Deep Belief Networks (DBN) and Convolutional Autoencoder (DCAE). However, interpretations of those decomposed networks are still open questions due to the lack of functional brain atlases, no correspondence across decomposed or reconstructed networks across different subjects, and significant individual variabilities. Recent studies showed that deep learning, especially deep convolutional neural networks (CNN), has extraordinary ability of accommodating spatial object patterns, e.g., our recent works using 3D CNN for fMRI-derived network classifications achieved high accuracy with a remarkable tolerance for mistakenly labelled training brain networks. However, the training data preparation is one of the biggest obstacles in these supervised deep learning models for functional brain network map recognitions, since manual labelling requires tedious and time-consuming labours which will sometimes even introduce label mistakes. Especially for mapping functional networks in large scale datasets such as hundreds of thousands of brain networks used in this paper, the manual labelling method will become almost infeasible. In response, in this work, we tackled both the network recognition and training data labelling tasks by proposing a new iteratively optimized deep learning CNN (IO-CNN) framework with an automatic weak label initialization, which enables the functional brain networks recognition task to a fully automatic large-scale classification procedure. Our extensive experiments based on ABIDE-II 1099 brains' fMRI data showed the great promise of our IO-CNN framework. Copyright © 2018 Elsevier B.V. All rights reserved.

Modeling and Simulation of a Non-Coherent Frequency Shift Keying Transceiver Using a Field Programmable Gate Array (FPGA)

National Research Council Canada - National Science Library

Voskakis, Konstantinos

2008-01-01

...) receiver-transmitter in a Field Programmable Gate Array (FPGA). After introducing the theory behind the Non- Coherent BFSK demodulation implemented at the receiver, the design of transmitter and receiver is illustrated...

Electroencephalography Based Fusion Two-Dimensional (2D-Convolution Neural Networks (CNN Model for Emotion Recognition System

Directory of Open Access Journals (Sweden)

Yea-Hoon Kwon

2018-04-01

Full Text Available The purpose of this study is to improve human emotional classification accuracy using a convolution neural networks (CNN model and to suggest an overall method to classify emotion based on multimodal data. We improved classification performance by combining electroencephalogram (EEG and galvanic skin response (GSR signals. GSR signals are preprocessed using by the zero-crossing rate. Sufficient EEG feature extraction can be obtained through CNN. Therefore, we propose a suitable CNN model for feature extraction by tuning hyper parameters in convolution filters. The EEG signal is preprocessed prior to convolution by a wavelet transform while considering time and frequency simultaneously. We use a database for emotion analysis using the physiological signals open dataset to verify the proposed process, achieving 73.4% accuracy, showing significant performance improvement over the current best practice models.

[Hardware Implementation of Numerical Simulation Function of Hodgkin-Huxley Model Neurons Action Potential Based on Field Programmable Gate Array].

Science.gov (United States)

Wang, Jinlong; Lu, Mai; Hu, Yanwen; Chen, Xiaoqiang; Pan, Qiangqiang

2015-12-01

Neuron is the basic unit of the biological neural system. The Hodgkin-Huxley (HH) model is one of the most realistic neuron models on the electrophysiological characteristic description of neuron. Hardware implementation of neuron could provide new research ideas to clinical treatment of spinal cord injury, bionics and artificial intelligence. Based on the HH model neuron and the DSP Builder technology, in the present study, a single HH model neuron hardware implementation was completed in Field Programmable Gate Array (FPGA). The neuron implemented in FPGA was stimulated by different types of current, the action potential response characteristics were analyzed, and the correlation coefficient between numerical simulation result and hardware implementation result were calculated. The results showed that neuronal action potential response of FPGA was highly consistent with numerical simulation result. This work lays the foundation for hardware implementation of neural network.

Robustness Design for CNN Templates with Performance of Extracting Closed Domain

International Nuclear Information System (INIS)

Li Weidong; Min Lequan

2006-01-01

The cellular neural/nonlinear network (CNN) is a powerful tool for image and video signal processing, robotic and biological visions. This paper introduces a kind of CNNs with performance of extracting closed domains in binary images, and gives a general method for designing templates of such a kind of CNNs. One theorem provides parameter inequalities for determining parameter intervals for implementing prescribed image processing functions, respectively. Examples for extracting closed domains in binary scale images are given.

Image processing with a cellular nonlinear network

International Nuclear Information System (INIS)

Morfu, S.

2005-01-01

A cellular nonlinear network (CNN) based on uncoupled nonlinear oscillators is proposed for image processing purposes. It is shown theoretically and numerically that the contrast of an image loaded at the nodes of the CNN is strongly enhanced, even if this one is initially weak. An image inversion can be also obtained without reconfiguration of the network whereas a gray levels extraction can be performed with an additional threshold filtering. Lastly, an electronic implementation of this CNN is presented

SIFT Meets CNN: A Decade Survey of Instance Retrieval.

Science.gov (United States)

Zheng, Liang; Yang, Yi; Tian, Qi

2018-05-01

In the early days, content-based image retrieval (CBIR) was studied with global features. Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively studied for over a decade due to the advantage of SIFT in dealing with image transformations. Recently, image representations based on the convolutional neural network (CNN) have attracted increasing interest in the community and demonstrated impressive performance. Given this time of rapid evolution, this article provides a comprehensive survey of instance retrieval over the last decade. Two broad categories, SIFT-based and CNN-based methods, are presented. For the former, according to the codebook size, we organize the literature into using large/medium-sized/small codebooks. For the latter, we discuss three lines of methods, i.e., using pre-trained or fine-tuned CNN models, and hybrid methods. The first two perform a single-pass of an image to the network, while the last category employs a patch-based feature extraction scheme. This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods. After analyzing and comparing retrieval performance of different categories on several datasets, we discuss promising directions towards generic and specialized instance retrieval.

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

Brain tumor segmentation in multi-spectral MRI using convolutional neural networks (CNN).

Science.gov (United States)

Iqbal, Sajid; Ghani, M Usman; Saba, Tanzila; Rehman, Amjad

2018-04-01

A tumor could be found in any area of the brain and could be of any size, shape, and contrast. There may exist multiple tumors of different types in a human brain at the same time. Accurate tumor area segmentation is considered primary step for treatment of brain tumors. Deep Learning is a set of promising techniques that could provide better results as compared to nondeep learning techniques for segmenting timorous part inside a brain. This article presents a deep convolutional neural network (CNN) to segment brain tumors in MRIs. The proposed network uses BRATS segmentation challenge dataset which is composed of images obtained through four different modalities. Accordingly, we present an extended version of existing network to solve segmentation problem. The network architecture consists of multiple neural network layers connected in sequential order with the feeding of Convolutional feature maps at the peer level. Experimental results on BRATS 2015 benchmark data thus show the usability of the proposed approach and its superiority over the other approaches in this area of research. © 2018 Wiley Periodicals, Inc.

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.

Developments of FPGA-based digital back-ends for low frequency antenna arrays at Medicina radio telescopes

Science.gov (United States)

Naldi, G.; Bartolini, M.; Mattana, A.; Pupillo, G.; Hickish, J.; Foster, G.; Bianchi, G.; Lingua, A.; Monari, J.; Montebugnoli, S.; Perini, F.; Rusticelli, S.; Schiaffino, M.; Virone, G.; Zarb Adami, K.

In radio astronomy Field Programmable Gate Array (FPGA) technology is largely used for the implementation of digital signal processing techniques applied to antenna arrays. This is mainly due to the good trade-off among computing resources, power consumption and cost offered by FPGA chip compared to other technologies like ASIC, GPU and CPU. In the last years several digital backend systems based on such devices have been developed at the Medicina radio astronomical station (INAF-IRA, Bologna, Italy). Instruments like FX correlator, direct imager, beamformer, multi-beam system have been successfully designed and realized on CASPER (Collaboration for Astronomy Signal Processing and Electronics Research, https://casper.berkeley.edu) processing boards. In this paper we present the gained experience in this kind of applications.

Cellular Neural Network for Real Time Image Processing

International Nuclear Information System (INIS)

Vagliasindi, G.; Arena, P.; Fortuna, L.; Mazzitelli, G.; Murari, A.

2008-01-01

Since their introduction in 1988, Cellular Nonlinear Networks (CNNs) have found a key role as image processing instruments. Thanks to their structure they are able of processing individual pixels in a parallel way providing fast image processing capabilities that has been applied to a wide range of field among which nuclear fusion. In the last years, indeed, visible and infrared video cameras have become more and more important in tokamak fusion experiments for the twofold aim of understanding the physics and monitoring the safety of the operation. Examining the output of these cameras in real-time can provide significant information for plasma control and safety of the machines. The potentiality of CNNs can be exploited to this aim. To demonstrate the feasibility of the approach, CNN image processing has been applied to several tasks both at the Frascati Tokamak Upgrade (FTU) and the Joint European Torus (JET)

Multiple constant multiplication optimizations for field programmable gate arrays

CERN Document Server

Kumm, Martin

2016-01-01

This work covers field programmable gate array (FPGA)-specific optimizations of circuits computing the multiplication of a variable by several constants, commonly denoted as multiple constant multiplication (MCM). These optimizations focus on low resource usage but high performance. They comprise the use of fast carry-chains in adder-based constant multiplications including ternary (3-input) adders as well as the integration of look-up table-based constant multipliers and embedded multipliers to get the optimal mapping to modern FPGAs. The proposed methods can be used for the efficient implementation of digital filters, discrete transforms and many other circuits in the domain of digital signal processing, communication and image processing. Contents Heuristic and ILP-Based Optimal Solutions for the Pipelined Multiple Constant Multiplication Problem Methods to Integrate Embedded Multipliers, LUT-Based Constant Multipliers and Ternary (3-Input) Adders An Optimized Multiple Constant Multiplication Architecture ...

Real-time field programmable gate array architecture for computer vision

Science.gov (United States)

Arias-Estrada, Miguel; Torres-Huitzil, Cesar

2001-01-01

This paper presents an architecture for real-time generic convolution of a mask and an image. The architecture is intended for fast low-level image processing. The field programmable gate array (FPGA)-based architecture takes advantage of the availability of registers in FPGAs to implement an efficient and compact module to process the convolutions. The architecture is designed to minimize the number of accesses to the image memory and it is based on parallel modules with internal pipeline operation in order to improve its performance. The architecture is prototyped in a FPGA, but it can be implemented on dedicated very- large-scale-integrated devices to reach higher clock frequencies. Complexity issues, FPGA resources utilization, FPGA limitations, and real-time performance are discussed. Some results are presented and discussed.

Multi-Pixel Simultaneous Classification of PolSAR Image Using Convolutional Neural Networks

Science.gov (United States)

Xu, Xin; Gui, Rong; Pu, Fangling

2018-01-01

Convolutional neural networks (CNN) have achieved great success in the optical image processing field. Because of the excellent performance of CNN, more and more methods based on CNN are applied to polarimetric synthetic aperture radar (PolSAR) image classification. Most CNN-based PolSAR image classification methods can only classify one pixel each time. Because all the pixels of a PolSAR image are classified independently, the inherent interrelation of different land covers is ignored. We use a fixed-feature-size CNN (FFS-CNN) to classify all pixels in a patch simultaneously. The proposed method has several advantages. First, FFS-CNN can classify all the pixels in a small patch simultaneously. When classifying a whole PolSAR image, it is faster than common CNNs. Second, FFS-CNN is trained to learn the interrelation of different land covers in a patch, so it can use the interrelation of land covers to improve the classification results. The experiments of FFS-CNN are evaluated on a Chinese Gaofen-3 PolSAR image and other two real PolSAR images. Experiment results show that FFS-CNN is comparable with the state-of-the-art PolSAR image classification methods. PMID:29510499

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.

H31G-1596: DeepSAT's CloudCNN: A Deep Neural Network for Rapid Cloud Detection from Geostationary Satellites

Science.gov (United States)

Kalia, Subodh; Ganguly, Sangram; Li, Shuang; Nemani, Ramakrishna R.

2017-01-01

Cloud and cloud shadow detection has important applications in weather and climate studies. It is even more crucial when we introduce geostationary satellites into the field of terrestrial remote sensing. With the challenges associated with data acquired in very high frequency (10-15 mins per scan), the ability to derive an accurate cloud shadow mask from geostationary satellite data is critical. The key to the success for most of the existing algorithms depends on spatially and temporally varying thresholds,which better capture local atmospheric and surface effects.However, the selection of proper threshold is difficult and may lead to erroneous results. In this work, we propose a deep neural network based approach called CloudCNN to classify cloudshadow from Himawari-8 AHI and GOES-16 ABI multispectral data. DeepSAT's CloudCNN consists of an encoderdecoder based architecture for binary-class pixel wise segmentation. We train CloudCNN on multi-GPU Nvidia Devbox cluster, and deploy the prediction pipeline on NASA Earth Exchange (NEX) Pleiades supercomputer. We achieved an overall accuracy of 93.29% on test samples. Since, the predictions take only a few seconds to segment a full multispectral GOES-16 or Himawari-8 Full Disk image, the developed framework can be used for real-time cloud detection, cyclone detection, or extreme weather event predictions.

Classifying Wheat Hyperspectral Pixels of Healthy Heads and Fusarium Head Blight Disease Using a Deep Neural Network in the Wild Field

Directory of Open Access Journals (Sweden)

Xiu Jin

2018-03-01

Full Text Available Classification of healthy and diseased wheat heads in a rapid and non-destructive manner for the early diagnosis of Fusarium head blight disease research is difficult. Our work applies a deep neural network classification algorithm to the pixels of hyperspectral image to accurately discern the disease area. The spectra of hyperspectral image pixels in a manually selected region of interest are preprocessed via mean removal to eliminate interference, due to the time interval and the environment. The generalization of the classification model is considered, and two improvements are made to the model framework. First, the pixel spectra data are reshaped into a two-dimensional data structure for the input layer of a Convolutional Neural Network (CNN. After training two types of CNNs, the assessment shows that a two-dimensional CNN model is more efficient than a one-dimensional CNN. Second, a hybrid neural network with a convolutional layer and bidirectional recurrent layer is reconstructed to improve the generalization of the model. When considering the characteristics of the dataset and models, the confusion matrices that are based on the testing dataset indicate that the classification model is effective for background and disease classification of hyperspectral image pixels. The results of the model show that the two-dimensional convolutional bidirectional gated recurrent unit neural network (2D-CNN-BidGRU has an F1 score and accuracy of 0.75 and 0.743, respectively, for the total testing dataset. A comparison of all the models shows that the hybrid neural network of 2D-CNN-BidGRU is the best at preventing over-fitting and optimize the generalization. Our results illustrate that the hybrid structure deep neural network is an excellent classification algorithm for healthy and Fusarium head blight diseased classification in the field of hyperspectral imagery.

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.

Field-programmable gate array implementation of an all-digital IEEE 802.15.4-compliant transceiver

Science.gov (United States)

Cornetta, Gianluca; Touhafi, Abdellah; Santos, David J.; Vázquez, José M.

2010-12-01

An architecture for a low-cost, low-complexity digital transceiver is presented in this article. The proposed architecture targets the IEEE 802.15.4 standard for short-range wireless personal area networks and has been implemented as a synthesisable VHDL register transfer level description. The system has been evaluated and tested using a Xilinx 90 nm Virtex-4 field-programmable gate array as the target technology. Bit error rate (BER) and error vector magnitude (EVM) have been used as the figures of merit for modem performance. Simulations show that the recommended minimum BER is achieved at E b/N 0 = 8.7 dB, whereas the EVM is 19.5%. The implemented device occupies 10% of the target FPGA and has a normalised maximum power consumption of 44 mW in transmit mode and 53 mW in receiver mode.

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.

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.

Classification of C2C12 cells at differentiation by convolutional neural network of deep learning using phase contrast images.

Science.gov (United States)

Niioka, Hirohiko; Asatani, Satoshi; Yoshimura, Aina; Ohigashi, Hironori; Tagawa, Seiichi; Miyake, Jun

2018-01-01

In the field of regenerative medicine, tremendous numbers of cells are necessary for tissue/organ regeneration. Today automatic cell-culturing system has been developed. The next step is constructing a non-invasive method to monitor the conditions of cells automatically. As an image analysis method, convolutional neural network (CNN), one of the deep learning method, is approaching human recognition level. We constructed and applied the CNN algorithm for automatic cellular differentiation recognition of myogenic C2C12 cell line. Phase-contrast images of cultured C2C12 are prepared as input dataset. In differentiation process from myoblasts to myotubes, cellular morphology changes from round shape to elongated tubular shape due to fusion of the cells. CNN abstract the features of the shape of the cells and classify the cells depending on the culturing days from when differentiation is induced. Changes in cellular shape depending on the number of days of culture (Day 0, Day 3, Day 6) are classified with 91.3% accuracy. Image analysis with CNN has a potential to realize regenerative medicine industry.

FPGA IMPLEMENTATION OF ADAPTIVE INTEGRATED SPIKING NEURAL NETWORK FOR EFFICIENT IMAGE RECOGNITION SYSTEM

Directory of Open Access Journals (Sweden)

T. Pasupathi

2014-05-01

Full Text Available Image recognition is a technology which can be used in various applications such as medical image recognition systems, security, defense video tracking, and factory automation. In this paper we present a novel pipelined architecture of an adaptive integrated Artificial Neural Network for image recognition. In our proposed work we have combined the feature of spiking neuron concept with ANN to achieve the efficient architecture for image recognition. The set of training images are trained by ANN and target output has been identified. Real time videos are captured and then converted into frames for testing purpose and the image were recognized. The machine can operate at up to 40 frames/sec using images acquired from the camera. The system has been implemented on XC3S400 SPARTAN-3 Field Programmable Gate Arrays.

A flexible 32-channel time-to-digital converter implemented in a Xilinx Zynq-7000 field programmable gate array

International Nuclear Information System (INIS)

Wang, Yonggang; Kuang, Jie; Liu, Chong; Cao, Qiang; Li, Deng

2017-01-01

A high performance multi-channel time-to-digital converter (TDC) is implemented in a Xilinx Zynq-7000 field programmable gate array (FPGA). It can be flexibly configured as either 32 TDC channels with 9.9 ps time-interval RMS precision, 16 TDC channels with 6.9 ps RMS precision, or 8 TDC channels with 5.8 ps RMS precision. All TDCs have a 380 M Samples/second measurement throughput and a 2.63 ns measurement dead time. The performance consistency and temperature dependence of TDC channels are also evaluated. Because Zynq-7000 FPGA family integrates a feature-rich dual-core ARM based processing system and 28 nm Xilinx programmable logic in a single device, the realization of high performance TDCs on it will make the platform more widely used in time-measuring related applications.

A flexible 32-channel time-to-digital converter implemented in a Xilinx Zynq-7000 field programmable gate array

Energy Technology Data Exchange (ETDEWEB)

Wang, Yonggang, E-mail: wangyg@ustc.edu.cn; Kuang, Jie; Liu, Chong; Cao, Qiang; Li, Deng

2017-03-01

A high performance multi-channel time-to-digital converter (TDC) is implemented in a Xilinx Zynq-7000 field programmable gate array (FPGA). It can be flexibly configured as either 32 TDC channels with 9.9 ps time-interval RMS precision, 16 TDC channels with 6.9 ps RMS precision, or 8 TDC channels with 5.8 ps RMS precision. All TDCs have a 380 M Samples/second measurement throughput and a 2.63 ns measurement dead time. The performance consistency and temperature dependence of TDC channels are also evaluated. Because Zynq-7000 FPGA family integrates a feature-rich dual-core ARM based processing system and 28 nm Xilinx programmable logic in a single device, the realization of high performance TDCs on it will make the platform more widely used in time-measuring related applications.

Handwritten Digits Recognition Using Neural Computing

Directory of Open Access Journals (Sweden)

Călin Enăchescu

2009-12-01

Full Text Available In this paper we present a method for the recognition of handwritten digits and a practical implementation of this method for real-time recognition. A theoretical framework for the neural networks used to classify the handwritten digits is also presented.The classification task is performed using a Convolutional Neural Network (CNN. CNN is a special type of multy-layer neural network, being trained with an optimized version of the back-propagation learning algorithm.CNN is designed to recognize visual patterns directly from pixel images with minimal preprocessing, being capable to recognize patterns with extreme variability (such as handwritten characters, and with robustness to distortions and simple geometric transformations.The main contributions of this paper are related to theoriginal methods for increasing the efficiency of the learning algorithm by preprocessing the images before the learning process and a method for increasing the precision and performance for real-time applications, by removing the non useful information from the background.By combining these strategies we have obtained an accuracy of 96.76%, using as training set the NIST (National Institute of Standards and Technology database.

GRAM-CNN: a deep learning approach with local context for named entity recognition in biomedical text.

Science.gov (United States)

Zhu, Qile; Li, Xiaolin; Conesa, Ana; Pereira, Cécile

2018-05-01

Best performing named entity recognition (NER) methods for biomedical literature are based on hand-crafted features or task-specific rules, which are costly to produce and difficult to generalize to other corpora. End-to-end neural networks achieve state-of-the-art performance without hand-crafted features and task-specific knowledge in non-biomedical NER tasks. However, in the biomedical domain, using the same architecture does not yield competitive performance compared with conventional machine learning models. We propose a novel end-to-end deep learning approach for biomedical NER tasks that leverages the local contexts based on n-gram character and word embeddings via Convolutional Neural Network (CNN). We call this approach GRAM-CNN. To automatically label a word, this method uses the local information around a word. Therefore, the GRAM-CNN method does not require any specific knowledge or feature engineering and can be theoretically applied to a wide range of existing NER problems. The GRAM-CNN approach was evaluated on three well-known biomedical datasets containing different BioNER entities. It obtained an F1-score of 87.26% on the Biocreative II dataset, 87.26% on the NCBI dataset and 72.57% on the JNLPBA dataset. Those results put GRAM-CNN in the lead of the biological NER methods. To the best of our knowledge, we are the first to apply CNN based structures to BioNER problems. The GRAM-CNN source code, datasets and pre-trained model are available online at: https://github.com/valdersoul/GRAM-CNN. andyli@ece.ufl.edu or aconesa@ufl.edu. Supplementary data are available at Bioinformatics online.

Similarity estimation for reference image retrieval in mammograms using convolutional neural network

Science.gov (United States)

Muramatsu, Chisako; Higuchi, Shunichi; Morita, Takako; Oiwa, Mikinao; Fujita, Hiroshi

2018-02-01

Periodic breast cancer screening with mammography is considered effective in decreasing breast cancer mortality. For screening programs to be successful, an intelligent image analytic system may support radiologists' efficient image interpretation. In our previous studies, we have investigated image retrieval schemes for diagnostic references of breast lesions on mammograms and ultrasound images. Using a machine learning method, reliable similarity measures that agree with radiologists' similarity were determined and relevant images could be retrieved. However, our previous method includes a feature extraction step, in which hand crafted features were determined based on manual outlines of the masses. Obtaining the manual outlines of masses is not practical in clinical practice and such data would be operator-dependent. In this study, we investigated a similarity estimation scheme using a convolutional neural network (CNN) to skip such procedure and to determine data-driven similarity scores. By using CNN as feature extractor, in which extracted features were employed in determination of similarity measures with a conventional 3-layered neural network, the determined similarity measures were correlated well with the subjective ratings and the precision of retrieving diagnostically relevant images was comparable with that of the conventional method using handcrafted features. By using CNN for determination of similarity measure directly, the result was also comparable. By optimizing the network parameters, results may be further improved. The proposed method has a potential usefulness in determination of similarity measure without precise lesion outlines for retrieval of similar mass images on mammograms.

An FPGA-Based Quantum Computing Emulation Framework Based on Serial-Parallel Architecture

Directory of Open Access Journals (Sweden)

Y. H. Lee

2016-01-01

Full Text Available Hardware emulation of quantum systems can mimic more efficiently the parallel behaviour of quantum computations, thus allowing higher processing speed-up than software simulations. In this paper, an efficient hardware emulation method that employs a serial-parallel hardware architecture targeted for field programmable gate array (FPGA is proposed. Quantum Fourier transform and Grover’s search are chosen as case studies in this work since they are the core of many useful quantum algorithms. Experimental work shows that, with the proposed emulation architecture, a linear reduction in resource utilization is attained against the pipeline implementations proposed in prior works. The proposed work contributes to the formulation of a proof-of-concept baseline FPGA emulation framework with optimization on datapath designs that can be extended to emulate practical large-scale quantum circuits.

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.

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. PMID:29066942

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.

Cellular Neural Network Method for Critical Slab with Albedo Boundary Condition

International Nuclear Information System (INIS)

Pirouzmanda, A.; Hadada, K.; Suh, K. Y.

2010-01-01

The neutron transport problems have been studied theoretically and numerically for years. A number of researchers have studied the criticality problems of one-speed neutrons in homogeneous slabs and spheres using various methods. The Chebyshev polynomial approximation method (T N method) has lately been developed and improved for the neutron transport equation in slab geometry. The one-speed time-dependent neutron transport equation using the Cellular Neural Network (CNN) for the vacuum boundary condition has previously been solved. In this paper, we demonstrate the capacity of CNN in calculating the critical slab thickness for different boundary conditions and its variation with moments N. The architecture of the CNN has already been dealt with thoroughly. Essentially, the CNN is used to model a first-order system of the partial differential equations (PDEs). The original equations in the T N approximation are also a set of PDEs. The CNN approach lends itself to analog VLSI implementation. In this study, the CNN model is implemented using the HSpice software package

Cellular neural network to the spherical harmonics approximation of neutron transport equation in x–y geometry

International Nuclear Information System (INIS)

Pirouzmand, Ahmad; Hadad, Kamal

2012-01-01

Highlights: ► This paper describes the solution of time-dependent neutron transport equation. ► We use a novel method based on cellular neural networks (CNNs) coupled with the spherical harmonics method. ► We apply the CNN model to simulate step and ramp perturbation transients in a core. ► The accuracy and capabilities of the CNN model are examined for x–y geometry. - Abstract: In an earlier paper we utilized a novel method using cellular neural networks (CNNs) coupled with spherical harmonics method to solve the steady state neutron transport equation in x–y geometry. Here, the previous work is extended to the study of time-dependent neutron transport equation. To achieve this goal, an equivalent electrical circuit based on a second-order form of time-dependent neutron transport equation and one equivalent group of neutron precursor density is obtained by the CNN method. The CNN model is used to simulate step and ramp perturbation transients in a typical 2D core.

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.

A counting-weighted calibration method for a field-programmable-gate-array-based time-to-digital converter

International Nuclear Information System (INIS)

Chen, Yuan-Ho

2017-01-01

In this work, we propose a counting-weighted calibration method for field-programmable-gate-array (FPGA)-based time-to-digital converter (TDC) to provide non-linearity calibration for use in positron emission tomography (PET) scanners. To deal with the non-linearity in FPGA, we developed a counting-weighted delay line (CWD) to count the delay time of the delay cells in the TDC in order to reduce the differential non-linearity (DNL) values based on code density counts. The performance of the proposed CWD-TDC with regard to linearity far exceeds that of TDC with a traditional tapped delay line (TDL) architecture, without the need for nonlinearity calibration. When implemented in a Xilinx Vertix-5 FPGA device, the proposed CWD-TDC achieved time resolution of 60 ps with integral non-linearity (INL) and DNL of [−0.54, 0.24] and [−0.66, 0.65] least-significant-bit (LSB), respectively. This is a clear indication of the suitability of the proposed FPGA-based CWD-TDC for use in PET scanners.

A counting-weighted calibration method for a field-programmable-gate-array-based time-to-digital converter

Energy Technology Data Exchange (ETDEWEB)

Chen, Yuan-Ho, E-mail: chenyh@mail.cgu.edu.tw [Department of Electronic Engineering, Chang Gung University, Tao-Yuan 333, Taiwan (China); Department of Radiation Oncology, Chang Gung Memorial Hospital, Tao-Yuan 333, Taiwan (China); Center for Reliability Sciences and Technologies, Chang Gung University, Tao-Yuan 333, Taiwan (China)

2017-05-11

In this work, we propose a counting-weighted calibration method for field-programmable-gate-array (FPGA)-based time-to-digital converter (TDC) to provide non-linearity calibration for use in positron emission tomography (PET) scanners. To deal with the non-linearity in FPGA, we developed a counting-weighted delay line (CWD) to count the delay time of the delay cells in the TDC in order to reduce the differential non-linearity (DNL) values based on code density counts. The performance of the proposed CWD-TDC with regard to linearity far exceeds that of TDC with a traditional tapped delay line (TDL) architecture, without the need for nonlinearity calibration. When implemented in a Xilinx Vertix-5 FPGA device, the proposed CWD-TDC achieved time resolution of 60 ps with integral non-linearity (INL) and DNL of [−0.54, 0.24] and [−0.66, 0.65] least-significant-bit (LSB), respectively. This is a clear indication of the suitability of the proposed FPGA-based CWD-TDC for use in PET scanners.

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.

Global detection of live virtual machine migration based on cellular neural networks.

Science.gov (United States)

Xie, Kang; Yang, Yixian; Zhang, Ling; Jing, Maohua; Xin, Yang; Li, Zhongxian

2014-01-01

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.

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.

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.

Involvement of Machine Learning for Breast Cancer Image Classification: A Survey.

Science.gov (United States)

Nahid, Abdullah-Al; Kong, Yinan

2017-01-01

Breast cancer is one of the largest causes of women's death in the world today. Advance engineering of natural image classification techniques and Artificial Intelligence methods has largely been used for the breast-image classification task. The involvement of digital image classification allows the doctor and the physicians a second opinion, and it saves the doctors' and physicians' time. Despite the various publications on breast image classification, very few review papers are available which provide a detailed description of breast cancer image classification techniques, feature extraction and selection procedures, classification measuring parameterizations, and image classification findings. We have put a special emphasis on the Convolutional Neural Network (CNN) method for breast image classification. Along with the CNN method we have also described the involvement of the conventional Neural Network (NN), Logic Based classifiers such as the Random Forest (RF) algorithm, Support Vector Machines (SVM), Bayesian methods, and a few of the semisupervised and unsupervised methods which have been used for breast image classification.

Involvement of Machine Learning for Breast Cancer Image Classification: A Survey

Directory of Open Access Journals (Sweden)

Abdullah-Al Nahid

2017-01-01

Full Text Available Breast cancer is one of the largest causes of women’s death in the world today. Advance engineering of natural image classification techniques and Artificial Intelligence methods has largely been used for the breast-image classification task. The involvement of digital image classification allows the doctor and the physicians a second opinion, and it saves the doctors’ and physicians’ time. Despite the various publications on breast image classification, very few review papers are available which provide a detailed description of breast cancer image classification techniques, feature extraction and selection procedures, classification measuring parameterizations, and image classification findings. We have put a special emphasis on the Convolutional Neural Network (CNN method for breast image classification. Along with the CNN method we have also described the involvement of the conventional Neural Network (NN, Logic Based classifiers such as the Random Forest (RF algorithm, Support Vector Machines (SVM, Bayesian methods, and a few of the semisupervised and unsupervised methods which have been used for breast image classification.

Cellular neural networks for motion estimation and obstacle detection

Directory of Open Access Journals (Sweden)

D. Feiden

2003-01-01

Full Text Available Obstacle detection is an important part of Video Processing because it is indispensable for a collision prevention of autonomously navigating moving objects. For example, vehicles driving without human guidance need a robust prediction of potential obstacles, like other vehicles or pedestrians. Most of the common approaches of obstacle detection so far use analytical and statistical methods like motion estimation or generation of maps. In the first part of this contribution a statistical algorithm for obstacle detection in monocular video sequences is presented. The proposed procedure is based on a motion estimation and a planar world model which is appropriate to traffic scenes. The different processing steps of the statistical procedure are a feature extraction, a subsequent displacement vector estimation and a robust estimation of the motion parameters. Since the proposed procedure is composed of several processing steps, the error propagation of the successive steps often leads to inaccurate results. In the second part of this contribution it is demonstrated, that the above mentioned problems can be efficiently overcome by using Cellular Neural Networks (CNN. It will be shown, that a direct obstacle detection algorithm can be easily performed, based only on CNN processing of the input images. Beside the enormous computing power of programmable CNN based devices, the proposed method is also very robust in comparison to the statistical method, because is shows much less sensibility to noisy inputs. Using the proposed approach of obstacle detection in planar worlds, a real time processing of large input images has been made possible.

Field Programmable Gate Array Control of Power Systems in Graduate Student Laboratories

National Research Council Canada - National Science Library

O'Connor, Joseph E

2008-01-01

...) continuously develops new design and education resources for students. One area of focus for students in the Power Electronics curriculum track is the development of a design center that explores Field Programmable Gate Array (FPGA...

Convolutional Neural Network Based on Extreme Learning Machine for Maritime Ships Recognition in Infrared Images.

Science.gov (United States)

Khellal, Atmane; Ma, Hongbin; Fei, Qing

2018-05-09

The success of Deep Learning models, notably convolutional neural networks (CNNs), makes them the favorable solution for object recognition systems in both visible and infrared domains. However, the lack of training data in the case of maritime ships research leads to poor performance due to the problem of overfitting. In addition, the back-propagation algorithm used to train CNN is very slow and requires tuning many hyperparameters. To overcome these weaknesses, we introduce a new approach fully based on Extreme Learning Machine (ELM) to learn useful CNN features and perform a fast and accurate classification, which is suitable for infrared-based recognition systems. The proposed approach combines an ELM based learning algorithm to train CNN for discriminative features extraction and an ELM based ensemble for classification. The experimental results on VAIS dataset, which is the largest dataset of maritime ships, confirm that the proposed approach outperforms the state-of-the-art models in term of generalization performance and training speed. For instance, the proposed model is up to 950 times faster than the traditional back-propagation based training of convolutional neural networks, primarily for low-level features extraction.

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.

NEPP Update of Independent Single Event Upset Field Programmable Gate Array Testing

Science.gov (United States)

Berg, Melanie; Label, Kenneth; Campola, Michael; Pellish, Jonathan

2017-01-01

This presentation provides a NASA Electronic Parts and Packaging (NEPP) Program update of independent Single Event Upset (SEU) Field Programmable Gate Array (FPGA) testing including FPGA test guidelines, Microsemi RTG4 heavy-ion results, Xilinx Kintex-UltraScale heavy-ion results, Xilinx UltraScale+ single event effect (SEE) test plans, development of a new methodology for characterizing SEU system response, and NEPP involvement with FPGA security and trust.

A Massively Parallel Face Recognition System

Directory of Open Access Journals (Sweden)

Lahdenoja Olli

2007-01-01

Full Text Available We present methods for processing the LBPs (local binary patterns with a massively parallel hardware, especially with CNN-UM (cellular nonlinear network-universal machine. In particular, we present a framework for implementing a massively parallel face recognition system, including a dedicated highly accurate algorithm suitable for various types of platforms (e.g., CNN-UM and digital FPGA. We study in detail a dedicated mixed-mode implementation of the algorithm and estimate its implementation cost in the view of its performance and accuracy restrictions.

A Massively Parallel Face Recognition System

Directory of Open Access Journals (Sweden)

Ari Paasio

2006-12-01

Full Text Available We present methods for processing the LBPs (local binary patterns with a massively parallel hardware, especially with CNN-UM (cellular nonlinear network-universal machine. In particular, we present a framework for implementing a massively parallel face recognition system, including a dedicated highly accurate algorithm suitable for various types of platforms (e.g., CNN-UM and digital FPGA. We study in detail a dedicated mixed-mode implementation of the algorithm and estimate its implementation cost in the view of its performance and accuracy restrictions.

Cellular neural network to the spherical harmonics approximation of neutron transport equation in x-y geometry. Part I: Modeling and verification for time-independent solution

International Nuclear Information System (INIS)

Pirouzmand, Ahmad; Hadad, Kamal

2011-01-01

Highlights: → This paper describes the solution of time-independent neutron transport equation. → Using a novel method based on cellular neural networks (CNNs) coupled with P N method. → Utilize the CNN model to simulate spatial scalar flux distribution in steady state. → The accuracy, stability, and capabilities of CNN model are examined in x-y geometry. - Abstract: This paper describes a novel method based on using cellular neural networks (CNN) coupled with spherical harmonics method (P N ) to solve the time-independent neutron transport equation in x-y geometry. To achieve this, an equivalent electrical circuit based on second-order form of neutron transport equation and relevant boundary conditions is obtained using CNN method. We use the CNN model to simulate spatial response of scalar flux distribution in the steady state condition for different order of spherical harmonics approximations. The accuracy, stability, and capabilities of CNN model are examined in 2D Cartesian geometry for fixed source and criticality problems.

How Transferable are CNN-based Features for Age and Gender Classification?

OpenAIRE

Özbulak, Gökhan; Aytar, Yusuf; Ekenel, Hazım Kemal

2016-01-01

Age and gender are complementary soft biometric traits for face recognition. Successful estimation of age and gender from facial images taken under real-world conditions can contribute improving the identification results in the wild. In this study, in order to achieve robust age and gender classification in the wild, we have benefited from Deep Convolutional Neural Networks based representation. We have explored transferability of existing deep convolutional neural network (CNN) models for a...

Depth Reconstruction from Single Images Using a Convolutional Neural Network and a Condition Random Field Model

Directory of Open Access Journals (Sweden)

Dan Liu

2018-04-01

Full Text Available This paper presents an effective approach for depth reconstruction from a single image through the incorporation of semantic information and local details from the image. A unified framework for depth acquisition is constructed by joining a deep Convolutional Neural Network (CNN and a continuous pairwise Conditional Random Field (CRF model. Semantic information and relative depth trends of local regions inside the image are integrated into the framework. A deep CNN network is firstly used to automatically learn a hierarchical feature representation of the image. To get more local details in the image, the relative depth trends of local regions are incorporated into the network. Combined with semantic information of the image, a continuous pairwise CRF is then established and is used as the loss function of the unified model. Experiments on real scenes demonstrate that the proposed approach is effective and that the approach obtains satisfactory results.

Depth Reconstruction from Single Images Using a Convolutional Neural Network and a Condition Random Field Model.

Science.gov (United States)

Liu, Dan; Liu, Xuejun; Wu, Yiguang

2018-04-24

This paper presents an effective approach for depth reconstruction from a single image through the incorporation of semantic information and local details from the image. A unified framework for depth acquisition is constructed by joining a deep Convolutional Neural Network (CNN) and a continuous pairwise Conditional Random Field (CRF) model. Semantic information and relative depth trends of local regions inside the image are integrated into the framework. A deep CNN network is firstly used to automatically learn a hierarchical feature representation of the image. To get more local details in the image, the relative depth trends of local regions are incorporated into the network. Combined with semantic information of the image, a continuous pairwise CRF is then established and is used as the loss function of the unified model. Experiments on real scenes demonstrate that the proposed approach is effective and that the approach obtains satisfactory results.

Relative location prediction in CT scan images using convolutional neural networks.

Science.gov (United States)

Guo, Jiajia; Du, Hongwei; Zhu, Jianyue; Yan, Ting; Qiu, Bensheng

2018-07-01

Relative location prediction in computed tomography (CT) scan images is a challenging problem. Many traditional machine learning methods have been applied in attempts to alleviate this problem. However, the accuracy and speed of these methods cannot meet the requirement of medical scenario. In this paper, we propose a regression model based on one-dimensional convolutional neural networks (CNN) to determine the relative location of a CT scan image both quickly and precisely. In contrast to other common CNN models that use a two-dimensional image as an input, the input of this CNN model is a feature vector extracted by a shape context algorithm with spatial correlation. Normalization via z-score is first applied as a pre-processing step. Then, in order to prevent overfitting and improve model's performance, 20% of the elements of the feature vectors are randomly set to zero. This CNN model consists primarily of three one-dimensional convolutional layers, three dropout layers and two fully-connected layers with appropriate loss functions. A public dataset is employed to validate the performance of the proposed model using a 5-fold cross validation. Experimental results demonstrate an excellent performance of the proposed model when compared with contemporary techniques, achieving a median absolute error of 1.04 cm and mean absolute error of 1.69 cm. The time taken for each relative location prediction is approximately 2 ms. Results indicate that the proposed CNN method can contribute to a quick and accurate relative location prediction in CT scan images, which can improve efficiency of the medical picture archiving and communication system in the future. Copyright © 2018 Elsevier B.V. All rights reserved.

Application of Field Programmable Gate Arrays in Instrumentation and Control Systems of Nuclear Power Plants

International Nuclear Information System (INIS)

2016-01-01

Field programmable gate arrays (FPGAs) are gaining increased attention worldwide for application in nuclear power plant (NPP) instrumentation and control (I&C) systems, particularly for safety and safety related applications, but also for non-safety ones. NPP operators and equipment suppliers see potential advantages of FPGA based digital I&C systems as compared to microprocessor based applications. This is because FPGA based systems can be made simpler, more testable and less reliant on complex software (e.g. operating systems), and are easier to qualify for safety and safety related applications. This publication results from IAEA consultancy meetings covering the various aspects, including design, qualification, implementation, licensing, and operation, of FPGA based I&C systems in NPPs

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.

Logic synthesis for FPGA-based finite state machines

CERN Document Server

Barkalov, Alexander; Kolopienczyk, Malgorzata; Mielcarek, Kamil; Bazydlo, Grzegorz

2016-01-01

This book discusses control units represented by the model of a finite state machine (FSM). It contains various original methods and takes into account the peculiarities of field-programmable gate arrays (FPGA) chips and a FSM model. It shows that one of the peculiarities of FPGA chips is the existence of embedded memory blocks (EMB). The book is devoted to the solution of problems of logic synthesis and reduction of hardware amount in control units. The book will be interesting and useful for researchers and PhD students in the area of Electrical Engineering and Computer Science, as well as for designers of modern digital systems.

Full image-processing pipeline in field-programmable gate array for a small endoscopic camera

Science.gov (United States)

Mostafa, Sheikh Shanawaz; Sousa, L. Natércia; Ferreira, Nuno Fábio; Sousa, Ricardo M.; Santos, Joao; Wäny, Martin; Morgado-Dias, F.

2017-01-01

Endoscopy is an imaging procedure used for diagnosis as well as for some surgical purposes. The camera used for the endoscopy should be small and able to produce a good quality image or video, to reduce discomfort of the patients, and to increase the efficiency of the medical team. To achieve these fundamental goals, a small endoscopy camera with a footprint of 1 mm×1 mm×1.65 mm is used. Due to the physical properties of the sensors and human vision system limitations, different image-processing algorithms, such as noise reduction, demosaicking, and gamma correction, among others, are needed to faithfully reproduce the image or video. A full image-processing pipeline is implemented using a field-programmable gate array (FPGA) to accomplish a high frame rate of 60 fps with minimum processing delay. Along with this, a viewer has also been developed to display and control the image-processing pipeline. The control and data transfer are done by a USB 3.0 end point in the computer. The full developed system achieves real-time processing of the image and fits in a Xilinx Spartan-6LX150 FPGA.

Radiation-hardened optically reconfigurable gate array exploiting holographic memory characteristics

Science.gov (United States)

Seto, Daisaku; Watanabe, Minoru

2015-09-01

In this paper, we present a proposal for a radiation-hardened optically reconfigurable gate array (ORGA). The ORGA is a type of field programmable gate array (FPGA). The ORGA configuration can be executed by the exploitation of holographic memory characteristics even if 20% of the configuration data are damaged. Moreover, the optoelectronic technology enables the high-speed reconfiguration of the programmable gate array. Such a high-speed reconfiguration can increase the radiation tolerance of its programmable gate array to 9.3 × 104 times higher than that of current FPGAs. Through experimentation, this study clarified the configuration dependability using the impulse-noise emulation and high-speed configuration capabilities of the ORGA with corrupt configuration contexts. Moreover, the radiation tolerance of the programmable gate array was confirmed theoretically through probabilistic calculation.

Using field programmable gate array hardware for the performance improvement of ultrasonic wave propagation imaging system

Energy Technology Data Exchange (ETDEWEB)

Shan, Jaffry Syed [Hamdard University, Karachi (Pakistan); Abbas, Syed Haider; Lee, Jung Ryul [Dept. of Aerospace Engineering, Korea Advanced Institute of Science and Technology, Daejeon (Korea, Republic of); Kang, Dong Hoon [Advanced Materials Research Team, Korea Railroad Research Institute, Uiwang (Korea, Republic of)

2015-12-15

Recently, wave propagation imaging based on laser scanning-generated elastic waves has been intensively used for nondestructive inspection. However, the proficiency of the conventional software based system reduces when the scan area is large since the processing time increases significantly due to unavoidable processor multitasking, where computing resources are shared with multiple processes. Hence, the field programmable gate array (FPGA) was introduced for a wave propagation imaging method in order to obtain extreme processing time reduction. An FPGA board was used for the design, implementing post-processing ultrasonic wave propagation imaging (UWPI). The results were compared with the conventional system and considerable improvement was observed, with at least 78% (scanning of 100x100mm{sup 2} with 0.5 mm interval) to 87.5% (scanning of 200x200mm{sup 2} with 0.5 mm interval) less processing time, strengthening the claim for the research. This new concept to implement FPGA technology into the UPI system will act as a break-through technology for full-scale automatic inspection.

Using field programmable gate array hardware for the performance improvement of ultrasonic wave propagation imaging system

International Nuclear Information System (INIS)

Shan, Jaffry Syed; Abbas, Syed Haider; Lee, Jung Ryul; Kang, Dong Hoon

2015-01-01

Recently, wave propagation imaging based on laser scanning-generated elastic waves has been intensively used for nondestructive inspection. However, the proficiency of the conventional software based system reduces when the scan area is large since the processing time increases significantly due to unavoidable processor multitasking, where computing resources are shared with multiple processes. Hence, the field programmable gate array (FPGA) was introduced for a wave propagation imaging method in order to obtain extreme processing time reduction. An FPGA board was used for the design, implementing post-processing ultrasonic wave propagation imaging (UWPI). The results were compared with the conventional system and considerable improvement was observed, with at least 78% (scanning of 100x100mm 2 with 0.5 mm interval) to 87.5% (scanning of 200x200mm 2 with 0.5 mm interval) less processing time, strengthening the claim for the research. This new concept to implement FPGA technology into the UPI system will act as a break-through technology for full-scale automatic inspection

FPGA-based digital convolution for wireless applications

CERN Document Server

Guan, Lei

2017-01-01

This book presents essential perspectives on digital convolutions in wireless communications systems and illustrates their corresponding efficient real-time field-programmable gate array (FPGA) implementations. Covering these digital convolutions from basic concept to vivid simulation/illustration, the book is also supplemented with MS PowerPoint presentations to aid in comprehension. FPGAs or generic all programmable devices will soon become widespread, serving as the “brains” of all types of real-time smart signal processing systems, like smart networks, smart homes and smart cities. The book examines digital convolution by bringing together the following main elements: the fundamental theory behind the mathematical formulae together with corresponding physical phenomena; virtualized algorithm simulation together with benchmark real-time FPGA implementations; and detailed, state-of-the-art case studies on wireless applications, including popular linear convolution in digital front ends (DFEs); nonlinear...

Field Programmable Gate Array-based I and C Safety System

International Nuclear Information System (INIS)

Kim, Hyun Jeong; Kim, Koh Eun; Kim, Young Geul; Kwon, Jong Soo

2014-01-01

Programmable Logic Controller (PLC)-based I and C safety system used in the operating nuclear power plants has the disadvantages of the Common Cause Failure (CCF), high maintenance costs and quick obsolescence, and then it is necessary to develop the other platform to replace the PLC. The Field Programmable Gate Array (FPGA)-based Instrument and Control (I and C) safety system is safer and more economical than Programmable Logic Controller (PLC)-based I and C safety system. Therefore, in the future, FPGA-based I and C safety system will be able to replace the PLC-based I and C safety system in the operating and the new nuclear power plants to get benefited from its safety and economic advantage. FPGA-based I and C safety system shall be implemented and verified by applying the related requirements to perform the safety function

Field Programmable Gate Array-based I and C Safety System

Energy Technology Data Exchange (ETDEWEB)

Kim, Hyun Jeong; Kim, Koh Eun; Kim, Young Geul; Kwon, Jong Soo [KEPCO, Daejeon (Korea, Republic of)

2014-08-15

Programmable Logic Controller (PLC)-based I and C safety system used in the operating nuclear power plants has the disadvantages of the Common Cause Failure (CCF), high maintenance costs and quick obsolescence, and then it is necessary to develop the other platform to replace the PLC. The Field Programmable Gate Array (FPGA)-based Instrument and Control (I and C) safety system is safer and more economical than Programmable Logic Controller (PLC)-based I and C safety system. Therefore, in the future, FPGA-based I and C safety system will be able to replace the PLC-based I and C safety system in the operating and the new nuclear power plants to get benefited from its safety and economic advantage. FPGA-based I and C safety system shall be implemented and verified by applying the related requirements to perform the safety function.

A new data acquisition and imaging system for nuclear microscopy based on a Field Programmable Gate Array card

International Nuclear Information System (INIS)

Bettiol, A.A.; Udalagama, C.; Watt, F.

2009-01-01

The introduction of the new Field Programmable Gate Array (FPGA) cards by National Instruments has made it possible for the first time to develop reconfigurable custom data acquisition hardware easily with the LabVIEW programming environment. Data acquisition issues such as precise timing for scanning and operating system latencies can now be easily overcome using this new technology because the data acquisition software is embedded in the FPGA chip on the card. In this paper we present the first results of the new data acquisition system developed at the Centre for Ion Beam Applications (CIBA), National University of Singapore using the new National Instruments cards in conjunction with rack mountable Wilkinson type ADCs.

Histopathological Breast Cancer Image Classification by Deep Neural Network Techniques Guided by Local Clustering.

Science.gov (United States)

Nahid, Abdullah-Al; Mehrabi, Mohamad Ali; Kong, Yinan

2018-01-01

Breast Cancer is a serious threat and one of the largest causes of death of women throughout the world. The identification of cancer largely depends on digital biomedical photography analysis such as histopathological images by doctors and physicians. Analyzing histopathological images is a nontrivial task, and decisions from investigation of these kinds of images always require specialised knowledge. However, Computer Aided Diagnosis (CAD) techniques can help the doctor make more reliable decisions. The state-of-the-art Deep Neural Network (DNN) has been recently introduced for biomedical image analysis. Normally each image contains structural and statistical information. This paper classifies a set of biomedical breast cancer images (BreakHis dataset) using novel DNN techniques guided by structural and statistical information derived from the images. Specifically a Convolutional Neural Network (CNN), a Long-Short-Term-Memory (LSTM), and a combination of CNN and LSTM are proposed for breast cancer image classification. Softmax and Support Vector Machine (SVM) layers have been used for the decision-making stage after extracting features utilising the proposed novel DNN models. In this experiment the best Accuracy value of 91.00% is achieved on the 200x dataset, the best Precision value 96.00% is achieved on the 40x dataset, and the best F -Measure value is achieved on both the 40x and 100x datasets.

Wavelet-enhanced convolutional neural network: a new idea in a deep learning paradigm.

Science.gov (United States)

Savareh, Behrouz Alizadeh; Emami, Hassan; Hajiabadi, Mohamadreza; Azimi, Seyed Majid; Ghafoori, Mahyar

2018-05-29

Manual brain tumor segmentation is a challenging task that requires the use of machine learning techniques. One of the machine learning techniques that has been given much attention is the convolutional neural network (CNN). The performance of the CNN can be enhanced by combining other data analysis tools such as wavelet transform. In this study, one of the famous implementations of CNN, a fully convolutional network (FCN), was used in brain tumor segmentation and its architecture was enhanced by wavelet transform. In this combination, a wavelet transform was used as a complementary and enhancing tool for CNN in brain tumor segmentation. Comparing the performance of basic FCN architecture against the wavelet-enhanced form revealed a remarkable superiority of enhanced architecture in brain tumor segmentation tasks. Using mathematical functions and enhancing tools such as wavelet transform and other mathematical functions can improve the performance of CNN in any image processing task such as segmentation and classification.

Identification of Village Building via Google Earth Images and Supervised Machine Learning Methods

Directory of Open Access Journals (Sweden)

Zhiling Guo

2016-03-01

Full Text Available In this study, a method based on supervised machine learning is proposed to identify village buildings from open high-resolution remote sensing images. We select Google Earth (GE RGB images to perform the classification in order to examine its suitability for village mapping, and investigate the feasibility of using machine learning methods to provide automatic classification in such fields. By analyzing the characteristics of GE images, we design different features on the basis of two kinds of supervised machine learning methods for classification: adaptive boosting (AdaBoost and convolutional neural networks (CNN. To recognize village buildings via their color and texture information, the RGB color features and a large number of Haar-like features in a local window are utilized in the AdaBoost method; with multilayer trained networks based on gradient descent algorithms and back propagation, CNN perform the identification by mining deeper information from buildings and their neighborhood. Experimental results from the testing area at Savannakhet province in Laos show that our proposed AdaBoost method achieves an overall accuracy of 96.22% and the CNN method is also competitive with an overall accuracy of 96.30%.

Discrimination of Oil Slicks and Lookalikes in Polarimetric SAR Images Using CNN.

Science.gov (United States)

Guo, Hao; Wu, Danni; An, Jubai

2017-08-09

Oil slicks and lookalikes (e.g., plant oil and oil emulsion) all appear as dark areas in polarimetric Synthetic Aperture Radar (SAR) images and are highly heterogeneous, so it is very difficult to use a single feature that can allow classification of dark objects in polarimetric SAR images as oil slicks or lookalikes. We established multi-feature fusion to support the discrimination of oil slicks and lookalikes. In the paper, simple discrimination analysis is used to rationalize a preferred features subset. The features analyzed include entropy, alpha, and Single-bounce Eigenvalue Relative Difference (SERD) in the C-band polarimetric mode. We also propose a novel SAR image discrimination method for oil slicks and lookalikes based on Convolutional Neural Network (CNN). The regions of interest are selected as the training and testing samples for CNN on the three kinds of polarimetric feature images. The proposed method is applied to a training data set of 5400 samples, including 1800 crude oil, 1800 plant oil, and 1800 oil emulsion samples. In the end, the effectiveness of the method is demonstrated through the analysis of some experimental results. The classification accuracy obtained using 900 samples of test data is 91.33%. It is here observed that the proposed method not only can accurately identify the dark spots on SAR images but also verify the ability of the proposed algorithm to classify unstructured features.

Event management for large scale event-driven digital hardware spiking neural networks.

Science.gov (United States)

Caron, Louis-Charles; D'Haene, Michiel; Mailhot, Frédéric; Schrauwen, Benjamin; Rouat, Jean

2013-09-01

The interest in brain-like computation has led to the design of a plethora of innovative neuromorphic systems. Individually, spiking neural networks (SNNs), event-driven simulation and digital hardware neuromorphic systems get a lot of attention. Despite the popularity of event-driven SNNs in software, very few digital hardware architectures are found. This is because existing hardware solutions for event management scale badly with the number of events. This paper introduces the structured heap queue, a pipelined digital hardware data structure, and demonstrates its suitability for event management. The structured heap queue scales gracefully with the number of events, allowing the efficient implementation of large scale digital hardware event-driven SNNs. The scaling is linear for memory, logarithmic for logic resources and constant for processing time. The use of the structured heap queue is demonstrated on a field-programmable gate array (FPGA) with an image segmentation experiment and a SNN of 65,536 neurons and 513,184 synapses. Events can be processed at the rate of 1 every 7 clock cycles and a 406×158 pixel image is segmented in 200 ms. Copyright © 2013 Elsevier Ltd. All rights reserved.

CNN-coupled Humanoid Panoramic Annular Lens (PAL)-Optical System for Military Applications (Feasibility Study)

National Research Council Canada - National Science Library

Greguss, Pal

2002-01-01

...) and the CNN chip for a few military applications. A polar beam splitter will be placed immediately after the relay lens to obtain two image planes, one will be used by the existing 64X64 CNN-UM focal plane array processor chip...

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.

Development of a Universal Networked Timer at NSTX

International Nuclear Information System (INIS)

Sichta, P.; Dong, J.; Lawson, J.E.; Oliaro, G.; Wertenbaker, J.

2005-01-01

A new Timing and Synchronization System component, the Universal Networked Timer (UNT), is under development at the National Spherical Torus Experiment (NSTX). The UNT is a second-generation multifunction timing device that emulates the timing functionality and electrical interfaces originally provided by various CAMAC modules. Using Field Programmable Gate Array (FPGA) technology, each of the UNT's eight channels can be dynamically programmed to emulate a specific CAMAC module type. The timer is compatible with the existing NSTX timing and synchronization system and will also support a (future) clock system with extended performance. To assist system designers and collaborators, software will be written to integrate the UNT with EPICS, MDSplus, and LabVIEW. This paper will describe the timing capabilities, hardware design, programming/software support, and the current status of the Universal Networked Timer at NSTX

MIMO Fading Emulator Development with FPGA and Its Application to Performance Evaluation of Mobile Radio Systems

Directory of Open Access Journals (Sweden)

Yoshio Karasawa

2017-01-01

Full Text Available We present four new developments for a multiple-input multiple-output (MIMO over-the-air measurement system based on our previous studies. The first two developments relate to the channel model for multipath environment generation. One is a further simplification of the circuit configuration without performance degradation by reducing the number of delay generation units, which dominate the performance limit when implementing the circuit on a field-programmable gate array (FPGA. The other is to realize spatial correlation characteristics among the input ports on the transmission side, whereas the previously proposed channel model did not consider this correlation. The third development involves the details of implementing the MIMO fading emulator on an FPGA as a two-stage scheme. The fourth is the demonstration of application examples of the developed system.

Convolutional neural network-based classification system design with compressed wireless sensor network images.

Science.gov (United States)

Ahn, Jungmo; Park, JaeYeon; Park, Donghwan; Paek, Jeongyeup; Ko, JeongGil

2018-01-01

With the introduction of various advanced deep learning algorithms, initiatives for image classification systems have transitioned over from traditional machine learning algorithms (e.g., SVM) to Convolutional Neural Networks (CNNs) using deep learning software tools. A prerequisite in applying CNN to real world applications is a system that collects meaningful and useful data. For such purposes, Wireless Image Sensor Networks (WISNs), that are capable of monitoring natural environment phenomena using tiny and low-power cameras on resource-limited embedded devices, can be considered as an effective means of data collection. However, with limited battery resources, sending high-resolution raw images to the backend server is a burdensome task that has direct impact on network lifetime. To address this problem, we propose an energy-efficient pre- and post- processing mechanism using image resizing and color quantization that can significantly reduce the amount of data transferred while maintaining the classification accuracy in the CNN at the backend server. We show that, if well designed, an image in its highly compressed form can be well-classified with a CNN model trained in advance using adequately compressed data. Our evaluation using a real image dataset shows that an embedded device can reduce the amount of transmitted data by ∼71% while maintaining a classification accuracy of ∼98%. Under the same conditions, this process naturally reduces energy consumption by ∼71% compared to a WISN that sends the original uncompressed images.

Efficient universal computing architectures for decoding neural activity.

Directory of Open Access Journals (Sweden)

Benjamin I Rapoport

Full Text Available The ability to decode neural activity into meaningful control signals for prosthetic devices is critical to the development of clinically useful brain- machine interfaces (BMIs. Such systems require input from tens to hundreds of brain-implanted recording electrodes in order to deliver robust and accurate performance; in serving that primary function they should also minimize power dissipation in order to avoid damaging neural tissue; and they should transmit data wirelessly in order to minimize the risk of infection associated with chronic, transcutaneous implants. Electronic architectures for brain- machine interfaces must therefore minimize size and power consumption, while maximizing the ability to compress data to be transmitted over limited-bandwidth wireless channels. Here we present a system of extremely low computational complexity, designed for real-time decoding of neural signals, and suited for highly scalable implantable systems. Our programmable architecture is an explicit implementation of a universal computing machine emulating the dynamics of a network of integrate-and-fire neurons; it requires no arithmetic operations except for counting, and decodes neural signals using only computationally inexpensive logic operations. The simplicity of this architecture does not compromise its ability to compress raw neural data by factors greater than [Formula: see text]. We describe a set of decoding algorithms based on this computational architecture, one designed to operate within an implanted system, minimizing its power consumption and data transmission bandwidth; and a complementary set of algorithms for learning, programming the decoder, and postprocessing the decoded output, designed to operate in an external, nonimplanted unit. The implementation of the implantable portion is estimated to require fewer than 5000 operations per second. A proof-of-concept, 32-channel field-programmable gate array (FPGA implementation of this portion

Classification of mass and normal breast tissue: A convolution neural network classifier with spatial domain and texture images

International Nuclear Information System (INIS)

Sahiner, B.; Chan, H.P.; Petrick, N.; Helvie, M.A.; Adler, D.D.; Goodsitt, M.M.; Wei, D.

1996-01-01

The authors investigated the classification of regions of interest (ROI's) on mammograms as either mass or normal tissue using a convolution neural network (CNN). A CNN is a back-propagation neural network with two-dimensional (2-D) weight kernels that operate on images. A generalized, fast and stable implementation of the CNN was developed. The input images to the CNN were obtained form the ROI's using two techniques. The first technique employed averaging and subsampling. The second technique employed texture feature extraction methods applied to small subregions inside the ROI. Features computed over different subregions were arranged as texture images, which were subsequently used as CNN inputs. The effects of CNN architecture and texture feature parameters on classification accuracy were studied. Receiver operating characteristic (ROC) methodology was used to evaluate the classification accuracy. A data set consisting of 168 ROI's containing biopsy-proven masses and 504 ROI's containing normal breast tissue was extracted from 168 mammograms by radiologists experienced in mammography. This data set was used for training and testing the CNN. With the best combination of CNN architecture and texture feature parameters, the area under the test ROC curve reached 0.87, which corresponded to a true-positive fraction of 90% at a false positive fraction of 31%. The results demonstrate the feasibility of using a CNN for classification of masses and normal tissue on mammograms

Inspecting rapidly moving surfaces for small defects using CNN cameras

Science.gov (United States)

Blug, Andreas; Carl, Daniel; Höfler, Heinrich

2013-04-01

A continuous increase in production speed and manufacturing precision raises a demand for the automated detection of small image features on rapidly moving surfaces. An example are wire drawing processes where kilometers of cylindrical metal surfaces moving with 10 m/s have to be inspected for defects such as scratches, dents, grooves, or chatter marks with a lateral size of 100 μm in real time. Up to now, complex eddy current systems are used for quality control instead of line cameras, because the ratio between lateral feature size and surface speed is limited by the data transport between camera and computer. This bottleneck is avoided by "cellular neural network" (CNN) cameras which enable image processing directly on the camera chip. This article reports results achieved with a demonstrator based on this novel analogue camera - computer system. The results show that computational speed and accuracy of the analogue computer system are sufficient to detect and discriminate the different types of defects. Area images with 176 x 144 pixels are acquired and evaluated in real time with frame rates of 4 to 10 kHz - depending on the number of defects to be detected. These frame rates correspond to equivalent line rates on line cameras between 360 and 880 kHz, a number far beyond the available features. Using the relation between lateral feature size and surface speed as a figure of merit, the CNN based system outperforms conventional image processing systems by an order of magnitude.

Failure mode taxonomy for assessing the reliability of Field Programmable Gate Array based Instrumentation and Control systems

International Nuclear Information System (INIS)

McNelles, Phillip; Zeng, Zhao Chang; Renganathan, Guna; Chirila, Marius; Lu, Lixuan

2017-01-01

Highlights: • The use FPGAs in I&C systems in Nuclear Power Plants is an important issue (IAEA). • OECD-NEA published a failure mode taxonomy for software-based digital I&C systems. • This paper extends the OECD-NEA taxonomy to model FPGA-based systems. • FPGA failure modes, failure effects, uncovering methods are categorized/described. • Provides an example of modelling an FPGA-Based RTS/ESFAS using the FPGA taxonomy. - Abstract: Field Programmable Gate Arrays (FPGAs) are a form of programmable digital hardware configured to perform digital logic functions. This configuration (programming) is performed using Hardware Description Language (HDL), making FPGAs a form of HDL Programmed Device (HPD). In the nuclear field, FPGAs have seen use in upgrades and replacements of obsolete Instrumentation and Control (I&C) systems. This paper expands upon previous work that resulted in extensive FPGA failure mode data, to allow for the application of the OECD-NEA failure modes taxonomy. The OECD-NEA taxonomy presented a method to model digital (software-based) I&C systems, based on the hardware and software failure modes, failure uncovering effects and levels of abstraction, using a Reactor Trip System/Engineering Safety Feature Actuation System (RTS/ESFAS) as an example system. To create the FPGA taxonomy, this paper presents an additional “sub-component” level of abstraction, to demonstrate the effect of the FPGA failure modes and failure categories on an FPGA-based system. The proposed FPGA taxonomy is based on the FPGA failure modes, failure categories, failure effects and uncovering situations. The FPGA taxonomy is applied to the RTS/ESFAS test system, to demonstrate the effects of the anticipated FPGA failure modes on a digital I&C system, and to provide a modelling example for this proposed taxonomy.

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.

Development of field programmable gate array–based encryption module to mitigate man-in-the-middle attack for nuclear power plant data communication network

Directory of Open Access Journals (Sweden)

Mohamed Abdallah Elakrat

2018-06-01

Full Text Available This article presents a security module based on a field programmable gate array (FPGA to mitigate man-in-the-middle cyber attacks. Nowadays, the FPGA is considered to be the state of the art in nuclear power plants I&C systems due to its flexibility, reconfigurability, and maintainability of the FPGA technology; it also provides acceptable solutions for embedded computing applications that require cybersecurity. The proposed FPGA-based security module is developed to mitigate information-gathering attacks, which can be made by gaining physical access to the network, e.g., a man-in-the-middle attack, using a cryptographic process to ensure data confidentiality and integrity and prevent injecting malware or malicious data into the critical digital assets of a nuclear power plant data communication system. A model-based system engineering approach is applied. System requirements analysis and enhanced function flow block diagrams are created and simulated using CORE9 to compare the performance of the current and developed systems. Hardware description language code for encryption and serial communication is developed using Vivado Design Suite 2017.2 as a programming tool to run the system synthesis and implementation for performance simulation and design verification. Simple windows are developed using Java for physical testing and communication between a personal computer and the FPGA. Keywords: AES-128, Cyber Security, Encryption, Field Programmable Gate Array, I&C

Multi-stream CNN: Learning representations based on human-related regions for action recognition

NARCIS (Netherlands)

Tu, Zhigang; Xie, Wei; Qin, Qianqing; Poppe, R.W.; Veltkamp, R.C.; Li, Baoxin; Yuan, Junsong

2018-01-01

The most successful video-based human action recognition methods rely on feature representations extracted using Convolutional Neural Networks (CNNs). Inspired by the two-stream network (TS-Net), we propose a multi-stream Convolutional Neural Network (CNN) architecture to recognize human actions. We

Generalized synthetic aperture radar automatic target recognition by convolutional neural network with joint use of two-dimensional principal component analysis and support vector machine

Science.gov (United States)

Zheng, Ce; Jiang, Xue; Liu, Xingzhao

2017-10-01

Convolutional neural network (CNN), as a vital part of the deep learning research field, has shown powerful potential for automatic target recognition (ATR) of synthetic aperture radar (SAR). However, the high complexity caused by the deep structure of CNN makes it difficult to generalize. An improved form of CNN with higher generalization capability and less probability of overfitting, which further improves the efficiency and robustness of the SAR ATR system, is proposed. The convolution layers of CNN are combined with a two-dimensional principal component analysis algorithm. Correspondingly, the kernel support vector machine is utilized as the classifier layer instead of the multilayer perceptron. The verification experiments are implemented using the moving and stationary target acquisition and recognition database, and the results validate the efficiency of the proposed method.

Design Methodology of an Equalizer for Unipolar Non Return to Zero Binary Signals in the Presence of Additive White Gaussian Noise Using a Time Delay Neural Network on a Field Programmable Gate Array

Science.gov (United States)

Pérez Suárez, Santiago T.; Travieso González, Carlos M.; Alonso Hernández, Jesús B.

2013-01-01

This article presents a design methodology for designing an artificial neural network as an equalizer for a binary signal. Firstly, the system is modelled in floating point format using Matlab. Afterward, the design is described for a Field Programmable Gate Array (FPGA) using fixed point format. The FPGA design is based on the System Generator from Xilinx, which is a design tool over Simulink of Matlab. System Generator allows one to design in a fast and flexible way. It uses low level details of the circuits and the functionality of the system can be fully tested. System Generator can be used to check the architecture and to analyse the effect of the number of bits on the system performance. Finally the System Generator design is compiled for the Xilinx Integrated System Environment (ISE) and the system is described using a hardware description language. In ISE the circuits are managed with high level details and physical performances are obtained. In the Conclusions section, some modifications are proposed to improve the methodology and to ensure portability across FPGA manufacturers.

Design Methodology of an Equalizer for Unipolar Non Return to Zero Binary Signals in the Presence of Additive White Gaussian Noise Using a Time Delay Neural Network on a Field Programmable Gate Array

Directory of Open Access Journals (Sweden)

Santiago T. Pérez Suárez

2013-12-01

Full Text Available This article presents a design methodology for designing an artificial neural network as an equalizer for a binary signal. Firstly, the system is modelled in floating point format using Matlab. Afterward, the design is described for a Field Programmable Gate Array (FPGA using fixed point format. The FPGA design is based on the System Generator from Xilinx, which is a design tool over Simulink of Matlab. System Generator allows one to design in a fast and flexible way. It uses low level details of the circuits and the functionality of the system can be fully tested. System Generator can be used to check the architecture and to analyse the effect of the number of bits on the system performance. Finally the System Generator design is compiled for the Xilinx Integrated System Environment (ISE and the system is described using a hardware description language. In ISE the circuits are managed with high level details and physical performances are obtained. In the Conclusions section, some modifications are proposed to improve the methodology and to ensure portability across FPGA manufacturers.

Phylogenetic convolutional neural networks in metagenomics.

Science.gov (United States)

Fioravanti, Diego; Giarratano, Ylenia; Maggio, Valerio; Agostinelli, Claudio; Chierici, Marco; Jurman, Giuseppe; Furlanello, Cesare

2018-03-08

Convolutional Neural Networks can be effectively used only when data are endowed with an intrinsic concept of neighbourhood in the input space, as is the case of pixels in images. We introduce here Ph-CNN, a novel deep learning architecture for the classification of metagenomics data based on the Convolutional Neural Networks, with the patristic distance defined on the phylogenetic tree being used as the proximity measure. The patristic distance between variables is used together with a sparsified version of MultiDimensional Scaling to embed the phylogenetic tree in a Euclidean space. Ph-CNN is tested with a domain adaptation approach on synthetic data and on a metagenomics collection of gut microbiota of 38 healthy subjects and 222 Inflammatory Bowel Disease patients, divided in 6 subclasses. Classification performance is promising when compared to classical algorithms like Support Vector Machines and Random Forest and a baseline fully connected neural network, e.g. the Multi-Layer Perceptron. Ph-CNN represents a novel deep learning approach for the classification of metagenomics data. Operatively, the algorithm has been implemented as a custom Keras layer taking care of passing to the following convolutional layer not only the data but also the ranked list of neighbourhood of each sample, thus mimicking the case of image data, transparently to the user.

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.

Design techniques for a stable operation of cryogenic field-programmable gate arrays

Science.gov (United States)

Homulle, Harald; Visser, Stefan; Patra, Bishnu; Charbon, Edoardo

2018-01-01

In this paper, we show how a deep-submicron field-programmable gate array (FPGA) can be operated more stably at extremely low temperatures through special firmware design techniques. Stability at low temperatures is limited through long power supply wires and reduced performance of various printed circuit board components commonly employed at room temperature. Extensive characterization of these components shows that the majority of decoupling capacitor types and voltage regulators are not well behaved at cryogenic temperatures, asking for an ad hoc solution to stabilize the FPGA supply voltage, especially for sensitive applications. Therefore, we have designed a firmware that enforces a constant power consumption, so as to stabilize the supply voltage in the interior of the FPGA. The FPGA is powered with a supply at several meters distance, causing significant resistive voltage drop and thus fluctuations on the local supply voltage. To achieve the stabilization, the variation in digital logic speed, which directly corresponds to changes in supply voltage, is constantly measured and corrected for through a tunable oscillator farm, implemented on the FPGA. The impact of the stabilization technique is demonstrated together with a reconfigurable analog-to-digital converter (ADC), completely implemented in the FPGA fabric and operating at 15 K. The ADC performance can be improved by at most 1.5 bits (effective number of bits) thanks to the more stable supply voltage. The method is versatile and robust, enabling seamless porting to other FPGA families and configurations.

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.

Classification of time-series images using deep convolutional neural networks

Science.gov (United States)

Hatami, Nima; Gavet, Yann; Debayle, Johan

2018-04-01

Convolutional Neural Networks (CNN) has achieved a great success in image recognition task by automatically learning a hierarchical feature representation from raw data. While the majority of Time-Series Classification (TSC) literature is focused on 1D signals, this paper uses Recurrence Plots (RP) to transform time-series into 2D texture images and then take advantage of the deep CNN classifier. Image representation of time-series introduces different feature types that are not available for 1D signals, and therefore TSC can be treated as texture image recognition task. CNN model also allows learning different levels of representations together with a classifier, jointly and automatically. Therefore, using RP and CNN in a unified framework is expected to boost the recognition rate of TSC. Experimental results on the UCR time-series classification archive demonstrate competitive accuracy of the proposed approach, compared not only to the existing deep architectures, but also to the state-of-the art TSC algorithms.

A locality aware convolutional neural networks accelerator

NARCIS (Netherlands)

Shi, R.; Xu, Z.; Sun, Z.; Peemen, M.C.J.; Li, A.; Corporaal, H.; Wu, D.

2015-01-01

The advantages of Convolutional Neural Networks (CNNs) with respect to traditional methods for visual pattern recognition have changed the field of machine vision. The main issue that hinders broad adoption of this technique is the massive computing workload in CNN that prevents real-time

Convolutional neural network features based change detection in satellite images

Science.gov (United States)

Mohammed El Amin, Arabi; Liu, Qingjie; Wang, Yunhong

2016-07-01

With the popular use of high resolution remote sensing (HRRS) satellite images, a huge research efforts have been placed on change detection (CD) problem. An effective feature selection method can significantly boost the final result. While hand-designed features have proven difficulties to design features that effectively capture high and mid-level representations, the recent developments in machine learning (Deep Learning) omit this problem by learning hierarchical representation in an unsupervised manner directly from data without human intervention. In this letter, we propose approaching the change detection problem from a feature learning perspective. A novel deep Convolutional Neural Networks (CNN) features based HR satellite images change detection method is proposed. The main guideline is to produce a change detection map directly from two images using a pretrained CNN. This method can omit the limited performance of hand-crafted features. Firstly, CNN features are extracted through different convolutional layers. Then, a concatenation step is evaluated after an normalization step, resulting in a unique higher dimensional feature map. Finally, a change map was computed using pixel-wise Euclidean distance. Our method has been validated on real bitemporal HRRS satellite images according to qualitative and quantitative analyses. The results obtained confirm the interest of the proposed method.

Evaluation of CNN architectures for gait recognition based on optical flow maps

OpenAIRE

Castro, F. M.; Marín-Jiménez, M.J.; Guil, N.; López-Tapia, S.; Pérez de la Blanca, N.

2017-01-01

This work targets people identification in video based on the way they walk (\\ie gait) by using deep learning architectures. We explore the use of convolutional neural networks (CNN) for learning high-level descriptors from low-level motion features (\\ie optical flow components). The low number of training samples for each subject and the use of a test set containing subjects different from the training ones makes the search of a good CNN architecture a challenging task. Universidad de Mál...

Convolutional Neural Network for Histopathological Analysis of Osteosarcoma.

Science.gov (United States)

Mishra, Rashika; Daescu, Ovidiu; Leavey, Patrick; Rakheja, Dinesh; Sengupta, Anita

2018-03-01

Pathologists often deal with high complexity and sometimes disagreement over osteosarcoma tumor classification due to cellular heterogeneity in the dataset. Segmentation and classification of histology tissue in H&E stained tumor image datasets is a challenging task because of intra-class variations, inter-class similarity, crowded context, and noisy data. In recent years, deep learning approaches have led to encouraging results in breast cancer and prostate cancer analysis. In this article, we propose convolutional neural network (CNN) as a tool to improve efficiency and accuracy of osteosarcoma tumor classification into tumor classes (viable tumor, necrosis) versus nontumor. The proposed CNN architecture contains eight learned layers: three sets of stacked two convolutional layers interspersed with max pooling layers for feature extraction and two fully connected layers with data augmentation strategies to boost performance. The use of a neural network results in higher accuracy of average 92% for the classification. We compare the proposed architecture with three existing and proven CNN architectures for image classification: AlexNet, LeNet, and VGGNet. We also provide a pipeline to calculate percentage necrosis in a given whole slide image. We conclude that the use of neural networks can assure both high accuracy and efficiency in osteosarcoma classification.

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

OpenAIRE

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

2015-01-01

State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN 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 simultan...

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.

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.

Field programmable gate array-assigned complex-valued computation and its limits

Energy Technology Data Exchange (ETDEWEB)

Bernard-Schwarz, Maria, E-mail: maria.bernardschwarz@ni.com [National Instruments, Ganghoferstrasse 70b, 80339 Munich (Germany); Institute of Applied Physics, TU Wien, Wiedner Hauptstrasse 8, 1040 Wien (Austria); Zwick, Wolfgang; Klier, Jochen [National Instruments, Ganghoferstrasse 70b, 80339 Munich (Germany); Wenzel, Lothar [National Instruments, 11500 N MOPac Expy, Austin, Texas 78759 (United States); Gröschl, Martin [Institute of Applied Physics, TU Wien, Wiedner Hauptstrasse 8, 1040 Wien (Austria)

2014-09-15

We discuss how leveraging Field Programmable Gate Array (FPGA) technology as part of a high performance computing platform reduces latency to meet the demanding real time constraints of a quantum optics simulation. Implementations of complex-valued operations using fixed point numeric on a Virtex-5 FPGA compare favorably to more conventional solutions on a central processing unit. Our investigation explores the performance of multiple fixed point options along with a traditional 64 bits floating point version. With this information, the lowest execution times can be estimated. Relative error is examined to ensure simulation accuracy is maintained.

Artificial neural network for bubbles pattern recognition on the images

International Nuclear Information System (INIS)

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

2016-01-01

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. (paper)

Performance evaluation of coherent Ising machines against classical neural networks

Science.gov (United States)

Haribara, Yoshitaka; Ishikawa, Hitoshi; Utsunomiya, Shoko; Aihara, Kazuyuki; Yamamoto, Yoshihisa

2017-12-01

The coherent Ising machine is expected to find a near-optimal solution in various combinatorial optimization problems, which has been experimentally confirmed with optical parametric oscillators and a field programmable gate array circuit. The similar mathematical models were proposed three decades ago by Hopfield et al in the context of classical neural networks. In this article, we compare the computational performance of both models.

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%.

Fusing Panchromatic and SWIR Bands Based on Cnn - a Preliminary Study Over WORLDVIEW-3 Datasets

Science.gov (United States)

Guo, M.; Ma, H.; Bao, Y.; Wang, L.

2018-04-01

The traditional fusion methods are based on the fact that the spectral ranges of the Panchromatic (PAN) and multispectral bands (MS) are almost overlapping. In this paper, we propose a new pan-sharpening method for the fusion of PAN and SWIR (short-wave infrared) bands, whose spectral coverages are not overlapping. This problem is addressed with a convolutional neural network (CNN), which is trained by WorldView-3 dataset. CNN can learn the complex relationship among bands, and thus alleviate spectral distortion. Consequently, in our network, we use the simple three-layer basic architecture with 16 × 16 kernels to conduct the experiment. Every layer use different receptive field. The first two layers compute 512 feature maps by using the 16 × 16 and 1 × 1 receptive field respectively and the third layer with a 8 × 8 receptive field. The fusion results are optimized by continuous training. As for assessment, four evaluation indexes including Entropy, CC, SAM and UIQI are selected built on subjective visual effect and quantitative evaluation. The preliminary experimental results demonstrate that the fusion algorithms can effectively enhance the spatial information. Unfortunately, the fusion image has spectral distortion, it cannot maintain the spectral information of the SWIR image.

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.

Dimensionality-varied deep convolutional neural network for spectral-spatial classification of hyperspectral data

Science.gov (United States)

Qu, Haicheng; Liang, Xuejian; Liang, Shichao; Liu, Wanjun

2018-01-01

Many methods of hyperspectral image classification have been proposed recently, and the convolutional neural network (CNN) achieves outstanding performance. However, spectral-spatial classification of CNN requires an excessively large model, tremendous computations, and complex network, and CNN is generally unable to use the noisy bands caused by water-vapor absorption. A dimensionality-varied CNN (DV-CNN) is proposed to address these issues. There are four stages in DV-CNN and the dimensionalities of spectral-spatial feature maps vary with the stages. DV-CNN can reduce the computation and simplify the structure of the network. All feature maps are processed by more kernels in higher stages to extract more precise features. DV-CNN also improves the classification accuracy and enhances the robustness to water-vapor absorption bands. The experiments are performed on data sets of Indian Pines and Pavia University scene. The classification performance of DV-CNN is compared with state-of-the-art methods, which contain the variations of CNN, traditional, and other deep learning methods. The experiment of performance analysis about DV-CNN itself is also carried out. The experimental results demonstrate that DV-CNN outperforms state-of-the-art methods for spectral-spatial classification and it is also robust to water-vapor absorption bands. Moreover, reasonable parameters selection is effective to improve classification accuracy.

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...

Agile convolutional neural network for pulmonary nodule classification using CT images.

Science.gov (United States)

Zhao, Xinzhuo; Liu, Liyao; Qi, Shouliang; Teng, Yueyang; Li, Jianhua; Qian, Wei

2018-04-01

To distinguish benign from malignant pulmonary nodules using CT images is critical for their precise diagnosis and treatment. A new Agile convolutional neural network (CNN) framework is proposed to conquer the challenges of a small-scale medical image database and the small size of the nodules, and it improves the performance of pulmonary nodule classification using CT images. A hybrid CNN of LeNet and AlexNet is constructed through combining the layer settings of LeNet and the parameter settings of AlexNet. A dataset with 743 CT image nodule samples is built up based on the 1018 CT scans of LIDC to train and evaluate the Agile CNN model. Through adjusting the parameters of the kernel size, learning rate, and other factors, the effect of these parameters on the performance of the CNN model is investigated, and an optimized setting of the CNN is obtained finally. After finely optimizing the settings of the CNN, the estimation accuracy and the area under the curve can reach 0.822 and 0.877, respectively. The accuracy of the CNN is significantly dependent on the kernel size, learning rate, training batch size, dropout, and weight initializations. The best performance is achieved when the kernel size is set to [Formula: see text], the learning rate is 0.005, the batch size is 32, and dropout and Gaussian initialization are used. This competitive performance demonstrates that our proposed CNN framework and the optimization strategy of the CNN parameters are suitable for pulmonary nodule classification characterized by small medical datasets and small targets. The classification model might help diagnose and treat pulmonary nodules effectively.

improvement of digital image watermarking techniques based on FPGA implementation

International Nuclear Information System (INIS)

EL-Hadedy, M.E

2006-01-01

digital watermarking provides the ownership of a piece of digital data by marking the considered data invisibly or visibly. this can be used to protect several types of multimedia objects such as audio, text, image and video. this thesis demonstrates the different types of watermarking techniques such as (discrete cosine transform (DCT) and discrete wavelet transform (DWT) and their characteristics. then, it classifies these techniques declaring their advantages and disadvantages. an improved technique with distinguished features, such as peak signal to noise ratio ( PSNR) and similarity ratio (SR) has been introduced. the modified technique has been compared with the other techniques by measuring heir robustness against differ attacks. finally, field programmable gate arrays (FPGA) based implementation and comparison, for the proposed watermarking technique have been presented and discussed

Design of acoustic logging signal source of imitation based on field programmable gate array

Science.gov (United States)

Zhang, K.; Ju, X. D.; Lu, J. Q.; Men, B. Y.

2014-08-01

An acoustic logging signal source of imitation is designed and realized, based on the Field Programmable Gate Array (FPGA), to improve the efficiency of examining and repairing acoustic logging tools during research and field application, and to inspect and verify acoustic receiving circuits and corresponding algorithms. The design of this signal source contains hardware design and software design,and the hardware design uses an FPGA as the control core. Four signals are made first by reading the Random Access Memory (RAM) data which are inside the FPGA, then dealing with the data by digital to analog conversion, amplification, smoothing and so on. Software design uses VHDL, a kind of hardware description language, to program the FPGA. Experiments illustrate that the ratio of signal to noise for the signal source is high, the waveforms are stable, and also its functions of amplitude adjustment, frequency adjustment and delay adjustment are in accord with the characteristics of real acoustic logging waveforms. These adjustments can be used to imitate influences on sonic logging received waveforms caused by many kinds of factors such as spacing and span of acoustic tools, sonic speeds of different layers and fluids, and acoustic attenuations of different cementation planes.

Parallel Fixed Point Implementation of a Radial Basis Function Network in an FPGA

Directory of Open Access Journals (Sweden)

Alisson C. D. de Souza

2014-09-01

Full Text Available This paper proposes a parallel fixed point radial basis function (RBF artificial neural network (ANN, implemented in a field programmable gate array (FPGA trained online with a least mean square (LMS algorithm. The processing time and occupied area were analyzed for various fixed point formats. The problems of precision of the ANN response for nonlinear classification using the XOR gate and interpolation using the sine function were also analyzed in a hardware implementation. The entire project was developed using the System Generator platform (Xilinx, with a Virtex-6 xc6vcx240t-1ff1156 as the target FPGA.

Understanding the Convolutional Neural Networks with Gradient Descent and Backpropagation

Science.gov (United States)

Zhou, XueFei

2018-04-01

With the development of computer technology, the applications of machine learning are more and more extensive. And machine learning is providing endless opportunities to develop new applications. One of those applications is image recognition by using Convolutional Neural Networks (CNNs). CNN is one of the most common algorithms in image recognition. It is significant to understand its theory and structure for every scholar who is interested in this field. CNN is mainly used in computer identification, especially in voice, text recognition and other aspects of the application. It utilizes hierarchical structure with different layers to accelerate computing speed. In addition, the greatest features of CNNs are the weight sharing and dimension reduction. And all of these consolidate the high effectiveness and efficiency of CNNs with idea computing speed and error rate. With the help of other learning altruisms, CNNs could be used in several scenarios for machine learning, especially for deep learning. Based on the general introduction to the background and the core solution CNN, this paper is going to focus on summarizing how Gradient Descent and Backpropagation work, and how they contribute to the high performances of CNNs. Also, some practical applications will be discussed in the following parts. The last section exhibits the conclusion and some perspectives of future work.

DeepX: Deep Learning Accelerator for Restricted Boltzmann Machine Artificial Neural Networks.

Science.gov (United States)

Kim, Lok-Won

2018-05-01

Although there have been many decades of research and commercial presence on high performance general purpose processors, there are still many applications that require fully customized hardware architectures for further computational acceleration. Recently, deep learning has been successfully used to learn in a wide variety of applications, but their heavy computation demand has considerably limited their practical applications. This paper proposes a fully pipelined acceleration architecture to alleviate high computational demand of an artificial neural network (ANN) which is restricted Boltzmann machine (RBM) ANNs. The implemented RBM ANN accelerator (integrating network size, using 128 input cases per batch, and running at a 303-MHz clock frequency) integrated in a state-of-the art field-programmable gate array (FPGA) (Xilinx Virtex 7 XC7V-2000T) provides a computational performance of 301-billion connection-updates-per-second and about 193 times higher performance than a software solution running on general purpose processors. Most importantly, the architecture enables over 4 times (12 times in batch learning) higher performance compared with a previous work when both are implemented in an FPGA device (XC2VP70).

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

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

2018-07-01

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.

Empirical Mode Decomposition and Neural Networks on FPGA for Fault Diagnosis in Induction Motors

Directory of Open Access Journals (Sweden)

David Camarena-Martinez

2014-01-01

Full Text Available Nowadays, many industrial applications require online systems that combine several processing techniques in order to offer solutions to complex problems as the case of detection and classification of multiple faults in induction motors. In this work, a novel digital structure to implement the empirical mode decomposition (EMD for processing nonstationary and nonlinear signals using the full spline-cubic function is presented; besides, it is combined with an adaptive linear network (ADALINE-based frequency estimator and a feed forward neural network (FFNN-based classifier to provide an intelligent methodology for the automatic diagnosis during the startup transient of motor faults such as: one and two broken rotor bars, bearing defects, and unbalance. Moreover, the overall methodology implementation into a field-programmable gate array (FPGA allows an online and real-time operation, thanks to its parallelism and high-performance capabilities as a system-on-a-chip (SoC solution. The detection and classification results show the effectiveness of the proposed fused techniques; besides, the high precision and minimum resource usage of the developed digital structures make them a suitable and low-cost solution for this and many other industrial applications.

Empirical Mode Decomposition and Neural Networks on FPGA for Fault Diagnosis in Induction Motors

Science.gov (United States)

Garcia-Perez, Arturo; Osornio-Rios, Roque Alfredo; Romero-Troncoso, Rene de Jesus

2014-01-01

Nowadays, many industrial applications require online systems that combine several processing techniques in order to offer solutions to complex problems as the case of detection and classification of multiple faults in induction motors. In this work, a novel digital structure to implement the empirical mode decomposition (EMD) for processing nonstationary and nonlinear signals using the full spline-cubic function is presented; besides, it is combined with an adaptive linear network (ADALINE)-based frequency estimator and a feed forward neural network (FFNN)-based classifier to provide an intelligent methodology for the automatic diagnosis during the startup transient of motor faults such as: one and two broken rotor bars, bearing defects, and unbalance. Moreover, the overall methodology implementation into a field-programmable gate array (FPGA) allows an online and real-time operation, thanks to its parallelism and high-performance capabilities as a system-on-a-chip (SoC) solution. The detection and classification results show the effectiveness of the proposed fused techniques; besides, the high precision and minimum resource usage of the developed digital structures make them a suitable and low-cost solution for this and many other industrial applications. PMID:24678281

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

A digital correlator upgrade for the Arcminute MicroKelvin Imager

Science.gov (United States)

Hickish, Jack; Razavi-Ghods, Nima; Perrott, Yvette C.; Titterington, David J.; Carey, Steve H.; Scott, Paul F.; Grainge, Keith J. B.; Scaife, Anna M. M.; Alexander, Paul; Saunders, Richard D. E.; Crofts, Mike; Javid, Kamran; Rumsey, Clare; Jin, Terry Z.; Ely, John A.; Shaw, Clive; Northrop, Ian G.; Pooley, Guy; D'Alessandro, Robert; Doherty, Peter; Willatt, Greg P.

2018-04-01

The Arcminute Microkelvin Imager (AMI) telescopes located at the Mullard Radio Astronomy Observatory near Cambridge have been significantly enhanced by the implementation of a new digital correlator with 1.2 MHz spectral resolution. This system has replaced a 750-MHz resolution analogue lag-based correlator, and was designed to mitigate the effects of radio frequency interference, particularly that from geostationary satellites which are visible from the AMI site when observing at low declinations. The upgraded instrument consists of 18 ROACH2 Field Programmable Gate Array platforms used to implement a pair of real-time FX correlators - one for each of AMI's two arrays. The new system separates the down-converted RF baseband signal from each AMI receiver into two sub-bands, each of which are filtered to a width of 2.3 GHz and digitized at 5-Gsps with 8 bits of precision. These digital data streams are filtered into 2048 frequency channels and cross-correlated using FPGA hardware, with a commercial 10 Gb Ethernet switch providing high-speed data interconnect. Images formed using data from the new digital correlator show over an order of magnitude improvement in dynamic range over the previous system. The ability to observe at low declinations has also been significantly improved.

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.

A novel deep learning-based approach to high accuracy breast density estimation in digital mammography

Science.gov (United States)

Ahn, Chul Kyun; Heo, Changyong; Jin, Heongmin; Kim, Jong Hyo

2017-03-01

Mammographic breast density is a well-established marker for breast cancer risk. However, accurate measurement of dense tissue is a difficult task due to faint contrast and significant variations in background fatty tissue. This study presents a novel method for automated mammographic density estimation based on Convolutional Neural Network (CNN). A total of 397 full-field digital mammograms were selected from Seoul National University Hospital. Among them, 297 mammograms were randomly selected as a training set and the rest 100 mammograms were used for a test set. We designed a CNN architecture suitable to learn the imaging characteristic from a multitudes of sub-images and classify them into dense and fatty tissues. To train the CNN, not only local statistics but also global statistics extracted from an image set were used. The image set was composed of original mammogram and eigen-image which was able to capture the X-ray characteristics in despite of the fact that CNN is well known to effectively extract features on original image. The 100 test images which was not used in training the CNN was used to validate the performance. The correlation coefficient between the breast estimates by the CNN and those by the expert's manual measurement was 0.96. Our study demonstrated the feasibility of incorporating the deep learning technology into radiology practice, especially for breast density estimation. The proposed method has a potential to be used as an automated and quantitative assessment tool for mammographic breast density in routine practice.

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

OpenAIRE

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

2017-01-01

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 centr...

Extended LaSalle's Invariance Principle for Full-Range Cellular Neural Networks

Directory of Open Access Journals (Sweden)

Mauro Di Marco

2009-01-01

Full Text Available In several relevant applications to the solution of signal processing tasks in real time, a cellular neural network (CNN is required to be convergent, that is, each solution should tend toward some equilibrium point. The paper develops a Lyapunov method, which is based on a generalized version of LaSalle's invariance principle, for studying convergence and stability of the differential inclusions modeling the dynamics of the full-range (FR model of CNNs. The applicability of the method is demonstrated by obtaining a rigorous proof of convergence for symmetric FR-CNNs. The proof, which is a direct consequence of the fact that a symmetric FR-CNN admits a strict Lyapunov function, is much more simple than the corresponding proof of convergence for symmetric standard CNNs.

Increasing feasibility of the field-programmable gate array implementation of an iterative image registration using a kernel-warping algorithm

Science.gov (United States)

Nguyen, An Hung; Guillemette, Thomas; Lambert, Andrew J.; Pickering, Mark R.; Garratt, Matthew A.

2017-09-01

Image registration is a fundamental image processing technique. It is used to spatially align two or more images that have been captured at different times, from different sensors, or from different viewpoints. There have been many algorithms proposed for this task. The most common of these being the well-known Lucas-Kanade (LK) and Horn-Schunck approaches. However, the main limitation of these approaches is the computational complexity required to implement the large number of iterations necessary for successful alignment of the images. Previously, a multi-pass image interpolation algorithm (MP-I2A) was developed to considerably reduce the number of iterations required for successful registration compared with the LK algorithm. This paper develops a kernel-warping algorithm (KWA), a modified version of the MP-I2A, which requires fewer iterations to successfully register two images and less memory space for the field-programmable gate array (FPGA) implementation than the MP-I2A. These reductions increase feasibility of the implementation of the proposed algorithm on FPGAs with very limited memory space and other hardware resources. A two-FPGA system rather than single FPGA system is successfully developed to implement the KWA in order to compensate insufficiency of hardware resources supported by one FPGA, and increase parallel processing ability and scalability of the system.

Implementing a Microcontroller Watchdog with a Field-Programmable Gate Array (FPGA)

Science.gov (United States)

Straka, Bartholomew

2013-01-01

Reliability is crucial to safety. Redundancy of important system components greatly enhances reliability and hence safety. Field-Programmable Gate Arrays (FPGAs) are useful for monitoring systems and handling the logic necessary to keep them running with minimal interruption when individual components fail. A complete microcontroller watchdog with logic for failure handling can be implemented in a hardware description language (HDL.). HDL-based designs are vendor-independent and can be used on many FPGAs with low overhead.

Field programmable gate array reliability analysis using the dynamic flow graph methodology

Energy Technology Data Exchange (ETDEWEB)

McNelles, Phillip; Lu, Lixuan [Faculty of Energy Systems and Nuclear Science, University of Ontario Institute of Technology (UOIT), Ontario (Canada)

2016-10-15

Field programmable gate array (FPGA)-based systems are thought to be a practical option to replace certain obsolete instrumentation and control systems in nuclear power plants. An FPGA is a type of integrated circuit, which is programmed after being manufactured. FPGAs have some advantages over other electronic technologies, such as analog circuits, microprocessors, and Programmable Logic Controllers (PLCs), for nuclear instrumentation and control, and safety system applications. However, safety-related issues for FPGA-based systems remain to be verified. Owing to this, modeling FPGA-based systems for safety assessment has now become an important point of research. One potential methodology is the dynamic flowgraph methodology (DFM). It has been used for modeling software/hardware interactions in modern control systems. In this paper, FPGA logic was analyzed using DFM. Four aspects of FPGAs are investigated: the 'IEEE 1164 standard', registers (D flip-flops), configurable logic blocks, and an FPGA-based signal compensator. The ModelSim simulations confirmed that DFM was able to accurately model those four FPGA properties, proving that DFM has the potential to be used in the modeling of FPGA-based systems. Furthermore, advantages of DFM over traditional reliability analysis methods and FPGA simulators are presented, along with a discussion of potential issues with using DFM for FPGA-based system modeling.

Recurrent Neural Networks to Correct Satellite Image Classification Maps

Science.gov (United States)

Maggiori, Emmanuel; Charpiat, Guillaume; Tarabalka, Yuliya; Alliez, Pierre

2017-09-01

While initially devised for image categorization, convolutional neural networks (CNNs) are being increasingly used for the pixelwise semantic labeling of images. However, the proper nature of the most common CNN architectures makes them good at recognizing but poor at localizing objects precisely. This problem is magnified in the context of aerial and satellite image labeling, where a spatially fine object outlining is of paramount importance. Different iterative enhancement algorithms have been presented in the literature to progressively improve the coarse CNN outputs, seeking to sharpen object boundaries around real image edges. However, one must carefully design, choose and tune such algorithms. Instead, our goal is to directly learn the iterative process itself. For this, we formulate a generic iterative enhancement process inspired from partial differential equations, and observe that it can be expressed as a recurrent neural network (RNN). Consequently, we train such a network from manually labeled data for our enhancement task. In a series of experiments we show that our RNN effectively learns an iterative process that significantly improves the quality of satellite image classification maps.

Change detection in multitemporal synthetic aperture radar images using dual-channel convolutional neural network

Science.gov (United States)

Liu, Tao; Li, Ying; Cao, Ying; Shen, Qiang

2017-10-01

This paper proposes a model of dual-channel convolutional neural network (CNN) that is designed for change detection in SAR images, in an effort to acquire higher detection accuracy and lower misclassification rate. This network model contains two parallel CNN channels, which can extract deep features from two multitemporal SAR images. For comparison and validation, the proposed method is tested along with other change detection algorithms on both simulated SAR images and real-world SAR images captured by different sensors. The experimental results demonstrate that the presented method outperforms the state-of-the-art techniques by a considerable margin.

3D Convolutional Neural Networks for Crop Classification with Multi-Temporal Remote Sensing Images

Directory of Open Access Journals (Sweden)

Shunping Ji

2018-01-01

Full Text Available This study describes a novel three-dimensional (3D convolutional neural networks (CNN based method that automatically classifies crops from spatio-temporal remote sensing images. First, 3D kernel is designed according to the structure of multi-spectral multi-temporal remote sensing data. Secondly, the 3D CNN framework with fine-tuned parameters is designed for training 3D crop samples and learning spatio-temporal discriminative representations, with the full crop growth cycles being preserved. In addition, we introduce an active learning strategy to the CNN model to improve labelling accuracy up to a required threshold with the most efficiency. Finally, experiments are carried out to test the advantage of the 3D CNN, in comparison to the two-dimensional (2D CNN and other conventional methods. Our experiments show that the 3D CNN is especially suitable in characterizing the dynamics of crop growth and outperformed the other mainstream methods.

3D multi-view convolutional neural networks for lung nodule classification

Science.gov (United States)

Kang, Guixia; Hou, Beibei; Zhang, Ningbo

2017-01-01

The 3D convolutional neural network (CNN) is able to make full use of the spatial 3D context information of lung nodules, and the multi-view strategy has been shown to be useful for improving the performance of 2D CNN in classifying lung nodules. In this paper, we explore the classification of lung nodules using the 3D multi-view convolutional neural networks (MV-CNN) with both chain architecture and directed acyclic graph architecture, including 3D Inception and 3D Inception-ResNet. All networks employ the multi-view-one-network strategy. We conduct a binary classification (benign and malignant) and a ternary classification (benign, primary malignant and metastatic malignant) on Computed Tomography (CT) images from Lung Image Database Consortium and Image Database Resource Initiative database (LIDC-IDRI). All results are obtained via 10-fold cross validation. As regards the MV-CNN with chain architecture, results show that the performance of 3D MV-CNN surpasses that of 2D MV-CNN by a significant margin. Finally, a 3D Inception network achieved an error rate of 4.59% for the binary classification and 7.70% for the ternary classification, both of which represent superior results for the corresponding task. We compare the multi-view-one-network strategy with the one-view-one-network strategy. The results reveal that the multi-view-one-network strategy can achieve a lower error rate than the one-view-one-network strategy. PMID:29145492

Design of acoustic logging signal source of imitation based on field programmable gate array

International Nuclear Information System (INIS)

Zhang, K; Ju, X D; Lu, J Q; Men, B Y

2014-01-01

An acoustic logging signal source of imitation is designed and realized, based on the Field Programmable Gate Array (FPGA), to improve the efficiency of examining and repairing acoustic logging tools during research and field application, and to inspect and verify acoustic receiving circuits and corresponding algorithms. The design of this signal source contains hardware design and software design,and the hardware design uses an FPGA as the control core. Four signals are made first by reading the Random Access Memory (RAM) data which are inside the FPGA, then dealing with the data by digital to analog conversion, amplification, smoothing and so on. Software design uses VHDL, a kind of hardware description language, to program the FPGA. Experiments illustrate that the ratio of signal to noise for the signal source is high, the waveforms are stable, and also its functions of amplitude adjustment, frequency adjustment and delay adjustment are in accord with the characteristics of real acoustic logging waveforms. These adjustments can be used to imitate influences on sonic logging received waveforms caused by many kinds of factors such as spacing and span of acoustic tools, sonic speeds of different layers and fluids, and acoustic attenuations of different cementation planes. (paper)

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.

Classification of Land Cover and Land Use Based on Convolutional Neural Networks

Science.gov (United States)

Yang, Chun; Rottensteiner, Franz; Heipke, Christian

2018-04-01

Land cover describes the physical material of the earth's surface, whereas land use describes the socio-economic function of a piece of land. Land use information is typically collected in geospatial databases. As such databases become outdated quickly, an automatic update process is required. This paper presents a new approach to determine land cover and to classify land use objects based on convolutional neural networks (CNN). The input data are aerial images and derived data such as digital surface models. Firstly, we apply a CNN to determine the land cover for each pixel of the input image. We compare different CNN structures, all of them based on an encoder-decoder structure for obtaining dense class predictions. Secondly, we propose a new CNN-based methodology for the prediction of the land use label of objects from a geospatial database. In this context, we present a strategy for generating image patches of identical size from the input data, which are classified by a CNN. Again, we compare different CNN architectures. Our experiments show that an overall accuracy of up to 85.7 % and 77.4 % can be achieved for land cover and land use, respectively. The classification of land cover has a positive contribution to the classification of the land use classification.

Compact field programmable gate array-based pulse-sequencer and radio-frequency generator for experiments with trapped atoms

Energy Technology Data Exchange (ETDEWEB)

Pruttivarasin, Thaned, E-mail: thaned.pruttivarasin@riken.jp [Quantum Metrology Laboratory, RIKEN, Wako-shi, Saitama 351-0198 (Japan); Katori, Hidetoshi [Quantum Metrology Laboratory, RIKEN, Wako-shi, Saitama 351-0198 (Japan); Innovative Space-Time Project, ERATO, JST, Bunkyo-ku, Tokyo 113-8656 (Japan); Department of Applied Physics, Graduate School of Engineering, The University of Tokyo, Bunkyo-ku, Tokyo 113-8656 (Japan)

2015-11-15

We present a compact field-programmable gate array (FPGA) based pulse sequencer and radio-frequency (RF) generator suitable for experiments with cold trapped ions and atoms. The unit is capable of outputting a pulse sequence with at least 32 transistor-transistor logic (TTL) channels with a timing resolution of 40 ns and contains a built-in 100 MHz frequency counter for counting electrical pulses from a photo-multiplier tube. There are 16 independent direct-digital-synthesizers RF sources with fast (rise-time of ∼60 ns) amplitude switching and sub-mHz frequency tuning from 0 to 800 MHz.

A control system based on field programmable gate array for papermaking sewage treatment

International Nuclear Information System (INIS)

Zhang, Zi Sheng; Xie, Chang; Xiong, Yan Qing; Liu, Zhi Qiang; Li, Qing

2013-01-01

A sewage treatment control system is designed to improve the efficiency of papermaking wastewater treatment system. The automation control system is based on Field Programmable Gate Array (FPGA), coded with Very-High-Speed Integrate Circuit Hardware Description Language (VHDL), compiled and simulated with Quartus. In order to ensure the stability of the data used in FPGA, the data is collected through temperature sensors, water level sensor and online PH measurement system. The automatic control system is more sensitive, and both the treatment efficiency and processing power are increased. This work provides a new method for sewage treatment control.

Development of measurement system for radiation effect on static random access memory based field programmable gate array

International Nuclear Information System (INIS)

Yao Zhibin; He Baoping; Zhang Fengqi; Guo Hongxia; Luo Yinhong; Wang Yuanming; Zhang Keying

2009-01-01

Based on the detailed investigation in field programmable gate array(FPGA) radiation effects theory, a measurement system for radiation effects on static random access memory(SRAM)-based FPGA was developed. The testing principle of internal memory, function and power current was introduced. The hardware and software implement means of system were presented. Some important parameters for radiation effects on SRAM-based FPGA, such as configuration RAM upset section, block RAM upset section, function fault section and single event latchup section can be gained with this system. The transmission distance of the system can be over 50 m and the maximum number of tested gates can reach one million. (authors)

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.

Hyperspectral Image Classification With Markov Random Fields and a Convolutional Neural Network

Science.gov (United States)

Cao, Xiangyong; Zhou, Feng; Xu, Lin; Meng, Deyu; Xu, Zongben; Paisley, John

2018-05-01

This paper presents a new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework. First, we formulate the HSI classification problem from a Bayesian perspective. Then, we adopt a convolutional neural network (CNN) to learn the posterior class distributions using a patch-wise training strategy to better use the spatial information. Next, spatial information is further considered by placing a spatial smoothness prior on the labels. Finally, we iteratively update the CNN parameters using stochastic gradient decent (SGD) and update the class labels of all pixel vectors using an alpha-expansion min-cut-based algorithm. Compared with other state-of-the-art methods, the proposed classification method achieves better performance on one synthetic dataset and two benchmark HSI datasets in a number of experimental settings.

Three-Dimensional Terahertz Coded-Aperture Imaging Based on Matched Filtering and Convolutional Neural Network.

Science.gov (United States)

Chen, Shuo; Luo, Chenggao; Wang, Hongqiang; Deng, Bin; Cheng, Yongqiang; Zhuang, Zhaowen

2018-04-26

As a promising radar imaging technique, terahertz coded-aperture imaging (TCAI) can achieve high-resolution, forward-looking, and staring imaging by producing spatiotemporal independent signals with coded apertures. However, there are still two problems in three-dimensional (3D) TCAI. Firstly, the large-scale reference-signal matrix based on meshing the 3D imaging area creates a heavy computational burden, thus leading to unsatisfactory efficiency. Secondly, it is difficult to resolve the target under low signal-to-noise ratio (SNR). In this paper, we propose a 3D imaging method based on matched filtering (MF) and convolutional neural network (CNN), which can reduce the computational burden and achieve high-resolution imaging for low SNR targets. In terms of the frequency-hopping (FH) signal, the original echo is processed with MF. By extracting the processed echo in different spike pulses separately, targets in different imaging planes are reconstructed simultaneously to decompose the global computational complexity, and then are synthesized together to reconstruct the 3D target. Based on the conventional TCAI model, we deduce and build a new TCAI model based on MF. Furthermore, the convolutional neural network (CNN) is designed to teach the MF-TCAI how to reconstruct the low SNR target better. The experimental results demonstrate that the MF-TCAI achieves impressive performance on imaging ability and efficiency under low SNR. Moreover, the MF-TCAI has learned to better resolve the low-SNR 3D target with the help of CNN. In summary, the proposed 3D TCAI can achieve: (1) low-SNR high-resolution imaging by using MF; (2) efficient 3D imaging by downsizing the large-scale reference-signal matrix; and (3) intelligent imaging with CNN. Therefore, the TCAI based on MF and CNN has great potential in applications such as security screening, nondestructive detection, medical diagnosis, etc.

Applying Gradient Descent in Convolutional Neural Networks

Science.gov (United States)

Cui, Nan

2018-04-01

With the development of the integrated circuit and computer science, people become caring more about solving practical issues via information technologies. Along with that, a new subject called Artificial Intelligent (AI) comes up. One popular research interest of AI is about recognition algorithm. In this paper, one of the most common algorithms, Convolutional Neural Networks (CNNs) will be introduced, for image recognition. Understanding its theory and structure is of great significance for every scholar who is interested in this field. Convolution Neural Network is an artificial neural network which combines the mathematical method of convolution and neural network. The hieratical structure of CNN provides it reliable computer speed and reasonable error rate. The most significant characteristics of CNNs are feature extraction, weight sharing and dimension reduction. Meanwhile, combining with the Back Propagation (BP) mechanism and the Gradient Descent (GD) method, CNNs has the ability to self-study and in-depth learning. Basically, BP provides an opportunity for backwardfeedback for enhancing reliability and GD is used for self-training process. This paper mainly discusses the CNN and the related BP and GD algorithms, including the basic structure and function of CNN, details of each layer, the principles and features of BP and GD, and some examples in practice with a summary in the end.

Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images.

Science.gov (United States)

Wang, Hongkai; Zhou, Zongwei; Li, Yingci; Chen, Zhonghua; Lu, Peiou; Wang, Wenzhi; Liu, Wanyu; Yu, Lijuan

2017-12-01

This study aimed to compare one state-of-the-art deep learning method and four classical machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer (NSCLC) from 18 F-FDG PET/CT images. Another objective was to compare the discriminative power of the recently popular PET/CT texture features with the widely used diagnostic features such as tumor size, CT value, SUV, image contrast, and intensity standard deviation. The four classical machine learning methods included random forests, support vector machines, adaptive boosting, and artificial neural network. The deep learning method was the convolutional neural networks (CNN). The five methods were evaluated using 1397 lymph nodes collected from PET/CT images of 168 patients, with corresponding pathology analysis results as gold standard. The comparison was conducted using 10 times 10-fold cross-validation based on the criterion of sensitivity, specificity, accuracy (ACC), and area under the ROC curve (AUC). For each classical method, different input features were compared to select the optimal feature set. Based on the optimal feature set, the classical methods were compared with CNN, as well as with human doctors from our institute. For the classical methods, the diagnostic features resulted in 81~85% ACC and 0.87~0.92 AUC, which were significantly higher than the results of texture features. CNN's sensitivity, specificity, ACC, and AUC were 84, 88, 86, and 0.91, respectively. There was no significant difference between the results of CNN and the best classical method. The sensitivity, specificity, and ACC of human doctors were 73, 90, and 82, respectively. All the five machine learning methods had higher sensitivities but lower specificities than human doctors. The present study shows that the performance of CNN is not significantly different from the best classical methods and human doctors for classifying mediastinal lymph node metastasis of NSCLC from PET/CT images

Development of a protection system for research reactor based in Field Programmable Gate Array - FPGA; Desenvolvimento de sistema de protecao para reator nuclear de pesquisa baseado em Field Programmable Gate Array - FPGA

Energy Technology Data Exchange (ETDEWEB)

Martins, Roque Hudson da Silva

2016-07-01

This study presents a implementation purpose of a protection system for research nuclear reactors by using a programed device FPGA (Field Programmable Gate Array). As well as logic protection method involved on an automatic shutdown (TRIP) of a reactor, that ensure the security on such systems. These new control and operation mechanics are developed to guarantee that the security limits of a power plant are not exceeded, these mechanics can work isolated or in groups to safe guard the security levels. For this implementation to be completed, there will be presented the main aspects and concepts referred to protection systems, mostly about research nuclear reactors, with some applications terms exposed. The system proposed at this paper was developed following the VHDL (Very High Speed Integrated Circuits) hardware describing language, and the Modelsim software from Altera Software to program the automatic turning off routines, and hypothetical simulations for such. The results show that for every software application for supporting nuclear reactors, like security devices, they have to meet the IEC 60880 criteria. This paper have great importance, seeing that nuclear reactor security systems, are a basic element for ensure the reactor security. (author)

Divide and Conquer-Based 1D CNN Human Activity Recognition Using Test Data Sharpening.

Science.gov (United States)

Cho, Heeryon; Yoon, Sang Min

2018-04-01

Human Activity Recognition (HAR) aims to identify the actions performed by humans using signals collected from various sensors embedded in mobile devices. In recent years, deep learning techniques have further improved HAR performance on several benchmark datasets. In this paper, we propose one-dimensional Convolutional Neural Network (1D CNN) for HAR that employs a divide and conquer-based classifier learning coupled with test data sharpening. Our approach leverages a two-stage learning of multiple 1D CNN models; we first build a binary classifier for recognizing abstract activities, and then build two multi-class 1D CNN models for recognizing individual activities. We then introduce test data sharpening during prediction phase to further improve the activity recognition accuracy. While there have been numerous researches exploring the benefits of activity signal denoising for HAR, few researches have examined the effect of test data sharpening for HAR. We evaluate the effectiveness of our approach on two popular HAR benchmark datasets, and show that our approach outperforms both the two-stage 1D CNN-only method and other state of the art approaches.

Robust Vehicle Detection in Aerial Images Based on Cascaded Convolutional Neural Networks.

Science.gov (United States)

Zhong, Jiandan; Lei, Tao; Yao, Guangle

2017-11-24

Vehicle detection in aerial images is an important and challenging task. Traditionally, many target detection models based on sliding-window fashion were developed and achieved acceptable performance, but these models are time-consuming in the detection phase. Recently, with the great success of convolutional neural networks (CNNs) in computer vision, many state-of-the-art detectors have been designed based on deep CNNs. However, these CNN-based detectors are inefficient when applied in aerial image data due to the fact that the existing CNN-based models struggle with small-size object detection and precise localization. To improve the detection accuracy without decreasing speed, we propose a CNN-based detection model combining two independent convolutional neural networks, where the first network is applied to generate a set of vehicle-like regions from multi-feature maps of different hierarchies and scales. Because the multi-feature maps combine the advantage of the deep and shallow convolutional layer, the first network performs well on locating the small targets in aerial image data. Then, the generated candidate regions are fed into the second network for feature extraction and decision making. Comprehensive experiments are conducted on the Vehicle Detection in Aerial Imagery (VEDAI) dataset and Munich vehicle dataset. The proposed cascaded detection model yields high performance, not only in detection accuracy but also in detection speed.

[Computer aided diagnosis model for lung tumor based on ensemble convolutional neural network].

Science.gov (United States)

Wang, Yuanyuan; Zhou, Tao; Lu, Huiling; Wu, Cuiying; Yang, Pengfei

2017-08-01

The convolutional neural network (CNN) could be used on computer-aided diagnosis of lung tumor with positron emission tomography (PET)/computed tomography (CT), which can provide accurate quantitative analysis to compensate for visual inertia and defects in gray-scale sensitivity, and help doctors diagnose accurately. Firstly, parameter migration method is used to build three CNNs (CT-CNN, PET-CNN, and PET/CT-CNN) for lung tumor recognition in CT, PET, and PET/CT image, respectively. Then, we aimed at CT-CNN to obtain the appropriate model parameters for CNN training through analysis the influence of model parameters such as epochs, batchsize and image scale on recognition rate and training time. Finally, three single CNNs are used to construct ensemble CNN, and then lung tumor PET/CT recognition was completed through relative majority vote method and the performance between ensemble CNN and single CNN was compared. The experiment results show that the ensemble CNN is better than single CNN on computer-aided diagnosis of lung tumor.

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

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.

A 45 ps time digitizer with a two-phase clock and dual-edge two-stage interpolation in a field programmable gate array device

Science.gov (United States)

Szplet, R.; Kalisz, J.; Jachna, Z.

2009-02-01

We present a time digitizer having 45 ps resolution, integrated in a field programmable gate array (FPGA) device. The time interval measurement is based on the two-stage interpolation method. A dual-edge two-phase interpolator is driven by the on-chip synthesized 250 MHz clock with precise phase adjustment. An improved dual-edge double synchronizer was developed to control the main counter. The nonlinearity of the digitizer's transfer characteristic is identified and utilized by the dedicated hardware code processor for the on-the-fly correction of the output data. Application of presented ideas has resulted in the measurement uncertainty of the digitizer below 70 ps RMS over the time interval ranging from 0 to 1 s. The use of the two-stage interpolation and a fast FIFO memory has allowed us to obtain the maximum measurement rate of five million measurements per second.

A 45 ps time digitizer with a two-phase clock and dual-edge two-stage interpolation in a field programmable gate array device

International Nuclear Information System (INIS)

Szplet, R; Kalisz, J; Jachna, Z

2009-01-01

We present a time digitizer having 45 ps resolution, integrated in a field programmable gate array (FPGA) device. The time interval measurement is based on the two-stage interpolation method. A dual-edge two-phase interpolator is driven by the on-chip synthesized 250 MHz clock with precise phase adjustment. An improved dual-edge double synchronizer was developed to control the main counter. The nonlinearity of the digitizer's transfer characteristic is identified and utilized by the dedicated hardware code processor for the on-the-fly correction of the output data. Application of presented ideas has resulted in the measurement uncertainty of the digitizer below 70 ps RMS over the time interval ranging from 0 to 1 s. The use of the two-stage interpolation and a fast FIFO memory has allowed us to obtain the maximum measurement rate of five million measurements per second

Image Encryption and Chaotic Cellular Neural Network

Science.gov (United States)

Peng, Jun; Zhang, Du

Machine learning has been playing an increasingly important role in information security and assurance. One of the areas of new applications is to design cryptographic systems by using chaotic neural network due to the fact that chaotic systems have several appealing features for information security applications. In this chapter, we describe a novel image encryption algorithm that is based on a chaotic cellular neural network. We start by giving an introduction to the concept of image encryption and its main technologies, and an overview of the chaotic cellular neural network. We then discuss the proposed image encryption algorithm in details, which is followed by a number of security analyses (key space analysis, sensitivity analysis, information entropy analysis and statistical analysis). The comparison with the most recently reported chaos-based image encryption algorithms indicates that the algorithm proposed in this chapter has a better security performance. Finally, we conclude the chapter with possible future work and application prospects of the chaotic cellular neural network in other information assurance and security areas.

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.

Field programmable gate array based reconfigurable scanning probe/optical microscope.

Science.gov (United States)

Nowak, Derek B; Lawrence, A J; Dzegede, Zechariah K; Hiester, Justin C; Kim, Cliff; Sánchez, Erik J

2011-10-01

The increasing popularity of nanometrology and nanospectroscopy has pushed researchers to develop complex new analytical systems. This paper describes the development of a platform on which to build a microscopy tool that will allow for flexibility of customization to suit research needs. The novelty of the described system lies in its versatility of capabilities. So far, one version of this microscope has allowed for successful near-field and far-field fluorescence imaging with single molecule detection sensitivity. This system is easily adapted for reflection, polarization (Kerr magneto-optical (MO)), Raman, super-resolution techniques, and other novel scanning probe imaging and spectroscopic designs. While collecting a variety of forms of optical images, the system can simultaneously monitor topographic information of a sample with an integrated tuning fork based shear force system. The instrument has the ability to image at room temperature and atmospheric pressure or under liquid. The core of the design is a field programmable gate array (FPGA) data acquisition card and a single, low cost computer to control the microscope with analog control circuitry using off-the-shelf available components. A detailed description of electronics, mechanical requirements, and software algorithms as well as examples of some different forms of the microscope developed so far are discussed.

Paediatric frontal chest radiograph screening with fine-tuned convolutional neural networks

CSIR Research Space (South Africa)

Gerrand, Jonathan D

2017-07-01

Full Text Available of fine-tuned convolutional neural networks (CNN). We use two popular CNN models that are pre-trained on a large natural image dataset and two distinct datasets containing paediatric and adult radiographs respectively. Evaluation is performed using a 5...

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).

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.

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.

FPGAs Emulate Microprocessors-A Successful Case for HFC NPP Digital I and C Upgrade

International Nuclear Information System (INIS)

Hsu, Allen; Crow, Ivan; Reese, Carl; Kim, Jong; Yang, Steve

2014-01-01

Field Programmable Gate Arrays (FPGAs), as programmable logic devices (PLDs) have gained a great deal of interests for implementing safety I and C applications in nuclear power plants (NPPs) largely owing to the FPGAs'potential advantage over the currently more common microprocessor-based digital I and C applications. First of all, FPGAs have adequate capabilities for most digital I and C applications in NPPs. Secondly, FPGAs provide products with longer lifetime, improve testability, and reduce the drift which occurs in analog-based systems, from hardware perspective. Thirdly, FPGAs, from software perspective, can be made simpler, less reliant on complex software such as operating systems, which should make FPGAs easier to qualify for nuclear safety applications. Fourthly, FPGAs are less vulnerable to cyber attacks when FPGAs implement the I and C systems that do not contain high-level, general purpose software that may be easily subjected to malicious modifications. Finally, FPGAs can bring cost reduction in an I and C digital upgrade because FPGAs can provide simpler licensing process than microprocessor-based digital I and C, and FPGAs can be implemented more efficiently. This paper will present one successful case for YGN Unit I and C upgrade using FPGA-based components to replace the obsolete Intel 8085 Microprocessor-based controllers. In this case, FPGAs emulated the process of the existing microprocessors and interpreted the execution of CPU processing. More than 160 of the FPGA-based SBC-01 controllers replacing the Intel 8085 Microprocessor-based Printed Circuit Boards have been installed and running successfully for safety I and C applications over the last five years. In this upgrade, the new FPGA-based controller board SBC-01 emulated the functions of Intel 8085 microprocessor correctly. It is a successful and cost-effective upgrade.vIn this paper, lifecycle design and implementation process and rigorous V and V activities that were used in the

FPGAs Emulate Microprocessors-A Successful Case for HFC NPP Digital I and C Upgrade

Energy Technology Data Exchange (ETDEWEB)

Hsu, Allen; Crow, Ivan; Reese, Carl; Kim, Jong; Yang, Steve [Doosan HF Controls Corp, Carrollton (United States)

2014-08-15

Field Programmable Gate Arrays (FPGAs), as programmable logic devices (PLDs) have gained a great deal of interests for implementing safety I and C applications in nuclear power plants (NPPs) largely owing to the FPGAs'potential advantage over the currently more common microprocessor-based digital I and C applications. First of all, FPGAs have adequate capabilities for most digital I and C applications in NPPs. Secondly, FPGAs provide products with longer lifetime, improve testability, and reduce the drift which occurs in analog-based systems, from hardware perspective. Thirdly, FPGAs, from software perspective, can be made simpler, less reliant on complex software such as operating systems, which should make FPGAs easier to qualify for nuclear safety applications. Fourthly, FPGAs are less vulnerable to cyber attacks when FPGAs implement the I and C systems that do not contain high-level, general purpose software that may be easily subjected to malicious modifications. Finally, FPGAs can bring cost reduction in an I and C digital upgrade because FPGAs can provide simpler licensing process than microprocessor-based digital I and C, and FPGAs can be implemented more efficiently. This paper will present one successful case for YGN Unit I and C upgrade using FPGA-based components to replace the obsolete Intel 8085 Microprocessor-based controllers. In this case, FPGAs emulated the process of the existing microprocessors and interpreted the execution of CPU processing. More than 160 of the FPGA-based SBC-01 controllers replacing the Intel 8085 Microprocessor-based Printed Circuit Boards have been installed and running successfully for safety I and C applications over the last five years. In this upgrade, the new FPGA-based controller board SBC-01 emulated the functions of Intel 8085 microprocessor correctly. It is a successful and cost-effective upgrade.vIn this paper, lifecycle design and implementation process and rigorous V and V activities that were used in the

CNN - en succes i krise

DEFF Research Database (Denmark)

Böss, Michael

1994-01-01

Om CNN og den krise, netværket hele tiden må bekæmpe og dække. Udgivelsesdato: 26. september......Om CNN og den krise, netværket hele tiden må bekæmpe og dække. Udgivelsesdato: 26. september...

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.

Programmable cellular arrays. Faults testing and correcting in cellular arrays

International Nuclear Information System (INIS)

Cercel, L.

1978-03-01

A review of some recent researches about programmable cellular arrays in computing and digital processing of information systems is presented, and includes both combinational and sequential arrays, with full arbitrary behaviour, or which can realize better implementations of specialized blocks as: arithmetic units, counters, comparators, control systems, memory blocks, etc. Also, the paper presents applications of cellular arrays in microprogramming, in implementing of a specialized computer for matrix operations, in modeling of universal computing systems. The last section deals with problems of fault testing and correcting in cellular arrays. (author)

Exploring the effects of transducer models when training convolutional neural networks to eliminate reflection artifacts in experimental photoacoustic images

Science.gov (United States)

Allman, Derek; Reiter, Austin; Bell, Muyinatu

2018-02-01

We previously proposed a method of removing reflection artifacts in photoacoustic images that uses deep learning. Our approach generally relies on using simulated photoacoustic channel data to train a convolutional neural network (CNN) that is capable of distinguishing sources from artifacts based on unique differences in their spatial impulse responses (manifested as depth-based differences in wavefront shapes). In this paper, we directly compare a CNN trained with our previous continuous transducer model to a CNN trained with an updated discrete acoustic receiver model that more closely matches an experimental ultrasound transducer. These two CNNs were trained with simulated data and tested on experimental data. The CNN trained using the continuous receiver model correctly classified 100% of sources and 70.3% of artifacts in the experimental data. In contrast, the CNN trained using the discrete receiver model correctly classified 100% of sources and 89.7% of artifacts in the experimental images. The 19.4% increase in artifact classification accuracy indicates that an acoustic receiver model that closely mimics the experimental transducer plays an important role in improving the classification of artifacts in experimental photoacoustic data. Results are promising for developing a method to display CNN-based images that remove artifacts in addition to only displaying network-identified sources as previously proposed.

Divide and Conquer-Based 1D CNN Human Activity Recognition Using Test Data Sharpening †

Science.gov (United States)

Yoon, Sang Min

2018-01-01

Human Activity Recognition (HAR) aims to identify the actions performed by humans using signals collected from various sensors embedded in mobile devices. In recent years, deep learning techniques have further improved HAR performance on several benchmark datasets. In this paper, we propose one-dimensional Convolutional Neural Network (1D CNN) for HAR that employs a divide and conquer-based classifier learning coupled with test data sharpening. Our approach leverages a two-stage learning of multiple 1D CNN models; we first build a binary classifier for recognizing abstract activities, and then build two multi-class 1D CNN models for recognizing individual activities. We then introduce test data sharpening during prediction phase to further improve the activity recognition accuracy. While there have been numerous researches exploring the benefits of activity signal denoising for HAR, few researches have examined the effect of test data sharpening for HAR. We evaluate the effectiveness of our approach on two popular HAR benchmark datasets, and show that our approach outperforms both the two-stage 1D CNN-only method and other state of the art approaches. PMID:29614767

Field Programmable Gate Array Failure Rate Estimation Guidelines for Launch Vehicle Fault Tree Models

Science.gov (United States)

Al Hassan, Mohammad; Novack, Steven D.; Hatfield, Glen S.; Britton, Paul

2017-01-01

Today's launch vehicles complex electronic and avionic systems heavily utilize the Field Programmable Gate Array (FPGA) integrated circuit (IC). FPGAs are prevalent ICs in communication protocols such as MIL-STD-1553B, and in control signal commands such as in solenoid/servo valves actuations. This paper will demonstrate guidelines to estimate FPGA failure rates for a launch vehicle, the guidelines will account for hardware, firmware, and radiation induced failures. The hardware contribution of the approach accounts for physical failures of the IC, FPGA memory and clock. The firmware portion will provide guidelines on the high level FPGA programming language and ways to account for software/code reliability growth. The radiation portion will provide guidelines on environment susceptibility as well as guidelines on tailoring other launch vehicle programs historical data to a specific launch vehicle.

A CLOUD BOUNDARY DETECTION SCHEME COMBINED WITH ASLIC AND CNN USING ZY-3, GF-1/2 SATELLITE IMAGERY

Directory of Open Access Journals (Sweden)

Z. Guo

2018-04-01

Full Text Available Remote sensing optical image cloud detection is one of the most important problems in remote sensing data processing. Aiming at the information loss caused by cloud cover, a cloud detection method based on convolution neural network (CNN is presented in this paper. Firstly, a deep CNN network is used to extract the multi-level feature generation model of cloud from the training samples. Secondly, the adaptive simple linear iterative clustering (ASLIC method is used to divide the detected images into superpixels. Finally, the probability of each superpixel belonging to the cloud region is predicted by the trained network model, thereby generating a cloud probability map. The typical region of GF-1/2 and ZY-3 were selected to carry out the cloud detection test, and compared with the traditional SLIC method. The experiment results show that the average accuracy of cloud detection is increased by more than 5 %, and it can detected thin-thick cloud and the whole cloud boundary well on different imaging platforms.

Field Programmable Gate Array Reliability Analysis Guidelines for Launch Vehicle Reliability Block Diagrams

Science.gov (United States)

Al Hassan, Mohammad; Britton, Paul; Hatfield, Glen Spencer; Novack, Steven D.

2017-01-01

Field Programmable Gate Arrays (FPGAs) integrated circuits (IC) are one of the key electronic components in today's sophisticated launch and space vehicle complex avionic systems, largely due to their superb reprogrammable and reconfigurable capabilities combined with relatively low non-recurring engineering costs (NRE) and short design cycle. Consequently, FPGAs are prevalent ICs in communication protocols and control signal commands. This paper will identify reliability concerns and high level guidelines to estimate FPGA total failure rates in a launch vehicle application. The paper will discuss hardware, hardware description language, and radiation induced failures. The hardware contribution of the approach accounts for physical failures of the IC. The hardware description language portion will discuss the high level FPGA programming languages and software/code reliability growth. The radiation portion will discuss FPGA susceptibility to space environment radiation.

Divide and Conquer-Based 1D CNN Human Activity Recognition Using Test Data Sharpening

Directory of Open Access Journals (Sweden)

Heeryon Cho

2018-04-01

Full Text Available Human Activity Recognition (HAR aims to identify the actions performed by humans using signals collected from various sensors embedded in mobile devices. In recent years, deep learning techniques have further improved HAR performance on several benchmark datasets. In this paper, we propose one-dimensional Convolutional Neural Network (1D CNN for HAR that employs a divide and conquer-based classifier learning coupled with test data sharpening. Our approach leverages a two-stage learning of multiple 1D CNN models; we first build a binary classifier for recognizing abstract activities, and then build two multi-class 1D CNN models for recognizing individual activities. We then introduce test data sharpening during prediction phase to further improve the activity recognition accuracy. While there have been numerous researches exploring the benefits of activity signal denoising for HAR, few researches have examined the effect of test data sharpening for HAR. We evaluate the effectiveness of our approach on two popular HAR benchmark datasets, and show that our approach outperforms both the two-stage 1D CNN-only method and other state of the art approaches.

Three-Dimensional Reconstruction from Single Image Base on Combination of CNN and Multi-Spectral Photometric Stereo

Science.gov (United States)

Lu, Liang; Qi, Lin; Luo, Yisong; Jiao, Hengchao; Dong, Junyu

2018-01-01

Multi-spectral photometric stereo can recover pixel-wise surface normal from a single RGB image. The difficulty lies in that the intensity in each channel is the tangle of illumination, albedo and camera response; thus, an initial estimate of the normal is required in optimization-based solutions. In this paper, we propose to make a rough depth estimation using the deep convolutional neural network (CNN) instead of using depth sensors or binocular stereo devices. Since high-resolution ground-truth data is expensive to obtain, we designed a network and trained it with rendered images of synthetic 3D objects. We use the model to predict initial normal of real-world objects and iteratively optimize the fine-scale geometry in the multi-spectral photometric stereo framework. The experimental results illustrate the improvement of the proposed method compared with existing methods. PMID:29498703

Three-Dimensional Reconstruction from Single Image Base on Combination of CNN and Multi-Spectral Photometric Stereo

Directory of Open Access Journals (Sweden)

Liang Lu

2018-03-01

Full Text Available Multi-spectral photometric stereo can recover pixel-wise surface normal from a single RGB image. The difficulty lies in that the intensity in each channel is the tangle of illumination, albedo and camera response; thus, an initial estimate of the normal is required in optimization-based solutions. In this paper, we propose to make a rough depth estimation using the deep convolutional neural network (CNN instead of using depth sensors or binocular stereo devices. Since high-resolution ground-truth data is expensive to obtain, we designed a network and trained it with rendered images of synthetic 3D objects. We use the model to predict initial normal of real-world objects and iteratively optimize the fine-scale geometry in the multi-spectral photometric stereo framework. The experimental results illustrate the improvement of the proposed method compared with existing methods.

CNN-PROMOTER, NEW CONSENSUS PROMOTER PREDICTION PROGRAM BASED ON NEURAL NETWORKS CNN-PROMOTER, NUEVO PROGRAMA PARA LA PREDICCIÓN DE PROMOTORES BASADO EN REDES NEURONALES CNN-PROMOTER, NOVO PROGRAMA PARA A PREDIÇÃO DE PROMOTORES BASEADO EM REDES NEURONAIS

Directory of Open Access Journals (Sweden)

Óscar Bedoya

2011-06-01

Full Text Available A new promoter prediction program called CNN-Promoter is presented. CNN-Promoter allows DNA sequences to be submitted and predicts them as promoter or non-promoter. Several methods have been developed to predict the promoter regions of genomes in eukaryotic organisms including algorithms based on Markov's models, decision trees, and statistical methods. Although there are plenty of programs proposed, there is still a need to improve the sensitivity and specificity values. In this paper, a new program is proposed; it is based on the consensus strategy of using experts to make a better prediction. The consensus strategy is developed by using neural networks. During the training process, the sensitivity and specificity were 100 % and during the test process the model reaches a sensitivity of 74.5 % and a specificity of 82.7 %.En este artículo se presenta un programa nuevo para la predicción de promotores llamado CNN-Promoter, que toma como entrada secuencias de ADN y las clasifica como promotor o no promotor. Se han desarrollado diversos métodos para predecir las regiones promotoras en organismos eucariotas, muchos de los cuales se basan en modelos de Markov, árboles de decisión y métodos estadísticos. A pesar de la variedad de programas existentes para la predicción de promotores, se necesita aún mejorar los valores de sensibilidad y especificidad. Se propone un nuevo programa que se basa en la estrategia de mezcla de expertos usando redes neuronales. Los resultados obtenidos en las pruebas alcanzan valores de sensibilidad y especificidad de 100 % en el entrenamiento y de 74,5 % de sensibilidad y 82,7 % de especificidad en los conjuntos de validación y prueba.Neste artigo a presenta-se um novo programa para a predição de promotores chamado CNN-Promoter, que toma como entrada sequências de DNA e as classifica como promotor ou não promotor. Desenvolveramse diversos métodos para predizer as regiões promotoras em organismos eucariotas

Chinese character recognition based on Gabor feature extraction and CNN

Science.gov (United States)

Xiong, Yudian; Lu, Tongwei; Jiang, Yongyuan

2018-03-01

As an important application in the field of text line recognition and office automation, Chinese character recognition has become an important subject of pattern recognition. However, due to the large number of Chinese characters and the complexity of its structure, there is a great difficulty in the Chinese character recognition. In order to solve this problem, this paper proposes a method of printed Chinese character recognition based on Gabor feature extraction and Convolution Neural Network(CNN). The main steps are preprocessing, feature extraction, training classification. First, the gray-scale Chinese character image is binarized and normalized to reduce the redundancy of the image data. Second, each image is convoluted with Gabor filter with different orientations, and the feature map of the eight orientations of Chinese characters is extracted. Third, the feature map through Gabor filters and the original image are convoluted with learning kernels, and the results of the convolution is the input of pooling layer. Finally, the feature vector is used to classify and recognition. In addition, the generalization capacity of the network is improved by Dropout technology. The experimental results show that this method can effectively extract the characteristics of Chinese characters and recognize Chinese characters.

Theory and implementation of a very high throughput true random number generator in field programmable gate array

Energy Technology Data Exchange (ETDEWEB)

Wang, Yonggang, E-mail: wangyg@ustc.edu.cn; Hui, Cong; Liu, Chong; Xu, Chao [Department of Modern Physics, University of Science and Technology of China, Hefei 230026 (China)

2016-04-15

The contribution of this paper is proposing a new entropy extraction mechanism based on sampling phase jitter in ring oscillators to make a high throughput true random number generator in a field programmable gate array (FPGA) practical. Starting from experimental observation and analysis of the entropy source in FPGA, a multi-phase sampling method is exploited to harvest the clock jitter with a maximum entropy and fast sampling speed. This parametrized design is implemented in a Xilinx Artix-7 FPGA, where the carry chains in the FPGA are explored to realize the precise phase shifting. The generator circuit is simple and resource-saving, so that multiple generation channels can run in parallel to scale the output throughput for specific applications. The prototype integrates 64 circuit units in the FPGA to provide a total output throughput of 7.68 Gbps, which meets the requirement of current high-speed quantum key distribution systems. The randomness evaluation, as well as its robustness to ambient temperature, confirms that the new method in a purely digital fashion can provide high-speed high-quality random bit sequences for a variety of embedded applications.

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.

Field-programmable beam reconfiguring based on digitally-controlled coding metasurface

Science.gov (United States)

Wan, Xiang; Qi, Mei Qing; Chen, Tian Yi; Cui, Tie Jun

2016-02-01

Digital phase shifters have been applied in traditional phased array antennas to realize beam steering. However, the phase shifter deals with the phase of the induced current; hence, it has to be in the path of each element of the antenna array, making the phased array antennas very expensive. Metamaterials and/or metasurfaces enable the direct modulation of electromagnetic waves by designing subwavelength structures, which opens a new way to control the beam scanning. Here, we present a direct digital mechanism to control the scattered electromagnetic waves using coding metasurface, in which each unit cell loads a pin diode to produce binary coding states of “1” and “0”. Through data lines, the instant communications are established between the coding metasurface and the internal memory of field-programmable gate arrays (FPGA). Thus, we realize the digital modulation of electromagnetic waves, from which we present the field-programmable reflective antenna with good measurement performance. The proposed mechanism and functional device have great application potential in new-concept radar and communication systems.

Genetic algorithm-based neural network for accidents diagnosis of research reactors on FPGA

International Nuclear Information System (INIS)

Ghuname, A.A.A.

2012-01-01

the efficiency of using genetic algorithm, which can construct the high performance neural network structure for recognizing the Nuclear Research Reactors accidents patterns.The third part is concerned with the hardware implementation of an artificial neural network that had obtained from Genetic Algorithm (GA) using MATLAB's toolbox. The excellent hardware performance has been performed through the use of field programmable gate array (FPGA), on Xilinx chip, to diagnosis the Multi-Purpose Research Reactor of Egypt (MPR) accidents patterns, to avoid the risk of occurrence of a nuclear accident. The artificial neural network hardware model has been designed using Xilinx Software environment. Hardware implementation results presented unfold the promise of the hardware implementation of artificial neural networks for improving the operating performance of the Nuclear Research Reactors.

Opinion mining on book review using CNN-L2-SVM algorithm

Science.gov (United States)

Rozi, M. F.; Mukhlash, I.; Soetrisno; Kimura, M.

2018-03-01

Review of a product can represent quality of a product itself. An extraction to that review can be used to know sentiment of that opinion. Process to extract useful information of user review is called Opinion Mining. Review extraction model that is enhancing nowadays is Deep Learning model. This Model has been used by many researchers to obtain excellent performance on Natural Language Processing. In this research, one of deep learning model, Convolutional Neural Network (CNN) is used for feature extraction and L2 Support Vector Machine (SVM) as classifier. These methods are implemented to know the sentiment of book review data. The result of this method shows state-of-the art performance in 83.23% for training phase and 64.6% for testing phase.

Development of an FPGA-Based Motion Control IC for Caving Machine

Directory of Open Access Journals (Sweden)

Chiu-Keng Lai

2014-03-01

Full Text Available Since the Field Programmable Gate Arrays (FPGAs with high density are available nowadays, systems with complex functions can thus be realized by FPGA in a single chip while they are traditionally implemented by several individual chips. In this research, the control of stepping motor drives as well as motion controller is integrated and implemented on Altera Cyclone III FPGA; the resulting system is evaluated by applying it to a 3-axis caving machine which is driven by stepping motors. Finally, the experimental results of current regulation and motion control integrated in FPGA IC are shown to prove the validness.

Automatic detection of anatomical regions in frontal x-ray images: comparing convolutional neural networks to random forest

Science.gov (United States)

Olory Agomma, R.; Vázquez, C.; Cresson, T.; De Guise, J.

2018-02-01

Most algorithms to detect and identify anatomical structures in medical images require either to be initialized close to the target structure, or to know that the structure is present in the image, or to be trained on a homogeneous database (e.g. all full body or all lower limbs). Detecting these structures when there is no guarantee that the structure is present in the image, or when the image database is heterogeneous (mixed configurations), is a challenge for automatic algorithms. In this work we compared two state-of-the-art machine learning techniques in order to determine which one is the most appropriate for predicting targets locations based on image patches. By knowing the position of thirteen landmarks points, labelled by an expert in EOS frontal radiography, we learn the displacement between salient points detected in the image and these thirteen landmarks. The learning step is carried out with a machine learning approach by exploring two methods: Convolutional Neural Network (CNN) and Random Forest (RF). The automatic detection of the thirteen landmarks points in a new image is then obtained by averaging the positions of each one of these thirteen landmarks estimated from all the salient points in the new image. We respectively obtain for CNN and RF, an average prediction error (both mean and standard deviation in mm) of 29 +/-18 and 30 +/- 21 for the thirteen landmarks points, indicating the approximate location of anatomical regions. On the other hand, the learning time is 9 days for CNN versus 80 minutes for RF. We provide a comparison of the results between the two machine learning approaches.

A convolutional neural network neutrino event classifier

International Nuclear Information System (INIS)

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

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.

Fringe pattern demodulation using the one-dimensional continuous wavelet transform: field-programmable gate array implementation.

Science.gov (United States)

Abid, Abdulbasit

2013-03-01

This paper presents a thorough discussion of the proposed field-programmable gate array (FPGA) implementation for fringe pattern demodulation using the one-dimensional continuous wavelet transform (1D-CWT) algorithm. This algorithm is also known as wavelet transform profilometry. Initially, the 1D-CWT is programmed using the C programming language and compiled into VHDL using the ImpulseC tool. This VHDL code is implemented on the Altera Cyclone IV GX EP4CGX150DF31C7 FPGA. A fringe pattern image with a size of 512×512 pixels is presented to the FPGA, which processes the image using the 1D-CWT algorithm. The FPGA requires approximately 100 ms to process the image and produce a wrapped phase map. For performance comparison purposes, the 1D-CWT algorithm is programmed using the C language. The C code is then compiled using the Intel compiler version 13.0. The compiled code is run on a Dell Precision state-of-the-art workstation. The time required to process the fringe pattern image is approximately 1 s. In order to further reduce the execution time, the 1D-CWT is reprogramed using Intel Integrated Primitive Performance (IPP) Library Version 7.1. The execution time was reduced to approximately 650 ms. This confirms that at least sixfold speedup was gained using FPGA implementation over a state-of-the-art workstation that executes heavily optimized implementation of the 1D-CWT algorithm.

IMPLEMENTATION OF NEURAL - CRYPTOGRAPHIC SYSTEM USING FPGA

Directory of Open Access Journals (Sweden)

KARAM M. Z. OTHMAN

2011-08-01

Full Text Available Modern cryptography techniques are virtually unbreakable. As the Internet and other forms of electronic communication become more prevalent, electronic security is becoming increasingly important. Cryptography is used to protect e-mail messages, credit card information, and corporate data. The design of the cryptography system is a conventional cryptography that uses one key for encryption and decryption process. The chosen cryptography algorithm is stream cipher algorithm that encrypt one bit at a time. The central problem in the stream-cipher cryptography is the difficulty of generating a long unpredictable sequence of binary signals from short and random key. Pseudo random number generators (PRNG have been widely used to construct this key sequence. The pseudo random number generator was designed using the Artificial Neural Networks (ANN. The Artificial Neural Networks (ANN providing the required nonlinearity properties that increases the randomness statistical properties of the pseudo random generator. The learning algorithm of this neural network is backpropagation learning algorithm. The learning process was done by software program in Matlab (software implementation to get the efficient weights. Then, the learned neural network was implemented using field programmable gate array (FPGA.

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.

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.

Development of a protection system for research reactor based in Field Programmable Gate Array - FPGA

International Nuclear Information System (INIS)

Martins, Roque Hudson da Silva

2016-01-01

This study presents a implementation purpose of a protection system for research nuclear reactors by using a programed device FPGA (Field Programmable Gate Array). As well as logic protection method involved on an automatic shutdown (TRIP) of a reactor, that ensure the security on such systems. These new control and operation mechanics are developed to guarantee that the security limits of a power plant are not exceeded, these mechanics can work isolated or in groups to safe guard the security levels. For this implementation to be completed, there will be presented the main aspects and concepts referred to protection systems, mostly about research nuclear reactors, with some applications terms exposed. The system proposed at this paper was developed following the VHDL (Very High Speed Integrated Circuits) hardware describing language, and the Modelsim software from Altera Software to program the automatic turning off routines, and hypothetical simulations for such. The results show that for every software application for supporting nuclear reactors, like security devices, they have to meet the IEC 60880 criteria. This paper have great importance, seeing that nuclear reactor security systems, are a basic element for ensure the reactor security. (author)

Automatic diagnosis of imbalanced ophthalmic images using a cost-sensitive deep convolutional neural network.

Science.gov (United States)

Jiang, Jiewei; Liu, Xiyang; Zhang, Kai; Long, Erping; Wang, Liming; Li, Wangting; Liu, Lin; Wang, Shuai; Zhu, Mingmin; Cui, Jiangtao; Liu, Zhenzhen; Lin, Zhuoling; Li, Xiaoyan; Chen, Jingjing; Cao, Qianzhong; Li, Jing; Wu, Xiaohang; Wang, Dongni; Wang, Jinghui; Lin, Haotian

2017-11-21

Ocular images play an essential role in ophthalmological diagnoses. Having an imbalanced dataset is an inevitable issue in automated ocular diseases diagnosis; the scarcity of positive samples always tends to result in the misdiagnosis of severe patients during the classification task. Exploring an effective computer-aided diagnostic method to deal with imbalanced ophthalmological dataset is crucial. In this paper, we develop an effective cost-sensitive deep residual convolutional neural network (CS-ResCNN) classifier to diagnose ophthalmic diseases using retro-illumination images. First, the regions of interest (crystalline lens) are automatically identified via twice-applied Canny detection and Hough transformation. Then, the localized zones are fed into the CS-ResCNN to extract high-level features for subsequent use in automatic diagnosis. Second, the impacts of cost factors on the CS-ResCNN are further analyzed using a grid-search procedure to verify that our proposed system is robust and efficient. Qualitative analyses and quantitative experimental results demonstrate that our proposed method outperforms other conventional approaches and offers exceptional mean accuracy (92.24%), specificity (93.19%), sensitivity (89.66%) and AUC (97.11%) results. Moreover, the sensitivity of the CS-ResCNN is enhanced by over 13.6% compared to the native CNN method. Our study provides a practical strategy for addressing imbalanced ophthalmological datasets and has the potential to be applied to other medical images. The developed and deployed CS-ResCNN could serve as computer-aided diagnosis software for ophthalmologists in clinical application.

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.

Implementation of an RBF neural network on embedded systems: real-time face tracking and identity verification.

Science.gov (United States)

Yang, Fan; Paindavoine, M

2003-01-01

This paper describes a real time vision system that allows us to localize faces in video sequences and verify their identity. These processes are image processing techniques based on the radial basis function (RBF) neural network approach. The robustness of this system has been evaluated quantitatively on eight video sequences. We have adapted our model for an application of face recognition using the Olivetti Research Laboratory (ORL), Cambridge, UK, database so as to compare the performance against other systems. We also describe three hardware implementations of our model on embedded systems based on the field programmable gate array (FPGA), zero instruction set computer (ZISC) chips, and digital signal processor (DSP) TMS320C62, respectively. We analyze the algorithm complexity and present results of hardware implementations in terms of the resources used and processing speed. The success rates of face tracking and identity verification are 92% (FPGA), 85% (ZISC), and 98.2% (DSP), respectively. For the three embedded systems, the processing speeds for images size of 288 /spl times/ 352 are 14 images/s, 25 images/s, and 4.8 images/s, respectively.

5W1H Information Extraction with CNN-Bidirectional LSTM

Science.gov (United States)

Nurdin, A.; Maulidevi, N. U.

2018-03-01

In this work, information about who, did what, when, where, why, and how on Indonesian news articles were extracted by combining Convolutional Neural Network and Bidirectional Long Short-Term Memory. Convolutional Neural Network can learn semantically meaningful representations of sentences. Bidirectional LSTM can analyze the relations among words in the sequence. We also use word embedding word2vec for word representation. By combining these algorithms, we obtained F-measure 0.808. Our experiments show that CNN-BLSTM outperforms other shallow methods, namely IBk, C4.5, and Naïve Bayes with the F-measure 0.655, 0.645, and 0.595, respectively.

Psoriasis skin biopsy image segmentation using Deep Convolutional Neural Network.

Science.gov (United States)

Pal, Anabik; Garain, Utpal; Chandra, Aditi; Chatterjee, Raghunath; Senapati, Swapan

2018-06-01

Development of machine assisted tools for automatic analysis of psoriasis skin biopsy image plays an important role in clinical assistance. Development of automatic approach for accurate segmentation of psoriasis skin biopsy image is the initial prerequisite for developing such system. However, the complex cellular structure, presence of imaging artifacts, uneven staining variation make the task challenging. This paper presents a pioneering attempt for automatic segmentation of psoriasis skin biopsy images. Several deep neural architectures are tried for segmenting psoriasis skin biopsy images. Deep models are used for classifying the super-pixels generated by Simple Linear Iterative Clustering (SLIC) and the segmentation performance of these architectures is compared with the traditional hand-crafted feature based classifiers built on popularly used classifiers like K-Nearest Neighbor (KNN), Support Vector Machine (SVM) and Random Forest (RF). A U-shaped Fully Convolutional Neural Network (FCN) is also used in an end to end learning fashion where input is the original color image and the output is the segmentation class map for the skin layers. An annotated real psoriasis skin biopsy image data set of ninety (90) images is developed and used for this research. The segmentation performance is evaluated with two metrics namely, Jaccard's Coefficient (JC) and the Ratio of Correct Pixel Classification (RCPC) accuracy. The experimental results show that the CNN based approaches outperform the traditional hand-crafted feature based classification approaches. The present research shows that practical system can be developed for machine assisted analysis of psoriasis disease. Copyright © 2018 Elsevier B.V. All rights reserved.

The impact of software and CAE tools on SEU in field programmable gate arrays

International Nuclear Information System (INIS)

Katz, R.; Wang, J.; McCollum, J.; Cronquist, B.

1999-01-01

Field programmable gate array (FPGA) devices, heavily used in spacecraft electronics, have grown substantially in size over the past few years, causing designers to work at a higher conceptual level, with computer aided engineering (CAE) tools synthesizing and optimizing the logic from a description. It is shown that the use of commercial-off-the-shelf (COTS) CAE tools can produce unreliable circuit designs when the device is used in a radiation environment and a flip-flop is upset. At a lower level, software can be used to improve the SEU performance of a flip-flop, exploiting the configurable nature of FPGA technology and on-chip delay, parasitic resistive, and capacitive circuit elements

Development of field programmable gate array-based reactor trip functions using systems engineering approach

Energy Technology Data Exchange (ETDEWEB)

Jung, Jae Cheon; Ahmed, Ibrahim [Nuclear Power Plant Engineering, KEPCO International Nuclear Graduate School, Ulsan (Korea, Republic of)

2016-08-15

Design engineering process for field programmable gate array (FPGA)-based reactor trip functions are developed in this work. The process discussed in this work is based on the systems engineering approach. The overall design process is effectively implemented by combining with design and implementation processes. It transforms its overall development process from traditional V-model to Y-model. This approach gives the benefit of concurrent engineering of design work with software implementation. As a result, it reduces development time and effort. The design engineering process consisted of five activities, which are performed and discussed: needs/systems analysis; requirement analysis; functional analysis; design synthesis; and design verification and validation. Those activities are used to develop FPGA-based reactor bistable trip functions that trigger reactor trip when the process input value exceeds the setpoint. To implement design synthesis effectively, a model-based design technique is implied. The finite-state machine with data path structural modeling technique together with very high speed integrated circuit hardware description language and the Aldec Active-HDL tool are used to design, model, and verify the reactor bistable trip functions for nuclear power plants.

CNN-SVM for Microvascular Morphological Type Recognition with Data Augmentation.

Science.gov (United States)

Xue, Di-Xiu; Zhang, Rong; Feng, Hui; Wang, Ya-Lei

2016-01-01

This paper focuses on the problem of feature extraction and the classification of microvascular morphological types to aid esophageal cancer detection. We present a patch-based system with a hybrid SVM model with data augmentation for intraepithelial papillary capillary loop recognition. A greedy patch-generating algorithm and a specialized CNN named NBI-Net are designed to extract hierarchical features from patches. We investigate a series of data augmentation techniques to progressively improve the prediction invariance of image scaling and rotation. For classifier boosting, SVM is used as an alternative to softmax to enhance generalization ability. The effectiveness of CNN feature representation ability is discussed for a set of widely used CNN models, including AlexNet, VGG-16, and GoogLeNet. Experiments are conducted on the NBI-ME dataset. The recognition rate is up to 92.74% on the patch level with data augmentation and classifier boosting. The results show that the combined CNN-SVM model beats models of traditional features with SVM as well as the original CNN with softmax. The synthesis results indicate that our system is able to assist clinical diagnosis to a certain extent.

Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists.

Science.gov (United States)

Haenssle, H A; Fink, C; Schneiderbauer, R; Toberer, F; Buhl, T; Blum, A; Kalloo, A; Hassen, A Ben Hadj; Thomas, L; Enk, A; Uhlmann, L

2018-05-28

Deep learning convolutional neural networks (CNN) may facilitate melanoma detection, but data comparing a CNN's diagnostic performance to larger groups of dermatologists are lacking. Google's Inception v4 CNN architecture was trained and validated using dermoscopic images and corresponding diagnoses. In a comparative cross-sectional reader study a 100-image test-set was used (level-I: dermoscopy only; level-II: dermoscopy plus clinical information and images). Main outcome measures were sensitivity, specificity and area under the curve (AUC) of receiver operating characteristics (ROC) for diagnostic classification (dichotomous) of lesions by the CNN versus an international group of 58 dermatologists during level-I or -II of the reader study. Secondary end points included the dermatologists' diagnostic performance in their management decisions and differences in the diagnostic performance of dermatologists during level-I and -II of the reader study. Additionally, the CNN's performance was compared with the top-five algorithms of the 2016 International Symposium on Biomedical Imaging (ISBI) challenge. In level-I dermatologists achieved a mean (±standard deviation) sensitivity and specificity for lesion classification of 86.6% (±9.3%) and 71.3% (±11.2%), respectively. More clinical information (level-II) improved the sensitivity to 88.9% (±9.6%, P = 0.19) and specificity to 75.7% (±11.7%, P < 0.05). The CNN ROC curve revealed a higher specificity of 82.5% when compared with dermatologists in level-I (71.3%, P < 0.01) and level-II (75.7%, P < 0.01) at their sensitivities of 86.6% and 88.9%, respectively. The CNN ROC AUC was greater than the mean ROC area of dermatologists (0.86 versus 0.79, P < 0.01). The CNN scored results close to the top three algorithms of the ISBI 2016 challenge. For the first time we compared a CNN's diagnostic performance with a large international group of 58 dermatologists, including 30 experts. Most dermatologists

Segmentation of white matter hyperintensities using convolutional neural networks with global spatial information in routine clinical brain MRI with none or mild vascular pathology.

Science.gov (United States)

Rachmadi, Muhammad Febrian; Valdés-Hernández, Maria Del C; Agan, Maria Leonora Fatimah; Di Perri, Carol; Komura, Taku

2018-06-01

We propose an adaptation of a convolutional neural network (CNN) scheme proposed for segmenting brain lesions with considerable mass-effect, to segment white matter hyperintensities (WMH) characteristic of brains with none or mild vascular pathology in routine clinical brain magnetic resonance images (MRI). This is a rather difficult segmentation problem because of the small area (i.e., volume) of the WMH and their similarity to non-pathological brain tissue. We investigate the effectiveness of the 2D CNN scheme by comparing its performance against those obtained from another deep learning approach: Deep Boltzmann Machine (DBM), two conventional machine learning approaches: Support Vector Machine (SVM) and Random Forest (RF), and a public toolbox: Lesion Segmentation Tool (LST), all reported to be useful for segmenting WMH in MRI. We also introduce a way to incorporate spatial information in convolution level of CNN for WMH segmentation named global spatial information (GSI). Analysis of covariance corroborated known associations between WMH progression, as assessed by all methods evaluated, and demographic and clinical data. Deep learning algorithms outperform conventional machine learning algorithms by excluding MRI artefacts and pathologies that appear similar to WMH. Our proposed approach of incorporating GSI also successfully helped CNN to achieve better automatic WMH segmentation regardless of network's settings tested. The mean Dice Similarity Coefficient (DSC) values for LST-LGA, SVM, RF, DBM, CNN and CNN-GSI were 0.2963, 0.1194, 0.1633, 0.3264, 0.5359 and 5389 respectively. Crown Copyright © 2018. Published by Elsevier Ltd. All rights reserved.

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.

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...

Implementing EW Receivers Based on Large Point Reconfigured FFT on FPGA Platforms

Directory of Open Access Journals (Sweden)

He Chen

2011-12-01

Full Text Available This paper presents design and implementation of digital receiver based on large point fast Fourier transform (FFT suitable for electronic warfare (EW applications. When implementing the FFT algorithm on field-programmable gate array (FPGA platforms, the primary goal is to maximize throughput and minimize area. This algorithm adopts two-dimension, parallel and pipeline stream mode and implements the reconfiguration of FFT's points. Moreover, a double-sequence-separation FFT algorithm has been implemented in order to achieve faster real time processing in broadband digital receivers. The performance of the hardware implementation on the FPGA platforms of broadband digital receivers has been analyzed in depth. It reaches the requirement of high-speed digital signal processing, and reveals the designing this kind of digital signal processing systems on FPGA platforms. Keywords: digital receivers, field programmable gate array (FPGA, fast Fourier transform (FFT, large point reconfigured, signal processing system.

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.

Field Programmable Gate Array (FPGA Respiratory Monitoring System Using a Flow Microsensor and an Accelerometer

Directory of Open Access Journals (Sweden)

Mellal Idir

2017-04-01

Full Text Available This paper describes a non-invasive system for respiratory monitoring using a Micro Electro Mechanical Systems (MEMS flow sensor and an IMU (Inertial Measurement Unit accelerometer. The designed system is intended to be wearable and used in a hospital or at home to assist people with respiratory disorders. To ensure the accuracy of our system, we proposed a calibration method based on ANN (Artificial Neural Network to compensate the temperature drift of the silicon flow sensor. The sigmoid activation functions used in the ANN model were computed with the CORDIC (COordinate Rotation DIgital Computer algorithm. This algorithm was also used to estimate the tilt angle in body position. The design was implemented on reconfigurable platform FPGA.

Design and Implementation of a FPGA and DSP Based MIMO Radar Imaging System

Directory of Open Access Journals (Sweden)

Wei Wang

2015-06-01

Full Text Available The work presented in this paper is aimed at the implementation of a real-time multiple-input multiple-output (MIMO imaging radar used for area surveillance. In this radar, the equivalent virtual array method and time-division technique are applied to make 16 virtual elements synthesized from the MIMO antenna array. The chirp signal generater is based on a combination of direct digital synthesizer (DDS and phase locked loop (PLL. A signal conditioning circuit is used to deal with the coupling effect within the array. The signal processing platform is based on an efficient field programmable gates array (FPGA and digital signal processor (DSP pipeline where a robust beamforming imaging algorithm is running on. The radar system was evaluated through a real field experiment. Imaging capability and real-time performance shown in the results demonstrate the practical feasibility of the implementation.

Implementation of Adaptive Digital Controllers on Programmable Logic Devices

Science.gov (United States)

Gwaltney, David A.; King, Kenneth D.; Smith, Keary J.; Monenegro, Justino (Technical Monitor)

2002-01-01

Much has been made of the capabilities of FPGA's (Field Programmable Gate Arrays) in the hardware implementation of fast digital signal processing. Such capability also makes an FPGA a suitable platform for the digital implementation of closed loop controllers. Other researchers have implemented a variety of closed-loop digital controllers on FPGA's. Some of these controllers include the widely used proportional-integral-derivative (PID) controller, state space controllers, neural network and fuzzy logic based controllers. There are myriad advantages to utilizing an FPGA for discrete-time control functions which include the capability for reconfiguration when SRAM-based FPGA's are employed, fast parallel implementation of multiple control loops and implementations that can meet space level radiation tolerance requirements in a compact form-factor. Generally, a software implementation on a DSP (Digital Signal Processor) or microcontroller is used to implement digital controllers. At Marshall Space Flight Center, the Control Electronics Group has been studying adaptive discrete-time control of motor driven actuator systems using digital signal processor (DSP) devices. While small form factor, commercial DSP devices are now available with event capture, data conversion, pulse width modulated (PWM) outputs and communication peripherals, these devices are not currently available in designs and packages which meet space level radiation requirements. In general, very few DSP devices are produced that are designed to meet any level of radiation tolerance or hardness. The goal of this effort is to create a fully digital, flight ready controller design that utilizes an FPGA for implementation of signal conditioning for control feedback signals, generation of commands to the controlled system, and hardware insertion of adaptive control algorithm approaches. An alternative is required for compact implementation of such functionality to withstand the harsh environment

CNN Newsroom Classroom Guides, October 2000.

Science.gov (United States)

Turner Educational Services, Inc., Newtown, PA.

These classroom guides, designed to accompany the daily CNN (Cable News Network) Newsroom broadcasts for the month of October 2000, provide program rundowns, suggestions for class activities and discussion, student handouts, and a list of related news terms. Top stories include: Chinese authorities detain Falun Gong protesters on Tiananmen Square…

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...

Segmentation of histological images and fibrosis identification with a convolutional neural network.

Science.gov (United States)

Fu, Xiaohang; Liu, Tong; Xiong, Zhaohan; Smaill, Bruce H; Stiles, Martin K; Zhao, Jichao

2018-05-16

Segmentation of histological images is one of the most crucial tasks for many biomedical analyses involving quantification of certain tissue types, such as fibrosis via Masson's trichrome staining. However, challenges are posed by the high variability and complexity of structural features in such images, in addition to imaging artifacts. Further, the conventional approach of manual thresholding is labor-intensive, and highly sensitive to inter- and intra-image intensity variations. An accurate and robust automated segmentation method is of high interest. We propose and evaluate an elegant convolutional neural network (CNN) designed for segmentation of histological images, particularly those with Masson's trichrome stain. The network comprises 11 successive convolutional - rectified linear unit - batch normalization layers. It outperformed state-of-the-art CNNs on a dataset of cardiac histological images (labeling fibrosis, myocytes, and background) with a Dice similarity coefficient of 0.947. With 100 times fewer (only 300,000) trainable parameters than the state-of-the-art, our CNN is less susceptible to overfitting, and is efficient. Additionally, it retains image resolution from input to output, captures fine-grained details, and can be trained end-to-end smoothly. To the best of our knowledge, this is the first deep CNN tailored to the problem of concern, and may potentially be extended to solve similar segmentation tasks to facilitate investigations into pathology and clinical treatment. Copyright © 2018. Published by Elsevier Ltd.

Abnormality Detection in Mammography using Deep Convolutional Neural Networks

OpenAIRE

Xi, Pengcheng; Shu, Chang; Goubran, Rafik

2018-01-01

Breast cancer is the most common cancer in women worldwide. The most common screening technology is mammography. To reduce the cost and workload of radiologists, we propose a computer aided detection approach for classifying and localizing calcifications and masses in mammogram images. To improve on conventional approaches, we apply deep convolutional neural networks (CNN) for automatic feature learning and classifier building. In computer-aided mammography, deep CNN classifiers cannot be tra...

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.

A Design Methodology for Efficient Implementation of Deconvolutional Neural Networks on an FPGA

OpenAIRE

Zhang, Xinyu; Das, Srinjoy; Neopane, Ojash; Kreutz-Delgado, Ken

2017-01-01

In recent years deep learning algorithms have shown extremely high performance on machine learning tasks such as image classification and speech recognition. In support of such applications, various FPGA accelerator architectures have been proposed for convolutional neural networks (CNNs) that enable high performance for classification tasks at lower power than CPU and GPU processors. However, to date, there has been little research on the use of FPGA implementations of deconvolutional neural...

Convolutional neural network guided blue crab knuckle detection for autonomous crab meat picking machine

Science.gov (United States)

Wang, Dongyi; Vinson, Robert; Holmes, Maxwell; Seibel, Gary; Tao, Yang

2018-04-01

The Atlantic blue crab is among the highest-valued seafood found in the American Eastern Seaboard. Currently, the crab processing industry is highly dependent on manual labor. However, there is great potential for vision-guided intelligent machines to automate the meat picking process. Studies show that the back-fin knuckles are robust features containing information about a crab's size, orientation, and the position of the crab's meat compartments. Our studies also make it clear that detecting the knuckles reliably in images is challenging due to the knuckle's small size, anomalous shape, and similarity to joints in the legs and claws. An accurate and reliable computer vision algorithm was proposed to detect the crab's back-fin knuckles in digital images. Convolutional neural networks (CNNs) can localize rough knuckle positions with 97.67% accuracy, transforming a global detection problem into a local detection problem. Compared to the rough localization based on human experience or other machine learning classification methods, the CNN shows the best localization results. In the rough knuckle position, a k-means clustering method is able to further extract the exact knuckle positions based on the back-fin knuckle color features. The exact knuckle position can help us to generate a crab cutline in XY plane using a template matching method. This is a pioneering research project in crab image analysis and offers advanced machine intelligence for automated crab processing.

Enhancing Learning Effectiveness in Digital Design Courses through the Use of Programmable Logic Boards

Science.gov (United States)

Zhu, Yi; Weng, T.; Cheng, Chung-Kuan

2009-01-01

Incorporating programmable logic devices (PLD) in digital design courses has become increasingly popular. The advantages of using PLDs, such as complex programmable logic devices (CPLDs) and field programmable gate arrays (FPGA), have been discussed before. However, previous studies have focused on the experiences from the point of view of the…

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%.

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.

Wrist sensor-based tremor severity quantification in Parkinson's disease using convolutional neural network.

Science.gov (United States)

Kim, Han Byul; Lee, Woong Woo; Kim, Aryun; Lee, Hong Ji; Park, Hye Young; Jeon, Hyo Seon; Kim, Sang Kyong; Jeon, Beomseok; Park, Kwang S

2018-04-01

Tremor is a commonly observed symptom in patients of Parkinson's disease (PD), and accurate measurement of tremor severity is essential in prescribing appropriate treatment to relieve its symptoms. We propose a tremor assessment system based on the use of a convolutional neural network (CNN) to differentiate the severity of symptoms as measured in data collected from a wearable device. Tremor signals were recorded from 92 PD patients using a custom-developed device (SNUMAP) equipped with an accelerometer and gyroscope mounted on a wrist module. Neurologists assessed the tremor symptoms on the Unified Parkinson's Disease Rating Scale (UPDRS) from simultaneously recorded video footages. The measured data were transformed into the frequency domain and used to construct a two-dimensional image for training the network, and the CNN model was trained by convolving tremor signal images with kernels. The proposed CNN architecture was compared to previously studied machine learning algorithms and found to outperform them (accuracy = 0.85, linear weighted kappa = 0.85). More precise monitoring of PD tremor symptoms in daily life could be possible using our proposed method. Copyright © 2018 Elsevier Ltd. All rights reserved.

Assessment of Convolution Neural Networks for Surficial Geology Mapping in the South Rae Geological Region, Northwest Territories, Canada

Directory of Open Access Journals (Sweden)

Rasim Latifovic

2018-02-01

Full Text Available Mapping of surficial geology is an important requirement for broadening the geoscience database of northern Canada. Surficial geology maps are an integral data source for mineral and energy exploration. Moreover, they provide information such as the location of gravels and sands, which are important for infrastructure development. Currently, surficial geology maps are produced through expert interpretation of aerial photography and field data. However, interpretation is known to be subjective, labour-intensive and difficult to repeat. The expert knowledge required for interpretation can be challenging to maintain and transfer. In this research, we seek to assess the potential of deep neural networks to aid surficial geology mapping by providing an objective surficial materials initial layer that experts can modify to speed map development and improve consistency between mapped areas. Such an approach may also harness expert knowledge in a way that is transferable to unmapped areas. For this purpose, we assess the ability of convolution neural networks (CNN to predict surficial geology classes under two sampling scenarios. In the first scenario, a CNN uses samples collected over the area to be mapped. In the second, a CNN trained over one area is then applied to locations where the available samples were not used in training the network. The latter case is important, as a collection of in situ training data can be costly. The evaluation of the CNN was carried out using aerial photos, Landsat reflectance, and high-resolution digital elevation data over five areas within the South Rae geological region of Northwest Territories, Canada. The results are encouraging, with the CNN generating average accuracy of 76% when locally trained. For independent test areas (i.e., trained over one area and applied over other, accuracy dropped to 59–70% depending on the classes selected for mapping. In the South Rae region, significant confusion was found

Taxon and trait recognition from digitized herbarium specimens using deep convolutional neural networks

KAUST Repository

Younis, Sohaib; Weiland, Claus; Hoehndorf, Robert; Dressler, Stefan; Hickler, Thomas; Seeger, Bernhard; Schmidt, Marco

2018-01-01

Herbaria worldwide are housing a treasure of hundreds of millions of herbarium specimens, which are increasingly being digitized and thereby more accessible to the scientific community. At the same time, deep-learning algorithms are rapidly improving pattern recognition from images and these techniques are more and more being applied to biological objects. In this study, we are using digital images of herbarium specimens in order to identify taxa and traits of these collection objects by applying convolutional neural networks (CNN). Images of the 1000 species most frequently documented by herbarium specimens on GBIF have been downloaded and combined with morphological trait data, preprocessed and divided into training and test datasets for species and trait recognition. Good performance in both domains suggests substantial potential of this approach for supporting taxonomy and natural history collection management. Trait recognition is also promising for applications in functional ecology.

Taxon and trait recognition from digitized herbarium specimens using deep convolutional neural networks

KAUST Repository

Younis, Sohaib

2018-03-13

Herbaria worldwide are housing a treasure of hundreds of millions of herbarium specimens, which are increasingly being digitized and thereby more accessible to the scientific community. At the same time, deep-learning algorithms are rapidly improving pattern recognition from images and these techniques are more and more being applied to biological objects. In this study, we are using digital images of herbarium specimens in order to identify taxa and traits of these collection objects by applying convolutional neural networks (CNN). Images of the 1000 species most frequently documented by herbarium specimens on GBIF have been downloaded and combined with morphological trait data, preprocessed and divided into training and test datasets for species and trait recognition. Good performance in both domains suggests substantial potential of this approach for supporting taxonomy and natural history collection management. Trait recognition is also promising for applications in functional ecology.

Hardware Implementation of Artificial Neural Network for Data Ciphering

Directory of Open Access Journals (Sweden)

Sahar L. Kadoory

2016-10-01

Full Text Available This paper introduces the design and realization of multiple blocks ciphering techniques on the FPGA (Field Programmable Gate Arrays. A back propagation neural networks have been built for substitution, permutation and XOR blocks ciphering using Neural Network Toolbox in MATLAB program. They are trained to encrypt the data, after obtaining the suitable weights, biases, activation function and layout. Afterward, they are described using VHDL and implemented using Xilinx Spartan-3E FPGA using two approaches: serial and parallel versions. The simulation results obtained with Xilinx ISE 9.2i software. The numerical precision is chosen carefully when implementing the Neural Network on FPGA. Obtained results from the hardware designs show accurate numeric values to cipher the data. As expected, the synthesis results indicate that the serial version requires less area resources than the parallel version. As, the data throughput in parallel version is higher than the serial version in rang between (1.13-1.5 times. Also, a slight difference can be observed in the maximum frequency.

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...

FPGA-Based Communications Receivers for Smart Antenna Array Embedded Systems

Directory of Open Access Journals (Sweden)

Millar James

2006-01-01

Full Text Available Field-programmable gate arrays (FPGAs are drawing ever increasing interest from designers of embedded wireless communications systems. They outpace digital signal processors (DSPs, through hardware execution of a wide range of parallelizable communications transceiver algorithms, at a fraction of the design and implementation effort and cost required for application-specific integrated circuits (ASICs. In our study, we employ an Altera Stratix FPGA development board, along with the DSP Builder software tool which acts as a high-level interface to the powerful Quartus II environment. We compare single- and multibranch FPGA-based receiver designs in terms of error rate performance and power consumption. We exploit FPGA operational flexibility and algorithm parallelism to design eigenmode-monitoring receivers that can adapt to variations in wireless channel statistics, for high-performing, inexpensive, smart antenna array embedded systems.

FPGA-Based Communications Receivers for Smart Antenna Array Embedded Systems

Directory of Open Access Journals (Sweden)

James Millar

2006-10-01

Full Text Available Field-programmable gate arrays (FPGAs are drawing ever increasing interest from designers of embedded wireless communications systems. They outpace digital signal processors (DSPs, through hardware execution of a wide range of parallelizable communications transceiver algorithms, at a fraction of the design and implementation effort and cost required for application-specific integrated circuits (ASICs. In our study, we employ an Altera Stratix FPGA development board, along with the DSP Builder software tool which acts as a high-level interface to the powerful Quartus II environment. We compare single- and multibranch FPGA-based receiver designs in terms of error rate performance and power consumption. We exploit FPGA operational flexibility and algorithm parallelism to design eigenmode-monitoring receivers that can adapt to variations in wireless channel statistics, for high-performing, inexpensive, smart antenna array embedded systems.

Comparison of machine learned approaches for thyroid nodule characterization from shear wave elastography images

Science.gov (United States)

Pereira, Carina; Dighe, Manjiri; Alessio, Adam M.

2018-02-01

Various Computer Aided Diagnosis (CAD) systems have been developed that characterize thyroid nodules using the features extracted from the B-mode ultrasound images and Shear Wave Elastography images (SWE). These features, however, are not perfect predictors of malignancy. In other domains, deep learning techniques such as Convolutional Neural Networks (CNNs) have outperformed conventional feature extraction based machine learning approaches. In general, fully trained CNNs require substantial volumes of data, motivating several efforts to use transfer learning with pre-trained CNNs. In this context, we sought to compare the performance of conventional feature extraction, fully trained CNNs, and transfer learning based, pre-trained CNNs for the detection of thyroid malignancy from ultrasound images. We compared these approaches applied to a data set of 964 B-mode and SWE images from 165 patients. The data were divided into 80% training/validation and 20% testing data. The highest accuracies achieved on the testing data for the conventional feature extraction, fully trained CNN, and pre-trained CNN were 0.80, 0.75, and 0.83 respectively. In this application, classification using a pre-trained network yielded the best performance, potentially due to the relatively limited sample size and sub-optimal architecture for the fully trained CNN.

SEU mitigation technique by Dynamic Reconfiguration method in FPGA based DSP application

International Nuclear Information System (INIS)

Dey, Madhusudan; Singh, Abhishek; Roy, Amitava

2012-01-01

Field Programmable Gate Array (FPGA), an SRAM based configurable devices meant for implementation of any digital circuits is susceptible to malfunction in the harsh radiation environment. It causes the corruption of the configuration memory of FPGA and the digital circuits starts malfunctioning. There is a need to restore the system as early as possible. This paper discusses about one such technique named dynamic partial reconfiguration (DPR) method. This paper also touches upon the signal processing by DPR method. The framework consisting of ADC, DAC and ICAP controllers designed using dedicated state machines to study the best possible downtime also for verifying the performance of digital filters for signal processing

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.

FPGA Implementation of one-dimensional and two-dimensional cellular automata

International Nuclear Information System (INIS)

D'Antone, I.

1999-01-01

This report describes the hardware implementation of one-dimensional and two-dimensional cellular automata (CAs). After a general introduction to the cellular automata, we consider a one-dimensional CA used to implement pseudo-random techniques in built-in self test for VLSI. Due to the increase in digital ASIC complexity, testing is becoming one of the major costs in the VLSI production. The high electronics complexity, used in particle physics experiments, demands higher reliability than in the past time. General criterions are given to evaluate the feasibility of the circuit used for testing and some quantitative parameters are underlined to optimize the architecture of the cellular automaton. Furthermore, we propose a two-dimensional CA that performs a peak finding algorithm in a matrix of cells mapping a sub-region of a calorimeter. As in a two-dimensional filtering process, the peaks of the energy clusters are found in one evolution step. This CA belongs to Wolfram class II cellular automata. Some quantitative parameters are given to optimize the architecture of the cellular automaton implemented in a commercial field programmable gate array (FPGA)

Relation Classification via Recurrent Neural Network

OpenAIRE

Zhang, Dongxu; Wang, Dong

2015-01-01

Deep learning has gained much success in sentence-level relation classification. For example, convolutional neural networks (CNN) have delivered competitive performance without much effort on feature engineering as the conventional pattern-based methods. Thus a lot of works have been produced based on CNN structures. However, a key issue that has not been well addressed by the CNN-based method is the lack of capability to learn temporal features, especially long-distance dependency between no...

Small-size pedestrian detection in large scene based on fast R-CNN

Science.gov (United States)

Wang, Shengke; Yang, Na; Duan, Lianghua; Liu, Lu; Dong, Junyu

2018-04-01

Pedestrian detection is a canonical sub-problem of object detection with high demand during recent years. Although recent deep learning object detectors such as Fast/Faster R-CNN have shown excellent performance for general object detection, they have limited success for small size pedestrian detection in large-view scene. We study that the insufficient resolution of feature maps lead to the unsatisfactory accuracy when handling small instances. In this paper, we investigate issues involving Fast R-CNN for pedestrian detection. Driven by the observations, we propose a very simple but effective baseline for pedestrian detection based on Fast R-CNN, employing the DPM detector to generate proposals for accuracy, and training a fast R-CNN style network to jointly optimize small size pedestrian detection with skip connection concatenating feature from different layers to solving coarseness of feature maps. And the accuracy is improved in our research for small size pedestrian detection in the real large scene.

Hardware Prototyping of Neural Network based Fetal Electrocardiogram Extraction

Science.gov (United States)

Hasan, M. A.; Reaz, M. B. I.

2012-01-01

The aim of this paper is to model the algorithm for Fetal ECG (FECG) extraction from composite abdominal ECG (AECG) using VHDL (Very High Speed Integrated Circuit Hardware Description Language) for FPGA (Field Programmable Gate Array) implementation. Artificial Neural Network that provides efficient and effective ways of separating FECG signal from composite AECG signal has been designed. The proposed method gives an accuracy of 93.7% for R-peak detection in FHR monitoring. The designed VHDL model is synthesized and fitted into Altera's Stratix II EP2S15F484C3 using the Quartus II version 8.0 Web Edition for FPGA implementation.

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

Design of a Tritium-in-air-monitor using field programmable gate arrays

International Nuclear Information System (INIS)

McNelles, Phillip; Lu, Lixuan

2015-01-01

Field Programmable Gate Arrays (FPGAs) have recently garnered significant interest for certain applications within the nuclear field. Some applications of these devices include Instrumentation and Control (I and C) systems, pulse measurement systems, particle detectors and health physics purposes. In CANada Deuterium Uranium (CANDU) nuclear power plants, the use of heavy water (D2O) as the moderator leads to the increased production of Tritium, which poses a health risk and must be monitored by Tritium-In-Air Monitors (TAMs). Traditional TAMs are mostly designed using microprocessors. More recent studies show that FPGAs could be a potential alternative to implement the electronic logic used in radiation detectors, such as the TAM, more effectively. In this paper, an FPGA-based TAM is designed and constructed in a laboratory setting using an FPGA-based cRIO system. New functionalities, such as the detection of Carbon-14 and the addition of noble gas compensation are incorporated into a new FPGA-based TAM. Additionally, all of the standard functions included in the original microprocessor-based TAM, such as tritium detection, gamma compensation, pump and air flow control, and background and thermal drift corrections were also implemented. The effectiveness of the new design is demonstrated through simulations as well as laboratory testing on the prototype system. (author)

Hierarchical graphical-based human pose estimation via local multi-resolution convolutional neural network

Science.gov (United States)

Zhu, Aichun; Wang, Tian; Snoussi, Hichem

2018-03-01

This paper addresses the problems of the graphical-based human pose estimation in still images, including the diversity of appearances and confounding background clutter. We present a new architecture for estimating human pose using a Convolutional Neural Network (CNN). Firstly, a Relative Mixture Deformable Model (RMDM) is defined by each pair of connected parts to compute the relative spatial information in the graphical model. Secondly, a Local Multi-Resolution Convolutional Neural Network (LMR-CNN) is proposed to train and learn the multi-scale representation of each body parts by combining different levels of part context. Thirdly, a LMR-CNN based hierarchical model is defined to explore the context information of limb parts. Finally, the experimental results demonstrate the effectiveness of the proposed deep learning approach for human pose estimation.

Hierarchical graphical-based human pose estimation via local multi-resolution convolutional neural network

Directory of Open Access Journals (Sweden)

Aichun Zhu

2018-03-01

Full Text Available This paper addresses the problems of the graphical-based human pose estimation in still images, including the diversity of appearances and confounding background clutter. We present a new architecture for estimating human pose using a Convolutional Neural Network (CNN. Firstly, a Relative Mixture Deformable Model (RMDM is defined by each pair of connected parts to compute the relative spatial information in the graphical model. Secondly, a Local Multi-Resolution Convolutional Neural Network (LMR-CNN is proposed to train and learn the multi-scale representation of each body parts by combining different levels of part context. Thirdly, a LMR-CNN based hierarchical model is defined to explore the context information of limb parts. Finally, the experimental results demonstrate the effectiveness of the proposed deep learning approach for human pose estimation.

Research on improving image recognition robustness by combining multiple features with associative memory

Science.gov (United States)

Guo, Dongwei; Wang, Zhe

2018-05-01

Convolutional neural networks (CNN) achieve great success in computer vision, it can learn hierarchical representation from raw pixels and has outstanding performance in various image recognition tasks [1]. However, CNN is easy to be fraudulent in terms of it is possible to produce images totally unrecognizable to human eyes that CNNs believe with near certainty are familiar objects. [2]. In this paper, an associative memory model based on multiple features is proposed. Within this model, feature extraction and classification are carried out by CNN, T-SNE and exponential bidirectional associative memory neural network (EBAM). The geometric features extracted from CNN and the digital features extracted from T-SNE are associated by EBAM. Thus we ensure the recognition of robustness by a comprehensive assessment of the two features. In our model, we can get only 8% error rate with fraudulent data. In systems that require a high safety factor or some key areas, strong robustness is extremely important, if we can ensure the image recognition robustness, network security will be greatly improved and the social production efficiency will be extremely enhanced.

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).

Dimensionality-varied convolutional neural network for spectral-spatial classification of hyperspectral data

Science.gov (United States)

Liu, Wanjun; Liang, Xuejian; Qu, Haicheng

2017-11-01

Hyperspectral image (HSI) classification is one of the most popular topics in remote sensing community. Traditional and deep learning-based classification methods were proposed constantly in recent years. In order to improve the classification accuracy and robustness, a dimensionality-varied convolutional neural network (DVCNN) was proposed in this paper. DVCNN was a novel deep architecture based on convolutional neural network (CNN). The input of DVCNN was a set of 3D patches selected from HSI which contained spectral-spatial joint information. In the following feature extraction process, each patch was transformed into some different 1D vectors by 3D convolution kernels, which were able to extract features from spectral-spatial data. The rest of DVCNN was about the same as general CNN and processed 2D matrix which was constituted by by all 1D data. So that the DVCNN could not only extract more accurate and rich features than CNN, but also fused spectral-spatial information to improve classification accuracy. Moreover, the robustness of network on water-absorption bands was enhanced in the process of spectral-spatial fusion by 3D convolution, and the calculation was simplified by dimensionality varied convolution. Experiments were performed on both Indian Pines and Pavia University scene datasets, and the results showed that the classification accuracy of DVCNN improved by 32.87% on Indian Pines and 19.63% on Pavia University scene than spectral-only CNN. The maximum accuracy improvement of DVCNN achievement was 13.72% compared with other state-of-the-art HSI classification methods, and the robustness of DVCNN on water-absorption bands noise was demonstrated.

The FPGA Pixel Array Detector

International Nuclear Information System (INIS)

Hromalik, Marianne S.; Green, Katherine S.; Philipp, Hugh T.; Tate, Mark W.; Gruner, Sol M.

2013-01-01

A proposed design for a reconfigurable x-ray Pixel Array Detector (PAD) is described. It operates by integrating a high-end commercial field programmable gate array (FPGA) into a 3-layer device along with a high-resistivity diode detection layer and a custom, application-specific integrated circuit (ASIC) layer. The ASIC layer contains an energy-discriminating photon-counting front end with photon hits streamed directly to the FPGA via a massively parallel, high-speed data connection. FPGA resources can be allocated to perform user defined tasks on the pixel data streams, including the implementation of a direct time autocorrelation function (ACF) with time resolution down to 100 ns. Using the FPGA at the front end to calculate the ACF reduces the required data transfer rate by several orders of magnitude when compared to a fast framing detector. The FPGA-ASIC high-speed interface, as well as the in-FPGA implementation of a real-time ACF for x-ray photon correlation spectroscopy experiments has been designed and simulated. A 16×16 pixel prototype of the ASIC has been fabricated and is being tested. -- Highlights: ► We describe the novelty and need for the FPGA Pixel Array Detector. ► We describe the specifications and design of the Diode, ASIC and FPGA layers. ► We highlight the Autocorrelation Function (ACF) for speckle as an example application. ► Simulated FPGA output calculates the ACF for different input bitstreams to 100 ns. ► Reduced data transfer rate by 640× and sped up real-time ACF by 100× other methods.

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%).

Deep convolutional neural network for classifying Fusarium wilt of radish from unmanned aerial vehicles

Science.gov (United States)

Ha, Jin Gwan; Moon, Hyeonjoon; Kwak, Jin Tae; Hassan, Syed Ibrahim; Dang, Minh; Lee, O. New; Park, Han Yong

2017-10-01

Recently, unmanned aerial vehicles (UAVs) have gained much attention. In particular, there is a growing interest in utilizing UAVs for agricultural applications such as crop monitoring and management. We propose a computerized system that is capable of detecting Fusarium wilt of radish with high accuracy. The system adopts computer vision and machine learning techniques, including deep learning, to process the images captured by UAVs at low altitudes and to identify the infected radish. The whole radish field is first segmented into three distinctive regions (radish, bare ground, and mulching film) via a softmax classifier and K-means clustering. Then, the identified radish regions are further classified into healthy radish and Fusarium wilt of radish using a deep convolutional neural network (CNN). In identifying radish, bare ground, and mulching film from a radish field, we achieved an accuracy of ≥97.4%. In detecting Fusarium wilt of radish, the CNN obtained an accuracy of 93.3%. It also outperformed the standard machine learning algorithm, obtaining 82.9% accuracy. Therefore, UAVs equipped with computational techniques are promising tools for improving the quality and efficiency of agriculture today.

Cardiac Arrhythmia Classification by Multi-Layer Perceptron and Convolution Neural Networks

Directory of Open Access Journals (Sweden)

Shalin Savalia

2018-05-01

Full Text Available The electrocardiogram (ECG plays an imperative role in the medical field, as it records heart signal over time and is used to discover numerous cardiovascular diseases. If a documented ECG signal has a certain irregularity in its predefined features, this is called arrhythmia, the types of which include tachycardia, bradycardia, supraventricular arrhythmias, and ventricular, etc. This has encouraged us to do research that consists of distinguishing between several arrhythmias by using deep neural network algorithms such as multi-layer perceptron (MLP and convolution neural network (CNN. The TensorFlow library that was established by Google for deep learning and machine learning is used in python to acquire the algorithms proposed here. The ECG databases accessible at PhysioBank.com and kaggle.com were used for training, testing, and validation of the MLP and CNN algorithms. The proposed algorithm consists of four hidden layers with weights, biases in MLP, and four-layer convolution neural networks which map ECG samples to the different classes of arrhythmia. The accuracy of the algorithm surpasses the performance of the current algorithms that have been developed by other cardiologists in both sensitivity and precision.

Cardiac Arrhythmia Classification by Multi-Layer Perceptron and Convolution Neural Networks.

Science.gov (United States)

Savalia, Shalin; Emamian, Vahid

2018-05-04

The electrocardiogram (ECG) plays an imperative role in the medical field, as it records heart signal over time and is used to discover numerous cardiovascular diseases. If a documented ECG signal has a certain irregularity in its predefined features, this is called arrhythmia, the types of which include tachycardia, bradycardia, supraventricular arrhythmias, and ventricular, etc. This has encouraged us to do research that consists of distinguishing between several arrhythmias by using deep neural network algorithms such as multi-layer perceptron (MLP) and convolution neural network (CNN). The TensorFlow library that was established by Google for deep learning and machine learning is used in python to acquire the algorithms proposed here. The ECG databases accessible at PhysioBank.com and kaggle.com were used for training, testing, and validation of the MLP and CNN algorithms. The proposed algorithm consists of four hidden layers with weights, biases in MLP, and four-layer convolution neural networks which map ECG samples to the different classes of arrhythmia. The accuracy of the algorithm surpasses the performance of the current algorithms that have been developed by other cardiologists in both sensitivity and precision.

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.

A Real-Time Solution to the Image Segmentation Problem: CNN-Movels

OpenAIRE

Iannizzotto, Giancarlo; Lanzafame, Pietro; Rosa, Francesco La

2007-01-01

In this work we have described a re-formulation of a 2D still-image segmentation algorithm, implemented on a single-layer CNN, previously proposed (Iannizzotto, 2003). This algorithm is able to step-over limitation inherent to the class of active contours: sensitivity to insignificant false edges or "edge fragmentation". The approach features an iterative process of uniform shrinking and deformation of the active contour. Guided by statistical properties of edgeness of the image pixels, the c...

Flexible experimental FPGA based platform

DEFF Research Database (Denmark)

Andersen, Karsten Holm; Nymand, Morten

2016-01-01

This paper presents an experimental flexible Field Programmable Gate Array (FPGA) based platform for testing and verifying digital controlled dc-dc converters. The platform supports different types of control strategies, dc-dc converter topologies and switching frequencies. The controller platform...... interface supporting configuration and reading of setup parameters, controller status and the acquisition memory in a simple way. The FPGA based platform, provides an easy way within education or research to use different digital control strategies and different converter topologies controlled by an FPGA...

Computer aided detection of clusters of microcalcifications on full field digital mammograms

International Nuclear Information System (INIS)

Ge Jun; Sahiner, Berkman; Hadjiiski, Lubomir M.; Chan, H.-P.; Wei Jun; Helvie, Mark A.; Zhou Chuan

2006-01-01

We are developing a computer-aided detection (CAD) system to identify microcalcification clusters (MCCs) automatically on full field digital mammograms (FFDMs). The CAD system includes six stages: preprocessing; image enhancement; segmentation of microcalcification candidates; false positive (FP) reduction for individual microcalcifications; regional clustering; and FP reduction for clustered microcalcifications. At the stage of FP reduction for individual microcalcifications, a truncated sum-of-squares error function was used to improve the efficiency and robustness of the training of an artificial neural network in our CAD system for FFDMs. At the stage of FP reduction for clustered microcalcifications, morphological features and features derived from the artificial neural network outputs were extracted from each cluster. Stepwise linear discriminant analysis (LDA) was used to select the features. An LDA classifier was then used to differentiate clustered microcalcifications from FPs. A data set of 96 cases with 192 images was collected at the University of Michigan. This data set contained 96 MCCs, of which 28 clusters were proven by biopsy to be malignant and 68 were proven to be benign. The data set was separated into two independent data sets for training and testing of the CAD system in a cross-validation scheme. When one data set was used to train and validate the convolution neural network (CNN) in our CAD system, the other data set was used to evaluate the detection performance. With the use of a truncated error metric, the training of CNN could be accelerated and the classification performance was improved. The CNN in combination with an LDA classifier could substantially reduce FPs with a small tradeoff in sensitivity. By using the free-response receiver operating characteristic methodology, it was found that our CAD system can achieve a cluster-based sensitivity of 70, 80, and 90 % at 0.21, 0.61, and 1.49 FPs/image, respectively. For case

Static facial expression recognition with convolution neural networks

Science.gov (United States)

Zhang, Feng; Chen, Zhong; Ouyang, Chao; Zhang, Yifei

2018-03-01

Facial expression recognition is a currently active research topic in the fields of computer vision, pattern recognition and artificial intelligence. In this paper, we have developed a convolutional neural networks (CNN) for classifying human emotions from static facial expression into one of the seven facial emotion categories. We pre-train our CNN model on the combined FER2013 dataset formed by train, validation and test set and fine-tune on the extended Cohn-Kanade database. In order to reduce the overfitting of the models, we utilized different techniques including dropout and batch normalization in addition to data augmentation. According to the experimental result, our CNN model has excellent classification performance and robustness for facial expression recognition.

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.

PSNet: prostate segmentation on MRI based on a convolutional neural network.

Science.gov (United States)

Tian, Zhiqiang; Liu, Lizhi; Zhang, Zhenfeng; Fei, Baowei

2018-04-01

Automatic segmentation of the prostate on magnetic resonance images (MRI) has many applications in prostate cancer diagnosis and therapy. We proposed 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, which uses prostate MRI and the corresponding ground truths as inputs. The learned CNN model can be used to make an inference for pixel-wise segmentation. Experiments were performed on three data sets, which contain prostate MRI of 140 patients. The proposed CNN model of prostate segmentation (PSNet) obtained a mean Dice similarity coefficient of [Formula: see text] as compared to the manually labeled ground truth. Experimental results show that the proposed model could yield satisfactory segmentation of the prostate on MRI.

Image processing for medical diagnosis using CNN

International Nuclear Information System (INIS)

Arena, Paolo; Basile, Adriano; Bucolo, Maide; Fortuna, Luigi

2003-01-01

Medical diagnosis is one of the most important area in which image processing procedures are usefully applied. Image processing is an important phase in order to improve the accuracy both for diagnosis procedure and for surgical operation. One of these fields is tumor/cancer detection by using Microarray analysis. The research studies in the Cancer Genetics Branch are mainly involved in a range of experiments including the identification of inherited mutations predisposing family members to malignant melanoma, prostate and breast cancer. In bio-medical field the real-time processing is very important, but often image processing is a quite time-consuming phase. Therefore techniques able to speed up the elaboration play an important rule. From this point of view, in this work a novel approach to image processing has been developed. The new idea is to use the Cellular Neural Networks to investigate on diagnostic images, like: Magnetic Resonance Imaging, Computed Tomography, and fluorescent cDNA microarray images

CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes

OpenAIRE

Li, Yuhong; Zhang, Xiaofan; Chen, Deming

2018-01-01

We propose a network for Congested Scene Recognition called CSRNet to provide a data-driven and deep learning method that can understand highly congested scenes and perform accurate count estimation as well as present high-quality density maps. The proposed CSRNet is composed of two major components: a convolutional neural network (CNN) as the front-end for 2D feature extraction and a dilated CNN for the back-end, which uses dilated kernels to deliver larger reception fields and to replace po...

Convolutional over Recurrent Encoder for Neural Machine Translation

Directory of Open Access Journals (Sweden)

Dakwale Praveen

2017-06-01

Full Text Available Neural machine translation is a recently proposed approach which has shown competitive results to traditional MT approaches. Standard neural MT is an end-to-end neural network where the source sentence is encoded by a recurrent neural network (RNN called encoder and the target words are predicted using another RNN known as decoder. Recently, various models have been proposed which replace the RNN encoder with a convolutional neural network (CNN. In this paper, we propose to augment the standard RNN encoder in NMT with additional convolutional layers in order to capture wider context in the encoder output. Experiments on English to German translation demonstrate that our approach can achieve significant improvements over a standard RNN-based baseline.

Vehicle Detection in Aerial Images Based on Region Convolutional Neural Networks and Hard Negative Example Mining.

Science.gov (United States)

Tang, Tianyu; Zhou, Shilin; Deng, Zhipeng; Zou, Huanxin; Lei, Lin

2017-02-10

Detecting vehicles in aerial imagery plays an important role in a wide range of applications. The current vehicle detection methods are mostly based on sliding-window search and handcrafted or shallow-learning-based features, having limited description capability and heavy computational costs. Recently, due to the powerful feature representations, region convolutional neural networks (CNN) based detection methods have achieved state-of-the-art performance in computer vision, especially Faster R-CNN. However, directly using it for vehicle detection in aerial images has many limitations: (1) region proposal network (RPN) in Faster R-CNN has poor performance for accurately locating small-sized vehicles, due to the relatively coarse feature maps; and (2) the classifier after RPN cannot distinguish vehicles and complex backgrounds well. In this study, an improved detection method based on Faster R-CNN is proposed in order to accomplish the two challenges mentioned above. Firstly, to improve the recall, we employ a hyper region proposal network (HRPN) to extract vehicle-like targets with a combination of hierarchical feature maps. Then, we replace the classifier after RPN by a cascade of boosted classifiers to verify the candidate regions, aiming at reducing false detection by negative example mining. We evaluate our method on the Munich vehicle dataset and the collected vehicle dataset, with improvements in accuracy and robustness compared to existing methods.

A digital optical phase-locked loop for diode lasers based on field programmable gate array

Science.gov (United States)

Xu, Zhouxiang; Zhang, Xian; Huang, Kaikai; Lu, Xuanhui

2012-09-01

We have designed and implemented a highly digital optical phase-locked loop (OPLL) for diode lasers in atom interferometry. The three parts of controlling circuit in this OPLL, including phase and frequency detector (PFD), loop filter and proportional integral derivative (PID) controller, are implemented in a single field programmable gate array chip. A structure type compatible with the model MAX9382/MCH12140 is chosen for PFD and pipeline and parallelism technology have been adapted in PID controller. Especially, high speed clock and twisted ring counter have been integrated in the most crucial part, the loop filter. This OPLL has the narrow beat note line width below 1 Hz, residual mean-square phase error of 0.14 rad2 and transition time of 100 μs under 10 MHz frequency step. A main innovation of this design is the completely digitalization of the whole controlling circuit in OPLL for diode lasers.

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%.

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

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.

Convolutional neural networks based on augmented training samples for synthetic aperture radar target recognition

Science.gov (United States)

Yan, Yue

2018-03-01

A synthetic aperture radar (SAR) automatic target recognition (ATR) method based on the convolutional neural networks (CNN) trained by augmented training samples is proposed. To enhance the robustness of CNN to various extended operating conditions (EOCs), the original training images are used to generate the noisy samples at different signal-to-noise ratios (SNRs), multiresolution representations, and partially occluded images. Then, the generated images together with the original ones are used to train a designed CNN for target recognition. The augmented training samples can contrapuntally improve the robustness of the trained CNN to the covered EOCs, i.e., the noise corruption, resolution variance, and partial occlusion. Moreover, the significantly larger training set effectively enhances the representation capability for other conditions, e.g., the standard operating condition (SOC), as well as the stability of the network. Therefore, better performance can be achieved by the proposed method for SAR ATR. For experimental evaluation, extensive experiments are conducted on the Moving and Stationary Target Acquisition and Recognition dataset under SOC and several typical EOCs.

Combining deep residual neural network features with supervised machine learning algorithms to classify diverse food image datasets.

Science.gov (United States)

McAllister, Patrick; Zheng, Huiru; Bond, Raymond; Moorhead, Anne

2018-04-01

Obesity is increasing worldwide and can cause many chronic conditions such as type-2 diabetes, heart disease, sleep apnea, and some cancers. Monitoring dietary intake through food logging is a key method to maintain a healthy lifestyle to prevent and manage obesity. Computer vision methods have been applied to food logging to automate image classification for monitoring dietary intake. In this work we applied pretrained ResNet-152 and GoogleNet convolutional neural networks (CNNs), initially trained using ImageNet Large Scale Visual Recognition Challenge (ILSVRC) dataset with MatConvNet package, to extract features from food image datasets; Food 5K, Food-11, RawFooT-DB, and Food-101. Deep features were extracted from CNNs and used to train machine learning classifiers including artificial neural network (ANN), support vector machine (SVM), Random Forest, and Naive Bayes. Results show that using ResNet-152 deep features with SVM with RBF kernel can accurately detect food items with 99.4% accuracy using Food-5K validation food image dataset and 98.8% with Food-5K evaluation dataset using ANN, SVM-RBF, and Random Forest classifiers. Trained with ResNet-152 features, ANN can achieve 91.34%, 99.28% when applied to Food-11 and RawFooT-DB food image datasets respectively and SVM with RBF kernel can achieve 64.98% with Food-101 image dataset. From this research it is clear that using deep CNN features can be used efficiently for diverse food item image classification. The work presented in this research shows that pretrained ResNet-152 features provide sufficient generalisation power when applied to a range of food image classification tasks. Copyright © 2018 Elsevier Ltd. All rights reserved.

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.

Strong convective storm nowcasting using a hybrid approach of convolutional neural network and hidden Markov model

Science.gov (United States)

Zhang, Wei; Jiang, Ling; Han, Lei

2018-04-01

Convective storm nowcasting refers to the prediction of the convective weather initiation, development, and decay in a very short term (typically 0 2 h) .Despite marked progress over the past years, severe convective storm nowcasting still remains a challenge. With the boom of machine learning, it has been well applied in various fields, especially convolutional neural network (CNN). In this paper, we build a servere convective weather nowcasting system based on CNN and hidden Markov model (HMM) using reanalysis meteorological data. The goal of convective storm nowcasting is to predict if there is a convective storm in 30min. In this paper, we compress the VDRAS reanalysis data to low-dimensional data by CNN as the observation vector of HMM, then obtain the development trend of strong convective weather in the form of time series. It shows that, our method can extract robust features without any artificial selection of features, and can capture the development trend of strong convective storm.

CNN Newsroom Classroom Guides. September 1-30, 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 August 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) truce in Northern Ireland, school censorship, scientific method, burial…

Pneumothorax detection in chest radiographs using convolutional neural networks

Science.gov (United States)

Blumenfeld, Aviel; Konen, Eli; Greenspan, Hayit

2018-02-01

This study presents a computer assisted diagnosis system for the detection of pneumothorax (PTX) in chest radiographs based on a convolutional neural network (CNN) for pixel classification. Using a pixel classification approach allows utilization of the texture information in the local environment of each pixel while training a CNN model on millions of training patches extracted from a relatively small dataset. The proposed system uses a pre-processing step of lung field segmentation to overcome the large variability in the input images coming from a variety of imaging sources and protocols. Using a CNN classification, suspected pixel candidates are extracted within each lung segment. A postprocessing step follows to remove non-physiological suspected regions and noisy connected components. The overall percentage of suspected PTX area was used as a robust global decision for the presence of PTX in each lung. The system was trained on a set of 117 chest x-ray images with ground truth segmentations of the PTX regions. The system was tested on a set of 86 images and reached diagnosis accuracy of AUC=0.95. Overall preliminary results are promising and indicate the growing ability of CAD based systems to detect findings in medical imaging on a clinical level accuracy.

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

Overview of deep learning in medical imaging.

Science.gov (United States)

Suzuki, Kenji

2017-09-01

The use of machine learning (ML) has been increasing rapidly in the medical imaging field, including computer-aided diagnosis (CAD), radiomics, and medical image analysis. Recently, an ML area called deep learning emerged in the computer vision field and became very popular in many fields. It started from an event in late 2012, when a deep-learning approach based on a convolutional neural network (CNN) won an overwhelming victory in the best-known worldwide computer vision competition, ImageNet Classification. Since then, researchers in virtually all fields, including medical imaging, have started actively participating in the explosively growing field of deep learning. In this paper, the area of deep learning in medical imaging is overviewed, including (1) what was changed in machine learning before and after the introduction of deep learning, (2) what is the source of the power of deep learning, (3) two major deep-learning models: a massive-training artificial neural network (MTANN) and a convolutional neural network (CNN), (4) similarities and differences between the two models, and (5) their applications to medical imaging. This review shows that ML with feature input (or feature-based ML) was dominant before the introduction of deep learning, and that the major and essential difference between ML before and after deep learning is the learning of image data directly without object segmentation or feature extraction; thus, it is the source of the power of deep learning, although the depth of the model is an important attribute. The class of ML with image input (or image-based ML) including deep learning has a long history, but recently gained popularity due to the use of the new terminology, deep learning. There are two major models in this class of ML in medical imaging, MTANN and CNN, which have similarities as well as several differences. In our experience, MTANNs were substantially more efficient in their development, had a higher performance, and required a

Motion camera based on a custom vision sensor and an FPGA architecture

Science.gov (United States)

Arias-Estrada, Miguel

1998-09-01

A digital camera for custom focal plane arrays was developed. The camera allows the test and development of analog or mixed-mode arrays for focal plane processing. The camera is used with a custom sensor for motion detection to implement a motion computation system. The custom focal plane sensor detects moving edges at the pixel level using analog VLSI techniques. The sensor communicates motion events using the event-address protocol associated to a temporal reference. In a second stage, a coprocessing architecture based on a field programmable gate array (FPGA) computes the time-of-travel between adjacent pixels. The FPGA allows rapid prototyping and flexible architecture development. Furthermore, the FPGA interfaces the sensor to a compact PC computer which is used for high level control and data communication to the local network. The camera could be used in applications such as self-guided vehicles, mobile robotics and smart surveillance systems. The programmability of the FPGA allows the exploration of further signal processing like spatial edge detection or image segmentation tasks. The article details the motion algorithm, the sensor architecture, the use of the event- address protocol for velocity vector computation and the FPGA architecture used in the motion camera system.

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

2018-04-01

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 79:2379-2391, 2018. © 2017 International Society for Magnetic Resonance in Medicine. © 2017 International Society for Magnetic Resonance in Medicine.

CNN Newsroom Classroom Guides. June 1-30, 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 June 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) Congressman Dan Rostenkowski, D-Day, cars and Singapore, Rodney King civil…

A novel method combining cellular neural networks and the coupled nonlinear oscillators' paradigm involving a related bifurcation analysis for robust image contrast enhancement in dynamically changing difficult visual environments

International Nuclear Information System (INIS)

Chedjou, Jean Chamberlain; Kyamakya, Kyandoghere

2010-01-01

It is well known that a machine vision-based analysis of a dynamic scene, for example in the context of advanced driver assistance systems (ADAS), does require real-time processing capabilities. Therefore, the system used must be capable of performing both robust and ultrafast analyses. Machine vision in ADAS must fulfil the above requirements when dealing with a dynamically changing visual context (i.e. driving in darkness or in a foggy environment, etc). Among the various challenges related to the analysis of a dynamic scene, this paper focuses on contrast enhancement, which is a well-known basic operation to improve the visual quality of an image (dynamic or static) suffering from poor illumination. The key objective is to develop a systematic and fundamental concept for image contrast enhancement that should be robust despite a dynamic environment and that should fulfil the real-time constraints by ensuring an ultrafast analysis. It is demonstrated that the new approach developed in this paper is capable of fulfilling the expected requirements. The proposed approach combines the good features of the 'coupled oscillators'-based signal processing paradigm with the good features of the 'cellular neural network (CNN)'-based one. The first paradigm in this combination is the 'master system' and consists of a set of coupled nonlinear ordinary differential equations (ODEs) that are (a) the so-called 'van der Pol oscillator' and (b) the so-called 'Duffing oscillator'. It is then implemented or realized on top of a 'slave system' platform consisting of a CNN-processors platform. An offline bifurcation analysis is used to find out, a priori, the windows of parameter settings in which the coupled oscillator system exhibits the best and most appropriate behaviours of interest for an optimal resulting image processing quality. In the frame of the extensive bifurcation analysis carried out, analytical formulae have been derived, which are capable of determining the various

Hybrid information privacy system: integration of chaotic neural network and RSA coding

Science.gov (United States)

Hsu, Ming-Kai; Willey, Jeff; Lee, Ting N.; Szu, Harold H.

2005-03-01

Electronic mails are adopted worldwide; most are easily hacked by hackers. In this paper, we purposed a free, fast and convenient hybrid privacy system to protect email communication. The privacy system is implemented by combining private security RSA algorithm with specific chaos neural network encryption process. The receiver can decrypt received email as long as it can reproduce the specified chaos neural network series, so called spatial-temporal keys. The chaotic typing and initial seed value of chaos neural network series, encrypted by the RSA algorithm, can reproduce spatial-temporal keys. The encrypted chaotic typing and initial seed value are hidden in watermark mixed nonlinearly with message media, wrapped with convolution error correction codes for wireless 3rd generation cellular phones. The message media can be an arbitrary image. The pattern noise has to be considered during transmission and it could affect/change the spatial-temporal keys. Since any change/modification on chaotic typing or initial seed value of chaos neural network series is not acceptable, the RSA codec system must be robust and fault-tolerant via wireless channel. The robust and fault-tolerant properties of chaos neural networks (CNN) were proved by a field theory of Associative Memory by Szu in 1997. The 1-D chaos generating nodes from the logistic map having arbitrarily negative slope a = p/q generating the N-shaped sigmoid was given first by Szu in 1992. In this paper, we simulated the robust and fault-tolerance properties of CNN under additive noise and pattern noise. We also implement a private version of RSA coding and chaos encryption process on messages.

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.

An FPGA-Integrated Time-to-Digital Converter Based on a Ring Oscillator for Programmable Delay Line Resolution Measurement

Directory of Open Access Journals (Sweden)

Chao Chen

2014-01-01

Full Text Available We describe the architecture of a time-to-digital converter (TDC, specially intended to measure the delay resolution of a programmable delay line (PDL. The configuration, which consists of a ring oscillator, a frequency divider (FD, and a period measurement circuit (PMC, is implemented in a field programmable gate array (FPGA device. The ring oscillator realized in loop containing a PDL and a look-up table (LUT generates periodic oscillatory pulses. The FD amplifies the oscillatory period from nanosecond range to microsecond range. The time-to-digital conversion is based on counting the number of clock cycles between two consecutive pulses of the FD by the PMC. Experiments have been conducted to verify the performance of the TDC. The achieved relative errors for four PDLs are within 0.50%–1.21% and the TDC has an equivalent resolution of about 0.4 ps.

A digital optical phase-locked loop for diode lasers based on field programmable gate array

Energy Technology Data Exchange (ETDEWEB)

Xu Zhouxiang; Zhang Xian; Huang Kaikai; Lu Xuanhui [Physics Department, Zhejiang University, Hangzhou, 310027 (China)

2012-09-15

We have designed and implemented a highly digital optical phase-locked loop (OPLL) for diode lasers in atom interferometry. The three parts of controlling circuit in this OPLL, including phase and frequency detector (PFD), loop filter and proportional integral derivative (PID) controller, are implemented in a single field programmable gate array chip. A structure type compatible with the model MAX9382/MCH12140 is chosen for PFD and pipeline and parallelism technology have been adapted in PID controller. Especially, high speed clock and twisted ring counter have been integrated in the most crucial part, the loop filter. This OPLL has the narrow beat note line width below 1 Hz, residual mean-square phase error of 0.14 rad{sup 2} and transition time of 100 {mu}s under 10 MHz frequency step. A main innovation of this design is the completely digitalization of the whole controlling circuit in OPLL for diode lasers.

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...

Learning-induced pattern classification in a chaotic neural network

International Nuclear Information System (INIS)

Li, Yang; Zhu, Ping; Xie, Xiaoping; He, Guoguang; Aihara, Kazuyuki

2012-01-01

In this Letter, we propose a Hebbian learning rule with passive forgetting (HLRPF) for use in a chaotic neural network (CNN). We then define the indices based on the Euclidean distance to investigate the evolution of the weights in a simplified way. Numerical simulations demonstrate that, under suitable external stimulations, the CNN with the proposed HLRPF acts as a fuzzy-like pattern classifier that performs much better than an ordinary CNN. The results imply relationship between learning and recognition. -- Highlights: ► Proposing a Hebbian learning rule with passive forgetting (HLRPF). ► Defining indices to investigate the evolution of the weights simply. ► The chaotic neural network with HLRPF acts as a fuzzy-like pattern classifier. ► The pattern classifier ability of the network is improved much.

FPGA development board for applications in cosmic rays physics

International Nuclear Information System (INIS)

Angelov, Ivo; Damov, Krasimir; Dimitrova, Svetla

2013-01-01

The modern experiments in cosmic rays and particle physics are usually performed with large number of detectors and signal processing have to be done by complex electronics. The analog signals from the detectors are converted to digital (by discriminators or fast ADC) and connected to different type of logic implemented in FPGA (Field Programmable Gate Arrays). A FPGA development board based on Xilinx XC3S50AN was designed, assembled and tested. The board will be used for developing a modern registering controller (to replace the existing now) for the muon telescope in the University and can be used for other experiments in cosmic rays physics when fast digital pulses have to be processed. Keywords: FPGA, Spartan3A, muon telescope, cosmic rays variations

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.

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

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.

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.

Real-time machine vision system using FPGA and soft-core processor

Science.gov (United States)

Malik, Abdul Waheed; Thörnberg, Benny; Meng, Xiaozhou; Imran, Muhammad

2012-06-01

This paper presents a machine vision system for real-time computation of distance and angle of a camera from reference points in the environment. Image pre-processing, component labeling and feature extraction modules were modeled at Register Transfer (RT) level and synthesized for implementation on field programmable gate arrays (FPGA). The extracted image component features were sent from the hardware modules to a soft-core processor, MicroBlaze, for computation of distance and angle. A CMOS imaging sensor operating at a clock frequency of 27MHz was used in our experiments to produce a video stream at the rate of 75 frames per second. Image component labeling and feature extraction modules were running in parallel having a total latency of 13ms. The MicroBlaze was interfaced with the component labeling and feature extraction modules through Fast Simplex Link (FSL). The latency for computing distance and angle of camera from the reference points was measured to be 2ms on the MicroBlaze, running at 100 MHz clock frequency. In this paper, we present the performance analysis, device utilization and power consumption for the designed system. The FPGA based machine vision system that we propose has high frame speed, low latency and a power consumption that is much lower compared to commercially available smart camera solutions.

Segmented Routing for Speed-Performance and Routability in Field-Programmable Gate Arrays

Directory of Open Access Journals (Sweden)

Stephen Brown

1996-01-01

Full Text Available This paper addresses several issues involved for routing in Field-Programmable Gate Arrays (FPGAs that have both horizontal and vertical routing channels, with wire segments of various lengths. Routing is studied by using CAD routing tools to map a set of benchmark circuits into FPGAs, and measuring the effects that various parameters of the CAD tools have on the implementation of the circuits. A two-stage routing strategy of global followed by detailed routing is used, and the effects of both of these CAD stages are discussed, with emphasis on detailed routing. We present a new detailed routing algorithm designed specifically for the types of routing structures found in the most recent generation of FPGAs, and show that the new algorithm achieves significantly better results than previously published FPGA routers with respect to the speed-performance of implemented circuits.

A field programmable gate array unit for the diagnosis and control of neoclassical tearing modes on MAST

Energy Technology Data Exchange (ETDEWEB)

O' Gorman, T.; Gibson, K. J.; Snape, J. A. [York Plasma Institute, Department of Physics, University of York, York YO10 5DD (United Kingdom); Naylor, G.; Huang, B.; McArdle, G. J.; Scannell, R.; Shibaev, S.; Thomas-Davies, N. [EURATOM/CCFE Fusion Association, Culham Science Centre, Oxfordshire OX14 3DB (United Kingdom)

2012-10-15

A real-time system has been developed to trigger both the MAST Thomson scattering (TS) system and the plasma control system on the phase and amplitude of neoclassical tearing modes (NTMs), extending the capabilities of the original system. This triggering system determines the phase and amplitude of a given NTM using magnetic coils at different toroidal locations. Real-time processing of the raw magnetic data occurs on a low cost field programmable gate array (FPGA) based unit which permits triggering of the TS lasers on specific amplitudes and phases of NTM evolution. The MAST plasma control system can receive a separate trigger from the FPGA unit that initiates a vertical shift of the MAST magnetic axis. Such shifts have fully removed m/n= 2/1 NTMs instabilities on a number of MAST discharges.

FPGA-based reconfigurable processor for ultrafast interlaced ultrasound and photoacoustic imaging.

Science.gov (United States)

Alqasemi, Umar; Li, Hai; Aguirre, Andrés; Zhu, Quing

2012-07-01

In this paper, we report, to the best of our knowledge, a unique field-programmable gate array (FPGA)-based reconfigurable processor for real-time interlaced co-registered ultrasound and photoacoustic imaging and its application in imaging tumor dynamic response. The FPGA is used to control, acquire, store, delay-and-sum, and transfer the data for real-time co-registered imaging. The FPGA controls the ultrasound transmission and ultrasound and photoacoustic data acquisition process of a customized 16-channel module that contains all of the necessary analog and digital circuits. The 16-channel module is one of multiple modules plugged into a motherboard; their beamformed outputs are made available for a digital signal processor (DSP) to access using an external memory interface (EMIF). The FPGA performs a key role through ultrafast reconfiguration and adaptation of its structure to allow real-time switching between the two imaging modes, including transmission control, laser synchronization, internal memory structure, beamforming, and EMIF structure and memory size. It performs another role by parallel accessing of internal memories and multi-thread processing to reduce the transfer of data and the processing load on the DSP. Furthermore, because the laser will be pulsing even during ultrasound pulse-echo acquisition, the FPGA ensures that the laser pulses are far enough from the pulse-echo acquisitions by appropriate time-division multiplexing (TDM). A co-registered ultrasound and photoacoustic imaging system consisting of four FPGA modules (64-channels) is constructed, and its performance is demonstrated using phantom targets and in vivo mouse tumor models.

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

On the use of multistability for image processing

International Nuclear Information System (INIS)

Morfu, S.; Nofiele, B.; Marquie, P.

2007-01-01

We use the multistable property of a Cellular Nonlinear Network (CNN) to extract the regions of interest of an image representing the radiography of a soldering. We also propose the electronic implementation of the elementary cell of this CNN for a further electronic implementation of this network. We conclude with a discussion which enlarges the potential applications of this elementary cell in the field of nonlinear physics

Knowledge-guided golf course detection using a convolutional neural network fine-tuned on temporally augmented data

Science.gov (United States)

Chen, Jingbo; Wang, Chengyi; Yue, Anzhi; Chen, Jiansheng; He, Dongxu; Zhang, Xiuyan

2017-10-01

The tremendous success of deep learning models such as convolutional neural networks (CNNs) in computer vision provides a method for similar problems in the field of remote sensing. Although research on repurposing pretrained CNN to remote sensing tasks is emerging, the scarcity of labeled samples and the complexity of remote sensing imagery still pose challenges. We developed a knowledge-guided golf course detection approach using a CNN fine-tuned on temporally augmented data. The proposed approach is a combination of knowledge-driven region proposal, data-driven detection based on CNN, and knowledge-driven postprocessing. To confront data complexity, knowledge-derived cooccurrence, composition, and area-based rules are applied sequentially to propose candidate golf regions. To confront sample scarcity, we employed data augmentation in the temporal domain, which extracts samples from multitemporal images. The augmented samples were then used to fine-tune a pretrained CNN for golf detection. Finally, commission error was further suppressed by postprocessing. Experiments conducted on GF-1 imagery prove the effectiveness of the proposed approach.

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.