WorldWideScience

Sample records for single spatial convolution

  1. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition.

    Science.gov (United States)

    He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing; Sun, Jian

    2015-09-01

    Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224 × 224) input image. This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale. In this work, we equip the networks with another pooling strategy, "spatial pyramid pooling", to eliminate the above requirement. The new network structure, called SPP-net, can generate a fixed-length representation regardless of image size/scale. Pyramid pooling is also robust to object deformations. With these advantages, SPP-net should in general improve all CNN-based image classification methods. On the ImageNet 2012 dataset, we demonstrate that SPP-net boosts the accuracy of a variety of CNN architectures despite their different designs. On the Pascal VOC 2007 and Caltech101 datasets, SPP-net achieves state-of-the-art classification results using a single full-image representation and no fine-tuning. The power of SPP-net is also significant in object detection. Using SPP-net, we compute the feature maps from the entire image only once, and then pool features in arbitrary regions (sub-images) to generate fixed-length representations for training the detectors. This method avoids repeatedly computing the convolutional features. In processing test images, our method is 24-102 × faster than the R-CNN method, while achieving better or comparable accuracy on Pascal VOC 2007. In ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2014, our methods rank #2 in object detection and #3 in image classification among all 38 teams. This manuscript also introduces the improvement made for this competition.

  2. Single-Cell Phenotype Classification Using Deep Convolutional Neural Networks.

    Science.gov (United States)

    Dürr, Oliver; Sick, Beate

    2016-10-01

    Deep learning methods are currently outperforming traditional state-of-the-art computer vision algorithms in diverse applications and recently even surpassed human performance in object recognition. Here we demonstrate the potential of deep learning methods to high-content screening-based phenotype classification. We trained a deep learning classifier in the form of convolutional neural networks with approximately 40,000 publicly available single-cell images from samples treated with compounds from four classes known to lead to different phenotypes. The input data consisted of multichannel images. The construction of appropriate feature definitions was part of the training and carried out by the convolutional network, without the need for expert knowledge or handcrafted features. We compare our results against the recent state-of-the-art pipeline in which predefined features are extracted from each cell using specialized software and then fed into various machine learning algorithms (support vector machine, Fisher linear discriminant, random forest) for classification. The performance of all classification approaches is evaluated on an untouched test image set with known phenotype classes. Compared to the best reference machine learning algorithm, the misclassification rate is reduced from 8.9% to 6.6%. © 2016 Society for Laboratory Automation and Screening.

  3. 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.

  4. Single Image Super-Resolution Based on Multi-Scale Competitive Convolutional Neural Network.

    Science.gov (United States)

    Du, Xiaofeng; Qu, Xiaobo; He, Yifan; Guo, Di

    2018-03-06

    Deep convolutional neural networks (CNNs) are successful in single-image super-resolution. Traditional CNNs are limited to exploit multi-scale contextual information for image reconstruction due to the fixed convolutional kernel in their building modules. To restore various scales of image details, we enhance the multi-scale inference capability of CNNs by introducing competition among multi-scale convolutional filters, and build up a shallow network under limited computational resources. The proposed network has the following two advantages: (1) the multi-scale convolutional kernel provides the multi-context for image super-resolution, and (2) the maximum competitive strategy adaptively chooses the optimal scale of information for image reconstruction. Our experimental results on image super-resolution show that the performance of the proposed network outperforms the state-of-the-art methods.

  5. Single-Image Super Resolution for Multispectral Remote Sensing Data Using Convolutional Neural Networks

    Science.gov (United States)

    Liebel, L.; Körner, M.

    2016-06-01

    In optical remote sensing, spatial resolution of images is crucial for numerous applications. Space-borne systems are most likely to be affected by a lack of spatial resolution, due to their natural disadvantage of a large distance between the sensor and the sensed object. Thus, methods for single-image super resolution are desirable to exceed the limits of the sensor. Apart from assisting visual inspection of datasets, post-processing operations—e.g., segmentation or feature extraction—can benefit from detailed and distinguishable structures. In this paper, we show that recently introduced state-of-the-art approaches for single-image super resolution of conventional photographs, making use of deep learning techniques, such as convolutional neural networks (CNN), can successfully be applied to remote sensing data. With a huge amount of training data available, end-to-end learning is reasonably easy to apply and can achieve results unattainable using conventional handcrafted algorithms. We trained our CNN on a specifically designed, domain-specific dataset, in order to take into account the special characteristics of multispectral remote sensing data. This dataset consists of publicly available SENTINEL-2 images featuring 13 spectral bands, a ground resolution of up to 10m, and a high radiometric resolution and thus satisfying our requirements in terms of quality and quantity. In experiments, we obtained results superior compared to competing approaches trained on generic image sets, which failed to reasonably scale satellite images with a high radiometric resolution, as well as conventional interpolation methods.

  6. SINGLE-IMAGE SUPER RESOLUTION FOR MULTISPECTRAL REMOTE SENSING DATA USING CONVOLUTIONAL NEURAL NETWORKS

    Directory of Open Access Journals (Sweden)

    L. Liebel

    2016-06-01

    Full Text Available In optical remote sensing, spatial resolution of images is crucial for numerous applications. Space-borne systems are most likely to be affected by a lack of spatial resolution, due to their natural disadvantage of a large distance between the sensor and the sensed object. Thus, methods for single-image super resolution are desirable to exceed the limits of the sensor. Apart from assisting visual inspection of datasets, post-processing operations—e.g., segmentation or feature extraction—can benefit from detailed and distinguishable structures. In this paper, we show that recently introduced state-of-the-art approaches for single-image super resolution of conventional photographs, making use of deep learning techniques, such as convolutional neural networks (CNN, can successfully be applied to remote sensing data. With a huge amount of training data available, end-to-end learning is reasonably easy to apply and can achieve results unattainable using conventional handcrafted algorithms. We trained our CNN on a specifically designed, domain-specific dataset, in order to take into account the special characteristics of multispectral remote sensing data. This dataset consists of publicly available SENTINEL-2 images featuring 13 spectral bands, a ground resolution of up to 10m, and a high radiometric resolution and thus satisfying our requirements in terms of quality and quantity. In experiments, we obtained results superior compared to competing approaches trained on generic image sets, which failed to reasonably scale satellite images with a high radiometric resolution, as well as conventional interpolation methods.

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

    Directory of Open Access Journals (Sweden)

    Shaohui Mei

    2017-11-01

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

  8. Convolutional Deep Belief Networks for Single-Cell/Object Tracking in Computational Biology and Computer Vision

    OpenAIRE

    Zhong, Bineng; Pan, Shengnan; Zhang, Hongbo; Wang, Tian; Du, Jixiang; Chen, Duansheng; Cao, Liujuan

    2016-01-01

    In this paper, we propose deep architecture to dynamically learn the most discriminative features from data for both single-cell and object tracking in computational biology and computer vision. Firstly, the discriminative features are automatically learned via a convolutional deep belief network (CDBN). Secondly, we design a simple yet effective method to transfer features learned from CDBNs on the source tasks for generic purpose to the object tracking tasks using only limited amount of tra...

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

    Directory of Open Access Journals (Sweden)

    Ying Li

    2017-01-01

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

  10. Convolutional Deep Belief Networks for Single-Cell/Object Tracking in Computational Biology and Computer Vision.

    Science.gov (United States)

    Zhong, Bineng; Pan, Shengnan; Zhang, Hongbo; Wang, Tian; Du, Jixiang; Chen, Duansheng; Cao, Liujuan

    2016-01-01

    In this paper, we propose deep architecture to dynamically learn the most discriminative features from data for both single-cell and object tracking in computational biology and computer vision. Firstly, the discriminative features are automatically learned via a convolutional deep belief network (CDBN). Secondly, we design a simple yet effective method to transfer features learned from CDBNs on the source tasks for generic purpose to the object tracking tasks using only limited amount of training data. Finally, to alleviate the tracker drifting problem caused by model updating, we jointly consider three different types of positive samples. Extensive experiments validate the robustness and effectiveness of the proposed method.

  11. SPATIAL-SPECTRAL CLASSIFICATION BASED ON THE UNSUPERVISED CONVOLUTIONAL SPARSE AUTO-ENCODER FOR HYPERSPECTRAL REMOTE SENSING IMAGERY

    Directory of Open Access Journals (Sweden)

    X. Han

    2016-06-01

    Full Text Available Current hyperspectral remote sensing imagery spatial-spectral classification methods mainly consider concatenating the spectral information vectors and spatial information vectors together. However, the combined spatial-spectral information vectors may cause information loss and concatenation deficiency for the classification task. To efficiently represent the spatial-spectral feature information around the central pixel within a neighbourhood window, the unsupervised convolutional sparse auto-encoder (UCSAE with window-in-window selection strategy is proposed in this paper. Window-in-window selection strategy selects the sub-window spatial-spectral information for the spatial-spectral feature learning and extraction with the sparse auto-encoder (SAE. Convolution mechanism is applied after the SAE feature extraction stage with the SAE features upon the larger outer window. The UCSAE algorithm was validated by two common hyperspectral imagery (HSI datasets – Pavia University dataset and the Kennedy Space Centre (KSC dataset, which shows an improvement over the traditional hyperspectral spatial-spectral classification methods.

  12. Spatial aggregation of holistically-nested convolutional neural networks for automated pancreas localization and segmentation.

    Science.gov (United States)

    Roth, Holger R; Lu, Le; Lay, Nathan; Harrison, Adam P; Farag, Amal; Sohn, Andrew; Summers, Ronald M

    2018-04-01

    Accurate and automatic organ segmentation from 3D radiological scans is an important yet challenging problem for medical image analysis. Specifically, as a small, soft, and flexible abdominal organ, the pancreas demonstrates very high inter-patient anatomical variability in both its shape and volume. This inhibits traditional automated segmentation methods from achieving high accuracies, especially compared to the performance obtained for other organs, such as the liver, heart or kidneys. To fill this gap, we present an automated system from 3D computed tomography (CT) volumes that is based on a two-stage cascaded approach-pancreas localization and pancreas segmentation. For the first step, we localize the pancreas from the entire 3D CT scan, providing a reliable bounding box for the more refined segmentation step. We introduce a fully deep-learning approach, based on an efficient application of holistically-nested convolutional networks (HNNs) on the three orthogonal axial, sagittal, and coronal views. The resulting HNN per-pixel probability maps are then fused using pooling to reliably produce a 3D bounding box of the pancreas that maximizes the recall. We show that our introduced localizer compares favorably to both a conventional non-deep-learning method and a recent hybrid approach based on spatial aggregation of superpixels using random forest classification. The second, segmentation, phase operates within the computed bounding box and integrates semantic mid-level cues of deeply-learned organ interior and boundary maps, obtained by two additional and separate realizations of HNNs. By integrating these two mid-level cues, our method is capable of generating boundary-preserving pixel-wise class label maps that result in the final pancreas segmentation. Quantitative evaluation is performed on a publicly available dataset of 82 patient CT scans using 4-fold cross-validation (CV). We achieve a (mean  ±  std. dev.) Dice similarity coefficient (DSC) of 81.27

  13. A deep convolutional neural network approach to single-particle recognition in cryo-electron microscopy.

    Science.gov (United States)

    Zhu, Yanan; Ouyang, Qi; Mao, Youdong

    2017-07-21

    Single-particle cryo-electron microscopy (cryo-EM) has become a mainstream tool for the structural determination of biological macromolecular complexes. However, high-resolution cryo-EM reconstruction often requires hundreds of thousands of single-particle images. Particle extraction from experimental micrographs thus can be laborious and presents a major practical bottleneck in cryo-EM structural determination. Existing computational methods for particle picking often use low-resolution templates for particle matching, making them susceptible to reference-dependent bias. It is critical to develop a highly efficient template-free method for the automatic recognition of particle images from cryo-EM micrographs. We developed a deep learning-based algorithmic framework, DeepEM, for single-particle recognition from noisy cryo-EM micrographs, enabling automated particle picking, selection and verification in an integrated fashion. The kernel of DeepEM is built upon a convolutional neural network (CNN) composed of eight layers, which can be recursively trained to be highly "knowledgeable". Our approach exhibits an improved performance and accuracy when tested on the standard KLH dataset. Application of DeepEM to several challenging experimental cryo-EM datasets demonstrated its ability to avoid the selection of un-wanted particles and non-particles even when true particles contain fewer features. The DeepEM methodology, derived from a deep CNN, allows automated particle extraction from raw cryo-EM micrographs in the absence of a template. It demonstrates an improved performance, objectivity and accuracy. Application of this novel method is expected to free the labor involved in single-particle verification, significantly improving the efficiency of cryo-EM data processing.

  14. A Convolution Tree with Deconvolution Branches: Exploiting Geometric Relationships for Single Shot Keypoint Detection

    OpenAIRE

    Kumar, Amit; Chellappa, Rama

    2017-01-01

    Recently, Deep Convolution Networks (DCNNs) have been applied to the task of face alignment and have shown potential for learning improved feature representations. Although deeper layers can capture abstract concepts like pose, it is difficult to capture the geometric relationships among the keypoints in DCNNs. In this paper, we propose a novel convolution-deconvolution network for facial keypoint detection. Our model predicts the 2D locations of the keypoints and their individual visibility ...

  15. Fundamentals of convolutional coding

    CERN Document Server

    Johannesson, Rolf

    2015-01-01

    Fundamentals of Convolutional Coding, Second Edition, regarded as a bible of convolutional coding brings you a clear and comprehensive discussion of the basic principles of this field * Two new chapters on low-density parity-check (LDPC) convolutional codes and iterative coding * Viterbi, BCJR, BEAST, list, and sequential decoding of convolutional codes * Distance properties of convolutional codes * Includes a downloadable solutions manual

  16. 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

    2018-02-17

    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.

  17. Fast Convolution Module (Fast Convolution Module)

    National Research Council Canada - National Science Library

    Bierens, L

    1997-01-01

    This report describes the design and realisation of a real-time range azimuth compression module, the so-called 'Fast Convolution Module', based on the fast convolution algorithm developed at TNO-FEL...

  18. 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

  19. Profiling convoluted single-dimension proton NMR spectra: a Plackett-Burman approach for assessing quantification error of metabolites in complex mixtures with application to cell culture.

    Science.gov (United States)

    Sokolenko, Stanislav; Blondeel, Eric J M; Azlah, Nada; George, Ben; Schulze, Steffen; Chang, David; Aucoin, Marc G

    2014-04-01

    Single-dimension hydrogen, or proton, nuclear magnetic resonance spectroscopy (1D-(1)H NMR) has become an attractive option for characterizing the full range of components in complex mixtures of small molecular weight compounds due to its relative simplicity, speed, spectral reproducibility, and noninvasive sample preparation protocols compared to alternative methods. One challenge associated with this method is the overlap of NMR resonances leading to "convoluted" spectra. While this can be mitigated through "targeted profiling", there is still the possibility of increased quantification error. This work presents the application of a Plackett-Burman experimental design for the robust estimation of precision and accuracy of 1D-(1)H NMR compound quantification in synthetic mixtures, with application to mammalian cell culture supernatant. A single, 20 sample experiment was able to provide a sufficient estimate of bias and variability at different metabolite concentrations. Two major sources of bias were identified: incorrect interpretation of singlet resonances and the quantification of resonances from protons in close proximity to labile protons. Furthermore, decreases in measurement accuracy and precision could be observed with decreasing concentration for a small fraction of the components as a result of their particular convolution patterns. Finally, the importance of a priori concentration estimates is demonstrated through the example of interpreting acetate metabolite trends from a bioreactor cultivation of Chinese hamster ovary cells expressing a recombinant antibody.

  20. Deep learning for steganalysis via convolutional neural networks

    Science.gov (United States)

    Qian, Yinlong; Dong, Jing; Wang, Wei; Tan, Tieniu

    2015-03-01

    Current work on steganalysis for digital images is focused on the construction of complex handcrafted features. This paper proposes a new paradigm for steganalysis to learn features automatically via deep learning models. We novelly propose a customized Convolutional Neural Network for steganalysis. The proposed model can capture the complex dependencies that are useful for steganalysis. Compared with existing schemes, this model can automatically learn feature representations with several convolutional layers. The feature extraction and classification steps are unified under a single architecture, which means the guidance of classification can be used during the feature extraction step. We demonstrate the effectiveness of the proposed model on three state-of-theart spatial domain steganographic algorithms - HUGO, WOW, and S-UNIWARD. Compared to the Spatial Rich Model (SRM), our model achieves comparable performance on BOSSbase and the realistic and large ImageNet database.

  1. Spatially incoherent single channel digital Fourier holography.

    Science.gov (United States)

    Kelner, Roy; Rosen, Joseph

    2012-09-01

    We present a new method for recording digital Fourier holograms under incoherent illumination. A single exposure recorded by a digital camera is sufficient to record a real-valued hologram that encodes the complete three-dimensional properties of an object.

  2. Dispersal and spatial heterogeneity: Single species

    Science.gov (United States)

    DeAngelis, Don; Ni, Wei-Ming; Zhang, Bo

    2016-01-01

    A recent result for a reaction-diffusion equation is that a population diffusing at any rate in an environment in which resources vary spatially will reach a higher total equilibrium biomass than the population in an environment in which the same total resources are distributed homogeneously. This has so far been proven by Lou for the case in which the reaction term has only one parameter, m(x)">m(x)m(x), varying with spatial location x">xx, which serves as both the intrinsic growth rate coefficient and carrying capacity of the population. However, this striking result seems rather limited when applies to real populations. In order to make the model more relevant for ecologists, we consider a logistic reaction term, with two parameters, r(x)">r(x)r(x) for intrinsic growth rate, and K(x)">K(x)K(x) for carrying capacity. When r(x)">r(x)r(x) and K(x)">K(x)K(x) are proportional, the logistic equation takes a particularly simple form, and the earlier result still holds. In this paper we have established the result for the more general case of a positive correlation between r(x)">r(x)r(x) and K(x)">K(x)K(x) when dispersal rate is small. We review natural and laboratory systems to which these results are relevant and discuss the implications of the results to population theory and conservation ecology.

  3. Spatial Attention Enhances Perceptual Processing of Single-Element Displays

    Science.gov (United States)

    Bacon, William; Johnston, James C.; Remington, Roger W.; Null, Cynthia H. (Technical Monitor)

    1994-01-01

    Shiu and Pashler (1993) reported that precueing masked, single-element displays had negligible effects on identification accuracy. They argued that spatial attention does not actually enhance stimulus perceptibility, but only reduces decision noise. Alternatively, such negative results may arise if cues are sub-optimal, or if masks place an insufficient premium on timely deployment of attention. We report results showing that valid cueing enhances processing of even single-element displays. Spatial attention does indeed enhance perceptual processes.

  4. Linear optical quantum computing in a single spatial mode.

    Science.gov (United States)

    Humphreys, Peter C; Metcalf, Benjamin J; Spring, Justin B; Moore, Merritt; Jin, Xian-Min; Barbieri, Marco; Kolthammer, W Steven; Walmsley, Ian A

    2013-10-11

    We present a scheme for linear optical quantum computing using time-bin-encoded qubits in a single spatial mode. We show methods for single-qubit operations and heralded controlled-phase (cphase) gates, providing a sufficient set of operations for universal quantum computing with the Knill-Laflamme-Milburn [Nature (London) 409, 46 (2001)] scheme. Our protocol is suited to currently available photonic devices and ideally allows arbitrary numbers of qubits to be encoded in the same spatial mode, demonstrating the potential for time-frequency modes to dramatically increase the quantum information capacity of fixed spatial resources. As a test of our scheme, we demonstrate the first entirely single spatial mode implementation of a two-qubit quantum gate and show its operation with an average fidelity of 0.84±0.07.

  5. High spatial resolution spectroscopy of single semiconductor nanostructures

    Science.gov (United States)

    Harris, T. D.; Gershoni, D.; Pfeiffer, L.; Nirmal, M.; Trautman, J. K.; Macklin, J. J.

    1996-11-01

    Low-temperature near-field scanning optical microscopy is used for the first time in spectroscopic studies of single, nanometre dimension, cleaved edge overgrown quantum wires. A direct experimental comparison between a two-dimensional system and a single genuinely one-dimensional quantum wire system, inaccessible to conventional far-field optical spectroscopy, is enabled by the enhanced spatial resolution. We show that the photoluminescence of a single quantum wire is easily distinguished from that of the surrounding quantum well. Emission from localized centres is shown to dominate the photoluminescence from both wires and wells at low temperatures. A factor of three oscillator strength enhancement for these wires compared with the wells is concluded from the photoluminescence excitation data. We also report room-temperature spectroscopy and dynamics of single CdSe nanocrystals. Photochemistry, trap dynamics and spectroscopy are easily determined.

  6. Multiplexing 200 spatial modes with a single hologram

    Science.gov (United States)

    Rosales-Guzmán, Carmelo; Bhebhe, Nkosiphile; Mahonisi, Nyiku; Forbes, Andrew

    2017-11-01

    The on-demand tailoring of light's spatial shape is of great relevance in a wide variety of research areas. Computer-controlled devices, such as spatial light modulators (SLMs) or digital micromirror devices, offer a very accurate, flexible and fast holographic means to this end. Remarkably, digital holography affords the simultaneous generation of multiple beams (multiplexing), a tool with numerous applications in many fields. Here, we provide a self-contained tutorial on light beam multiplexing. Through the use of several examples, the readers will be guided step by step in the process of light beam shaping and multiplexing. Additionally, we provide a quantitative analysis on the multiplexing capabilities of SLMs to assess the maximum number of beams that can be multiplexed on a single SLM, showing approximately 200 modes on a single hologram.

  7. Supervised Convolutional Sparse Coding

    KAUST Repository

    Affara, Lama Ahmed

    2018-04-08

    Convolutional Sparse Coding (CSC) is a well-established image representation model especially suited for image restoration tasks. In this work, we extend the applicability of this model by proposing a supervised approach to convolutional sparse coding, which aims at learning discriminative dictionaries instead of purely reconstructive ones. We incorporate a supervised regularization term into the traditional unsupervised CSC objective to encourage the final dictionary elements to be discriminative. Experimental results show that using supervised convolutional learning results in two key advantages. First, we learn more semantically relevant filters in the dictionary and second, we achieve improved image reconstruction on unseen data.

  8. Spatially Resolved Sensitivity of Single-Particle Plasmon Sensors.

    Science.gov (United States)

    Beuwer, Michael A; van Hoof, Bas; Zijlstra, Peter

    2018-03-01

    The high sensitivity of localized surface plasmon resonance sensors to the local refractive index allows for the detection of single-molecule binding events. Though binding events of single objects can be detected by their induced plasmon shift, the broad distribution of observed shifts remains poorly understood. Here, we perform a single-particle study wherein single nanospheres bind to a gold nanorod, and relate the observed plasmon shift to the binding location using correlative microscopy. To achieve this we combine atomic force microscopy to determine the binding location, and single-particle spectroscopy to determine the corresponding plasmon shift. As expected, we find a larger plasmon shift for nanospheres binding at the tip of a rod compared to its sides, in good agreement with numerical calculations. However, we also find a broad distribution of shifts even for spheres that were bound at a similar location to the nanorod. Our correlative approach allows us to disentangle effects of nanoparticle dimensions and binding location, and by comparison to numerical calculations we find that the biggest contributor to this observed spread is the dispersion in nanosphere diameter. These experiments provide insight into the spatial sensitivity and signal-heterogeneity of single-particle plasmon sensors and provides a framework for signal interpretation in sensing applications.

  9. Convolution based profile fitting

    International Nuclear Information System (INIS)

    Kern, A.; Coelho, A.A.; Cheary, R.W.

    2002-01-01

    Full text: In convolution based profile fitting, profiles are generated by convoluting functions together to form the observed profile shape. For a convolution of 'n' functions this process can be written as, Y(2θ)=F 1 (2θ)x F 2 (2θ)x... x F i (2θ)x....xF n (2θ). In powder diffractometry the functions F i (2θ) can be interpreted as the aberration functions of the diffractometer, but in general any combination of appropriate functions for F i (2θ) may be used in this context. Most direct convolution fitting methods are restricted to combinations of F i (2θ) that can be convoluted analytically (e.g. GSAS) such as Lorentzians, Gaussians, the hat (impulse) function and the exponential function. However, software such as TOPAS is now available that can accurately convolute and refine a wide variety of profile shapes numerically, including user defined profiles, without the need to convolute analytically. Some of the most important advantages of modern convolution based profile fitting are: 1) virtually any peak shape and angle dependence can normally be described using minimal profile parameters in laboratory and synchrotron X-ray data as well as in CW and TOF neutron data. This is possible because numerical convolution and numerical differentiation is used within the refinement procedure so that a wide range of functions can easily be incorporated into the convolution equation; 2) it can use physically based diffractometer models by convoluting the instrument aberration functions. This can be done for most laboratory based X-ray powder diffractometer configurations including conventional divergent beam instruments, parallel beam instruments, and diffractometers used for asymmetric diffraction. It can also accommodate various optical elements (e.g. multilayers and monochromators) and detector systems (e.g. point and position sensitive detectors) and has already been applied to neutron powder diffraction systems (e.g. ANSTO) as well as synchrotron based

  10. Fourier-transform spatial modulation spectroscopy of single gold nanorods

    Directory of Open Access Journals (Sweden)

    Kollmann Heiko

    2018-03-01

    Full Text Available Sensing the scattered fields of single metallic nanostructures is a crucial step towards the applications of isolated plasmonic antennas, such as for the sensing of single molecules or nanoparticles. In the past, both near- and far-field spectroscopy methods have been applied to monitor single plasmonic resonances. So far, however, these spectral-domain techniques do not yet provide the femtosecond time resolution that is needed to probe the dynamics of plasmonic fields in the time domain. Here, we introduce a time-domain technique that combines broadband Fourier-transform spectroscopy and spatial modulation spectroscopy (FT-SMS to quantitatively measure the extinction spectra of the isolated gold nanorods with a nominal footprint of 41×10 nm2. Using a phase-stable pulse pair for excitation, the technique is capable of rejecting off-resonant stray fields and providing absolute measurements of the extinction cross section. Our results indicate that the method is well suited for measuring the optical response of strongly coupled hybrid systems with high signal-to-noise ratio. It may form the basis for new approaches towards time-domain spectroscopy of single nanoantennas with few-cycle time resolution.

  11. Multithreaded implicitly dealiased convolutions

    Science.gov (United States)

    Roberts, Malcolm; Bowman, John C.

    2018-03-01

    Implicit dealiasing is a method for computing in-place linear convolutions via fast Fourier transforms that decouples work memory from input data. It offers easier memory management and, for long one-dimensional input sequences, greater efficiency than conventional zero-padding. Furthermore, for convolutions of multidimensional data, the segregation of data and work buffers can be exploited to reduce memory usage and execution time significantly. This is accomplished by processing and discarding data as it is generated, allowing work memory to be reused, for greater data locality and performance. A multithreaded implementation of implicit dealiasing that accepts an arbitrary number of input and output vectors and a general multiplication operator is presented, along with an improved one-dimensional Hermitian convolution that avoids the loop dependency inherent in previous work. An alternate data format that can accommodate a Nyquist mode and enhance cache efficiency is also proposed.

  12. Convolution copula econometrics

    CERN Document Server

    Cherubini, Umberto; Mulinacci, Sabrina

    2016-01-01

    This book presents a novel approach to time series econometrics, which studies the behavior of nonlinear stochastic processes. This approach allows for an arbitrary dependence structure in the increments and provides a generalization with respect to the standard linear independent increments assumption of classical time series models. The book offers a solution to the problem of a general semiparametric approach, which is given by a concept called C-convolution (convolution of dependent variables), and the corresponding theory of convolution-based copulas. Intended for econometrics and statistics scholars with a special interest in time series analysis and copula functions (or other nonparametric approaches), the book is also useful for doctoral students with a basic knowledge of copula functions wanting to learn about the latest research developments in the field.

  13. Efficient convolutional sparse coding

    Energy Technology Data Exchange (ETDEWEB)

    Wohlberg, Brendt

    2017-06-20

    Computationally efficient algorithms may be applied for fast dictionary learning solving the convolutional sparse coding problem in the Fourier domain. More specifically, efficient convolutional sparse coding may be derived within an alternating direction method of multipliers (ADMM) framework that utilizes fast Fourier transforms (FFT) to solve the main linear system in the frequency domain. Such algorithms may enable a significant reduction in computational cost over conventional approaches by implementing a linear solver for the most critical and computationally expensive component of the conventional iterative algorithm. The theoretical computational cost of the algorithm may be reduced from O(M.sup.3N) to O(MN log N), where N is the dimensionality of the data and M is the number of elements in the dictionary. This significant improvement in efficiency may greatly increase the range of problems that can practically be addressed via convolutional sparse representations.

  14. Convolution Operators on Groups

    CERN Document Server

    Derighetti, Antoine

    2011-01-01

    This volume is devoted to a systematic study of the Banach algebra of the convolution operators of a locally compact group. Inspired by classical Fourier analysis we consider operators on Lp spaces, arriving at a description of these operators and Lp versions of the theorems of Wiener and Kaplansky-Helson.

  15. Convolutional Neural Networks for Handwritten Javanese Character Recognition

    OpenAIRE

    Dewa, Chandra Kusuma; Fadhilah, Amanda Lailatul; Afiahayati, A

    2018-01-01

    Convolutional neural network (CNN) is state-of-the-art method in object recognition task. Specialized for spatial input data type, CNN has special convolutional and pooling layers which enable hierarchical feature learning from the input space. For offline handwritten character recognition problem such as classifying character in MNIST database, CNN shows better classification result than any other methods. By leveraging the advantages of CNN over character recognition task, in this paper we ...

  16. Spatially resolved Hall effect measurement in a single semiconductor nanowire

    Science.gov (United States)

    Storm, Kristian; Halvardsson, Filip; Heurlin, Magnus; Lindgren, David; Gustafsson, Anders; Wu, Phillip M.; Monemar, Bo; Samuelson, Lars

    2012-12-01

    Efficient light-emitting diodes and photovoltaic energy-harvesting devices are expected to play an important role in the continued efforts towards sustainable global power consumption. Semiconductor nanowires are promising candidates as the active components of both light-emitting diodes and photovoltaic cells, primarily due to the added freedom in device design offered by the nanowire geometry. However, for nanowire-based components to move past the proof-of-concept stage and be implemented in production-grade devices, it is necessary to precisely quantify and control fundamental material properties such as doping and carrier mobility. Unfortunately, the nanoscale geometry that makes nanowires interesting for applications also makes them inherently difficult to characterize. Here, we report a method to carry out Hall measurements on single core-shell nanowires. Our technique allows spatially resolved and quantitative determination of the carrier concentration and mobility of the nanowire shell. As Hall measurements have previously been completely unavailable for nanowires, the experimental platform presented here should facilitate the implementation of nanowires in advanced practical devices.

  17. Invariant scattering convolution networks.

    Science.gov (United States)

    Bruna, Joan; Mallat, Stéphane

    2013-08-01

    A wavelet scattering network computes a translation invariant image representation which is stable to deformations and preserves high-frequency information for classification. It cascades wavelet transform convolutions with nonlinear modulus and averaging operators. The first network layer outputs SIFT-type descriptors, whereas the next layers provide complementary invariant information that improves classification. The mathematical analysis of wavelet scattering networks explains important properties of deep convolution networks for classification. A scattering representation of stationary processes incorporates higher order moments and can thus discriminate textures having the same Fourier power spectrum. State-of-the-art classification results are obtained for handwritten digits and texture discrimination, with a Gaussian kernel SVM and a generative PCA classifier.

  18. Fast convolutions meet Montgomery

    Science.gov (United States)

    Mihailescu, Preda

    2008-06-01

    Arithmetic in large ring and field extensions is an important problem of symbolic computation, and it consists essentially of the combination of one multiplication and one division in the underlying ring. Methods are known for replacing one division by two short multiplications in the underlying ring, which can be performed essentially by using convolutions. However, while using school-book multiplication, modular multiplication may be grouped into 2 mathsf{M}(mathbf{R}) operations (where mathsf{M}(mathbf{R}) denotes the number of operations of one multiplication in the underlying ring), the short multiplication problem is an important obstruction to convolution. It raises the costs in that case to 3 mathsf{M}(mathbf{R}) . In this paper we give a method for understanding and bypassing this problem, thus reducing the costs of ring arithmetic to roughly 2mathsf{M}(mathbf{R}) when also using fast convolutions. The algorithms have been implemented with results which fit well the theoretical prediction and which shall be presented in a separate paper.

  19. The convolution transform

    CERN Document Server

    Hirschman, Isidore Isaac

    2005-01-01

    In studies of general operators of the same nature, general convolution transforms are immediately encountered as the objects of inversion. The relation between differential operators and integral transforms is the basic theme of this work, which is geared toward upper-level undergraduates and graduate students. It may be read easily by anyone with a working knowledge of real and complex variable theory. Topics include the finite and non-finite kernels, variation diminishing transforms, asymptotic behavior of kernels, real inversion theory, representation theory, the Weierstrass transform, and

  20. Consensus Convolutional Sparse Coding

    KAUST Repository

    Choudhury, Biswarup

    2017-04-11

    Convolutional sparse coding (CSC) is a promising direction for unsupervised learning in computer vision. In contrast to recent supervised methods, CSC allows for convolutional image representations to be learned that are equally useful for high-level vision tasks and low-level image reconstruction and can be applied to a wide range of tasks without problem-specific retraining. Due to their extreme memory requirements, however, existing CSC solvers have so far been limited to low-dimensional problems and datasets using a handful of low-resolution example images at a time. In this paper, we propose a new approach to solving CSC as a consensus optimization problem, which lifts these limitations. By learning CSC features from large-scale image datasets for the first time, we achieve significant quality improvements in a number of imaging tasks. Moreover, the proposed method enables new applications in high dimensional feature learning that has been intractable using existing CSC methods. This is demonstrated for a variety of reconstruction problems across diverse problem domains, including 3D multispectral demosaickingand 4D light field view synthesis.

  1. Consensus Convolutional Sparse Coding

    KAUST Repository

    Choudhury, Biswarup

    2017-12-01

    Convolutional sparse coding (CSC) is a promising direction for unsupervised learning in computer vision. In contrast to recent supervised methods, CSC allows for convolutional image representations to be learned that are equally useful for high-level vision tasks and low-level image reconstruction and can be applied to a wide range of tasks without problem-specific retraining. Due to their extreme memory requirements, however, existing CSC solvers have so far been limited to low-dimensional problems and datasets using a handful of low-resolution example images at a time. In this paper, we propose a new approach to solving CSC as a consensus optimization problem, which lifts these limitations. By learning CSC features from large-scale image datasets for the first time, we achieve significant quality improvements in a number of imaging tasks. Moreover, the proposed method enables new applications in high-dimensional feature learning that has been intractable using existing CSC methods. This is demonstrated for a variety of reconstruction problems across diverse problem domains, including 3D multispectral demosaicing and 4D light field view synthesis.

  2. Separating Underdetermined Convolutive Speech Mixtures

    DEFF Research Database (Denmark)

    Pedersen, Michael Syskind; Wang, DeLiang; Larsen, Jan

    2006-01-01

    a method for underdetermined blind source separation of convolutive mixtures. The proposed framework is applicable for separation of instantaneous as well as convolutive speech mixtures. It is possible to iteratively extract each speech signal from the mixture by combining blind source separation...

  3. Strongly-MDS convolutional codes

    NARCIS (Netherlands)

    Gluesing-Luerssen, H; Rosenthal, J; Smarandache, R

    Maximum-distance separable (MDS) convolutional codes have the property that their free distance is maximal among all codes of the same rate and the same degree. In this paper, a class of MDS convolutional codes is introduced whose column distances reach the generalized Singleton bound at the

  4. Single Canonical Model of Reflexive Memory and Spatial Attention.

    Science.gov (United States)

    Patel, Saumil S; Red, Stuart; Lin, Eric; Sereno, Anne B

    2015-10-23

    Many neurons in the dorsal and ventral visual stream have the property that after a brief visual stimulus presentation in their receptive field, the spiking activity in these neurons persists above their baseline levels for several seconds. This maintained activity is not always correlated with the monkey's task and its origin is unknown. We have previously proposed a simple neural network model, based on shape selective neurons in monkey lateral intraparietal cortex, which predicts the valence and time course of reflexive (bottom-up) spatial attention. In the same simple model, we demonstrate here that passive maintained activity or short-term memory of specific visual events can result without need for an external or top-down modulatory signal. Mutual inhibition and neuronal adaptation play distinct roles in reflexive attention and memory. This modest 4-cell model provides the first simple and unified physiologically plausible mechanism of reflexive spatial attention and passive short-term memory processes.

  5. Recurrent Spatial Transformer Networks

    DEFF Research Database (Denmark)

    Sønderby, Søren Kaae; Sønderby, Casper Kaae; Maaløe, Lars

    2015-01-01

    We integrate the recently proposed spatial transformer network (SPN) [Jaderberg et. al 2015] into a recurrent neural network (RNN) to form an RNN-SPN model. We use the RNN-SPN to classify digits in cluttered MNIST sequences. The proposed model achieves a single digit error of 1.5% compared to 2.......9% for a convolutional networks and 2.0% for convolutional networks with SPN layers. The SPN outputs a zoomed, rotated and skewed version of the input image. We investigate different down-sampling factors (ratio of pixel in input and output) for the SPN and show that the RNN-SPN model is able to down-sample the input...

  6. Inverse scattering solution for the spatially heterogeneous compliance of a single fracture

    NARCIS (Netherlands)

    Minato, S.; Ghose, R.

    2013-01-01

    Characterizing the spatially heterogeneous fracture compliance through use of elastic waves has the potential to illuminate the hydraulic and mechanical properties along a fracture. We formulate the inverse scattering problem to estimate the heterogeneous compliance distribution along a single

  7. Spherical convolutions and their application in molecular modelling

    DEFF Research Database (Denmark)

    Boomsma, Wouter; Frellsen, Jes

    2017-01-01

    Convolutional neural networks are increasingly used outside the domain of image analysis, in particular in various areas of the natural sciences concerned with spatial data. Such networks often work out-of-the box, and in some cases entire model architectures from image analysis can be carried ov...

  8. Fast space-varying convolution using matrix source coding with applications to camera stray light reduction.

    Science.gov (United States)

    Wei, Jianing; Bouman, Charles A; Allebach, Jan P

    2014-05-01

    Many imaging applications require the implementation of space-varying convolution for accurate restoration and reconstruction of images. Here, we use the term space-varying convolution to refer to linear operators whose impulse response has slow spatial variation. In addition, these space-varying convolution operators are often dense, so direct implementation of the convolution operator is typically computationally impractical. One such example is the problem of stray light reduction in digital cameras, which requires the implementation of a dense space-varying deconvolution operator. However, other inverse problems, such as iterative tomographic reconstruction, can also depend on the implementation of dense space-varying convolution. While space-invariant convolution can be efficiently implemented with the fast Fourier transform, this approach does not work for space-varying operators. So direct convolution is often the only option for implementing space-varying convolution. In this paper, we develop a general approach to the efficient implementation of space-varying convolution, and demonstrate its use in the application of stray light reduction. Our approach, which we call matrix source coding, is based on lossy source coding of the dense space-varying convolution matrix. Importantly, by coding the transformation matrix, we not only reduce the memory required to store it; we also dramatically reduce the computation required to implement matrix-vector products. Our algorithm is able to reduce computation by approximately factoring the dense space-varying convolution operator into a product of sparse transforms. Experimental results show that our method can dramatically reduce the computation required for stray light reduction while maintaining high accuracy.

  9. Discrete singular convolution for the generalized variable-coefficient ...

    African Journals Online (AJOL)

    Numerical solutions of the generalized variable-coefficient Korteweg-de Vries equation are obtained using a discrete singular convolution and a fourth order singly diagonally implicit Runge-Kutta method for space and time discretisation, respectively. The theoretical convergence of the proposed method is rigorously ...

  10. Design of convolutional tornado code

    Science.gov (United States)

    Zhou, Hui; Yang, Yao; Gao, Hongmin; Tan, Lu

    2017-09-01

    As a linear block code, the traditional tornado (tTN) code is inefficient in burst-erasure environment and its multi-level structure may lead to high encoding/decoding complexity. This paper presents a convolutional tornado (cTN) code which is able to improve the burst-erasure protection capability by applying the convolution property to the tTN code, and reduce computational complexity by abrogating the multi-level structure. The simulation results show that cTN code can provide a better packet loss protection performance with lower computation complexity than tTN code.

  11. Spatial Interactions in Multiple-Use Forestry and Substitution and Wealth Effects for the Single Stand

    Science.gov (United States)

    Stephen K. Swallow; David N. Wear

    1993-01-01

    Forestry models often ignore spatial relationships between forest stands. This paper isolates the effects of stand interactions in muitiple-use forestry through a straightforward extension of the single-stand model. Effects of stand interactions decompose into wealth and substitution effects and may cause time-varying patterns of resource use for a forest...

  12. Solutions to Arithmetic Convolution Equations

    Czech Academy of Sciences Publication Activity Database

    Glöckner, H.; Lucht, L.G.; Porubský, Štefan

    2007-01-01

    Roč. 135, č. 6 (2007), s. 1619-1629 ISSN 0002-9939 R&D Projects: GA ČR GA201/04/0381 Institutional research plan: CEZ:AV0Z10300504 Keywords : arithmetic functions * Dirichlet convolution * polynomial equations * analytic equations * topological algebras * holomorphic functional calculus Subject RIV: BA - General Mathematics Impact factor: 0.520, year: 2007

  13. Single-acquisition method for simultaneous determination of extrinsic gamma-camera sensitivity and spatial resolution

    Energy Technology Data Exchange (ETDEWEB)

    Santos, J.A.M. [Servico de Fisica Medica, Instituto Portugues de Oncologia Francisco Gentil do Porto, E.P.E., Rua Dr. Antonio Bernardino de Almeida, 4200-072 Porto (Portugal)], E-mail: a.miranda@portugalmail.pt; Sarmento, S. [Servico de Fisica Medica, Instituto Portugues de Oncologia Francisco Gentil do Porto, E.P.E., Rua Dr. Antonio Bernardino de Almeida, 4200-072 Porto (Portugal); Alves, P.; Torres, M.C. [Departamento de Fisica da Universidade do Porto, Rua do Campo Alegre 687, 4169-007 Porto (Portugal); Bastos, A.L. [Servico de Medicina Nuclear, Instituto Portugues de Oncologia Francisco Gentil do Porto, E.P.E., Rua Dr. Antonio Bernardino de Almeida, 4200-072 Porto (Portugal); Ponte, F. [Servico de Fisica Medica, Instituto Portugues de Oncologia Francisco Gentil do Porto, E.P.E., Rua Dr. Antonio Bernardino de Almeida, 4200-072 Porto (Portugal)

    2008-01-15

    A new method for measuring simultaneously both the extrinsic sensitivity and spatial resolution of a gamma-camera in a single planar acquisition was implemented. A dual-purpose phantom (SR phantom; sensitivity/resolution) was developed, tested and the results compared with other conventional methods used for separate determination of these two important image quality parameters. The SR phantom yielded reproducible and accurate results, allowing an immediate visual inspection of the spatial resolution as well as the quantitative determination of the contrast for six different spatial frequencies. It also proved to be useful in the estimation of the modulation transfer function (MTF) of the image formation collimator/detector system at six different frequencies and can be used to estimate the spatial resolution as function of the direction relative to the digital matrix of the detector.

  14. Convolutional Sparse Coding for RGB+NIR Imaging.

    Science.gov (United States)

    Hu, Xuemei; Heide, Felix; Dai, Qionghai; Wetzstein, Gordon

    2018-04-01

    Emerging sensor designs increasingly rely on novel color filter arrays (CFAs) to sample the incident spectrum in unconventional ways. In particular, capturing a near-infrared (NIR) channel along with conventional RGB color is an exciting new imaging modality. RGB+NIR sensing has broad applications in computational photography, such as low-light denoising, it has applications in computer vision, such as facial recognition and tracking, and it paves the way toward low-cost single-sensor RGB and depth imaging using structured illumination. However, cost-effective commercial CFAs suffer from severe spectral cross talk. This cross talk represents a major challenge in high-quality RGB+NIR imaging, rendering existing spatially multiplexed sensor designs impractical. In this work, we introduce a new approach to RGB+NIR image reconstruction using learned convolutional sparse priors. We demonstrate high-quality color and NIR imaging for challenging scenes, even including high-frequency structured NIR illumination. The effectiveness of the proposed method is validated on a large data set of experimental captures, and simulated benchmark results which demonstrate that this work achieves unprecedented reconstruction quality.

  15. Spatial-Temporal Feature Analysis on Single-Trial Event Related Potential for Rapid Face Identification

    Directory of Open Access Journals (Sweden)

    Lei Jiang

    2017-11-01

    Full Text Available The event-related potential (ERP is the brain response measured in electroencephalography (EEG, which reflects the process of human cognitive activity. ERP has been introduced into brain computer interfaces (BCIs to communicate the computer with the subject's intention. Due to the low signal-to-noise ratio of EEG, most ERP studies are based on grand-averaging over many trials. Recently single-trial ERP detection attracts more attention, which enables real time processing tasks as rapid face identification. All the targets needed to be retrieved may appear only once, and there is no knowledge of target label for averaging. More interestingly, how the features contribute temporally and spatially to single-trial ERP detection has not been fully investigated. In this paper, we propose to implement a local-learning-based (LLB feature extraction method to investigate the importance of spatial-temporal components of ERP in a task of rapid face identification using single-trial detection. Comparing to previous methods, LLB method preserves the nonlinear structure of EEG signal distribution, and analyze the importance of original spatial-temporal components via optimization in feature space. As a data-driven methods, the weighting of the spatial-temporal component does not depend on the ERP detection method. The importance weights are optimized by making the targets more different from non-targets in feature space, and regularization penalty is introduced in optimization for sparse weights. This spatial-temporal feature extraction method is evaluated on the EEG data of 15 participants in performing a face identification task using rapid serial visual presentation paradigm. Comparing with other methods, the proposed spatial-temporal analysis method uses sparser (only 10% of the total features, and could achieve comparable performance (98% of single-trial ERP detection as the whole features across different detection methods. The interesting finding is

  16. Dispersion-convolution model for simulating peaks in a flow injection system.

    Science.gov (United States)

    Pai, Su-Cheng; Lai, Yee-Hwong; Chiao, Ling-Yun; Yu, Tiing

    2007-01-12

    A dispersion-convolution model is proposed for simulating peak shapes in a single-line flow injection system. It is based on the assumption that an injected sample plug is expanded due to a "bulk" dispersion mechanism along the length coordinate, and that after traveling over a distance or a period of time, the sample zone will develop into a Gaussian-like distribution. This spatial pattern is further transformed to a temporal coordinate by a convolution process, and finally a temporal peak image is generated. The feasibility of the proposed model has been examined by experiments with various coil lengths, sample sizes and pumping rates. An empirical dispersion coefficient (D*) can be estimated by using the observed peak position, height and area (tp*, h* and At*) from a recorder. An empirical temporal shift (Phi*) can be further approximated by Phi*=D*/u2, which becomes an important parameter in the restoration of experimental peaks. Also, the dispersion coefficient can be expressed as a second-order polynomial function of the pumping rate Q, for which D*(Q)=delta0+delta1Q+delta2Q2. The optimal dispersion occurs at a pumping rate of Qopt=sqrt[delta0/delta2]. This explains the interesting "Nike-swoosh" relationship between the peak height and pumping rate. The excellent coherence of theoretical and experimental peak shapes confirms that the temporal distortion effect is the dominating reason to explain the peak asymmetry in flow injection analysis.

  17. Two-stream Convolutional Neural Network for Methane Emissions Quantification

    Science.gov (United States)

    Wang, J.; Ravikumar, A. P.; McGuire, M.; Bell, C.; Tchapmi, L. P.; Brandt, A. R.

    2017-12-01

    Methane, a key component of natural gas, has a 25x higher global warming potential than carbon dioxide on a 100-year basis. Accurately monitoring and mitigating methane emissions require cost-effective detection and quantification technologies. Optical gas imaging, one of the most commonly used leak detection technology, adopted by Environmental Protection Agency, cannot estimate leak-sizes. In this work, we harness advances in computer science to allow for rapid and automatic leak quantification. Particularly, we utilize two-stream deep Convolutional Networks (ConvNets) to estimate leak-size by capturing complementary spatial information from still plume frames, and temporal information from plume motion between frames. We build large leak datasets for training and evaluating purposes by collecting about 20 videos (i.e. 397,400 frames) of leaks. The videos were recorded at six distances from the source, covering 10 -60 ft. Leak sources included natural gas well-heads, separators, and tanks. All frames were labeled with a true leak size, which has eight levels ranging from 0 to 140 MCFH. Preliminary analysis shows that two-stream ConvNets provides significant accuracy advantage over single steam ConvNets. Spatial stream ConvNet can achieve an accuracy of 65.2%, by extracting important features, including texture, plume area, and pattern. Temporal stream, fed by the results of optical flow analysis, results in an accuracy of 58.3%. The integration of the two-stream ConvNets gives a combined accuracy of 77.6%. For future work, we will split the training and testing datasets in distinct ways in order to test the generalization of the algorithm for different leak sources. Several analytic metrics, including confusion matrix and visualization of key features, will be used to understand accuracy rates and occurrences of false positives. The quantification algorithm can help to find and fix super-emitters, and improve the cost-effectiveness of leak detection and repair

  18. A convolutional neural network to filter artifacts in spectroscopic MRI.

    Science.gov (United States)

    Gurbani, Saumya S; Schreibmann, Eduard; Maudsley, Andrew A; Cordova, James Scott; Soher, Brian J; Poptani, Harish; Verma, Gaurav; Barker, Peter B; Shim, Hyunsuk; Cooper, Lee A D

    2018-03-09

    Proton MRSI is a noninvasive modality capable of generating volumetric maps of in vivo tissue metabolism without the need for ionizing radiation or injected contrast agent. Magnetic resonance spectroscopic imaging has been shown to be a viable imaging modality for studying several neuropathologies. However, a key hurdle in the routine clinical adoption of MRSI is the presence of spectral artifacts that can arise from a number of sources, possibly leading to false information. A deep learning model was developed that was capable of identifying and filtering out poor quality spectra. The core of the model used a tiled convolutional neural network that analyzed frequency-domain spectra to detect artifacts. When compared with a panel of MRS experts, our convolutional neural network achieved high sensitivity and specificity with an area under the curve of 0.95. A visualization scheme was implemented to better understand how the convolutional neural network made its judgement on single-voxel or multivoxel MRSI, and the convolutional neural network was embedded into a pipeline capable of producing whole-brain spectroscopic MRI volumes in real time. The fully automated method for assessment of spectral quality provides a valuable tool to support clinical MRSI or spectroscopic MRI studies for use in fields such as adaptive radiation therapy planning. © 2018 International Society for Magnetic Resonance in Medicine.

  19. End-to-end unsupervised deformable image registration with a convolutional neural network

    NARCIS (Netherlands)

    de Vos, Bob D.; Berendsen, Floris; Viergever, Max A.; Staring, Marius; Išgum, Ivana

    2017-01-01

    In this work we propose a deep learning network for deformable image registration (DIRNet). The DIRNet consists of a convolutional neural network (ConvNet) regressor, a spatial transformer, and a resampler. The ConvNet analyzes a pair of fixed and moving images and outputs parameters for the spatial

  20. Model structure selection in convolutive mixtures

    DEFF Research Database (Denmark)

    Dyrholm, Mads; Makeig, Scott; Hansen, Lars Kai

    2006-01-01

    The CICAAR algorithm (convolutive independent component analysis with an auto-regressive inverse model) allows separation of white (i.i.d) source signals from convolutive mixtures. We introduce a source color model as a simple extension to the CICAAR which allows for a more parsimoneous...... representation in many practical mixtures. The new filter-CICAAR allows Bayesian model selection and can help answer questions like: 'Are we actually dealing with a convolutive mixture?'. We try to answer this question for EEG data....

  1. Method for assessing the probability of accumulated doses from an intermittent source using the convolution technique

    International Nuclear Information System (INIS)

    Coleman, J.H.

    1980-10-01

    A technique is discussed for computing the probability distribution of the accumulated dose received by an arbitrary receptor resulting from several single releases from an intermittent source. The probability density of the accumulated dose is the convolution of the probability densities of doses from the intermittent releases. Emissions are not assumed to be constant over the brief release period. The fast fourier transform is used in the calculation of the convolution

  2. Spatial and frequency domain ring source models for the single muscle fiber action potential

    DEFF Research Database (Denmark)

    Henneberg, Kaj-åge; R., Plonsey

    1994-01-01

    In the paper, single-fibre models for the extracellular action potential are developed that will allow the potential to the evaluated at an arbitrary field point in the extracellular space. Fourier-domain models are restricted in that they evaluate potentials at equidistant points along a line...... parallel to the fibre axis. Consequently, they cannot easily evaluate the potential at the boundary nodes of a boundary-element electrode model. The Fourier-domain models employ axial-symmetric ring source models, and thereby provide higher accuracy that the line source model, where the source is lumped...... including anisotropy show that the spatial models require extreme care in the integration procedure owing to the singularity in the weighting functions. With adequate sampling, the spatial models can evaluate extracellular potentials with high accuracy....

  3. Spatial distribution of mineral dust single scattering albedo based on DREAM model

    Science.gov (United States)

    Kuzmanoski, Maja; Ničković, Slobodan; Ilić, Luka

    2016-04-01

    Mineral dust comprises a significant part of global aerosol burden. There is a large uncertainty in estimating role of dust in Earth's climate system, partly due to poor characterization of its optical properties. Single scattering albedo is one of key optical properties determining radiative effects of dust particles. While it depends on dust particle sizes, it is also strongly influenced by dust mineral composition, particularly the content of light-absorbing iron oxides and the mixing state (external or internal). However, an assumption of uniform dust composition is typically used in models. To better represent single scattering albedo in dust atmospheric models, required to increase accuracy of dust radiative effect estimates, it is necessary to include information on particle mineral content. In this study, we present the spatial distribution of dust single scattering albedo based on the Dust Regional Atmospheric Model (DREAM) with incorporated particle mineral composition. The domain of the model covers Northern Africa, Middle East and the European continent, with horizontal resolution set to 1/5°. It uses eight particle size bins within the 0.1-10 μm radius range. Focusing on dust episode of June 2010, we analyze dust single scattering albedo spatial distribution over the model domain, based on particle sizes and mineral composition from model output; we discuss changes in this optical property after long-range transport. Furthermore, we examine how the AERONET-derived aerosol properties respond to dust mineralogy. Finally we use AERONET data to evaluate model-based single scattering albedo. Acknowledgement We would like to thank the AERONET network and the principal investigators, as well as their staff, for establishing and maintaining the AERONET sites used in this work.

  4. Voxel-Based Spatial Filtering Method for Canopy Height Retrieval from Airborne Single-Photon Lidar

    Directory of Open Access Journals (Sweden)

    Hao Tang

    2016-09-01

    Full Text Available Airborne single-photon lidar (SPL is a new technology that holds considerable potential for forest structure and carbon monitoring at large spatial scales because it acquires 3D measurements of vegetation faster and more efficiently than conventional lidar instruments. However, SPL instruments use green wavelength (532 nm lasers, which are sensitive to background solar noise, and therefore SPL point clouds require more elaborate noise filtering than other lidar instruments to determine canopy heights, particularly in daytime acquisitions. Histogram-based aggregation is a commonly used approach for removing noise from photon counting lidar data, but it reduces the resolution of the dataset. Here we present an alternate voxel-based spatial filtering method that filters noise points efficiently while largely preserving the spatial integrity of SPL data. We develop and test our algorithms on an experimental SPL dataset acquired over Garrett County in Maryland, USA. We then compare canopy attributes retrieved using our new algorithm with those obtained from the conventional histogram binning approach. Our results show that canopy heights derived using the new algorithm have a strong agreement with field-measured heights (r2 = 0.69, bias = 0.42 m, RMSE = 4.85 m and discrete return lidar heights (r2 = 0.94, bias = 1.07 m, RMSE = 2.42 m. Results are consistently better than height accuracies from the histogram method (field data: r2 = 0.59, bias = 0.00 m, RMSE = 6.25 m; DRL: r2 = 0.78, bias = −0.06 m and RMSE = 4.88 m. Furthermore, we find that the spatial-filtering method retains fine-scale canopy structure detail and has lower errors over steep slopes. We therefore believe that automated spatial filtering algorithms such as the one presented here can support large-scale, canopy structure mapping from airborne SPL data.

  5. Spatial mapping of exciton lifetimes in single ZnO nanowires

    Directory of Open Access Journals (Sweden)

    J. S. Reparaz

    2013-07-01

    Full Text Available We investigate the spatial dependence of the exciton lifetimes in single ZnO nanowires. We have found that the free exciton and bound exciton lifetimes exhibit a maximum at the center of nanowires, while they decrease by 30% towards the tips. This dependence is explained by considering the cavity-like properties of the nanowires in combination with the Purcell effect. We show that the lifetime of the bound-excitons scales with the localization energy to the power of 3/2, which validates the model of Rashba and Gurgenishvili at the nanoscale.

  6. Spatial assessment of wolf-dog hybridization in a single breeding period

    OpenAIRE

    Pacheco, C.; L?pez-Bao, J. V.; Garc?a, E. J.; Lema, F. J.; Llaneza, L.; Palacios, V.; Godinho, R.

    2017-01-01

    Understanding the dynamics of wolf-dog hybridization and delineating evidence-based conservation strategies requires information on the spatial extent of wolf-dog hybridization in real-time, which remains largely unknown. We collected 332 wolf-like scats over ca. 5,000km2 in the NW Iberian Peninsula to evaluate wolf-dog hybridization at population level in a single breeding/pup-rearing season. Mitochondrial DNA (MtDNA) and 18 ancestry informative markers were used for species and individual i...

  7. Integrated single grating compressor for variable pulse front tilt in simultaneously spatially and temporally focused systems.

    Science.gov (United States)

    Block, Erica; Thomas, Jens; Durfee, Charles; Squier, Jeff

    2014-12-15

    A Ti:Al(3)O(2) multipass chirped pulse amplification system is outfitted with a single-grating, simultaneous spatial and temporal focusing (SSTF) compressor platform. For the first time, this novel design has the ability to easily vary the beam aspect ratio of an SSTF beam, and thus the degree of pulse-front tilt at focus, while maintaining a net zero-dispersion system. Accessible variation of pulse front tilt gives full spatiotemporal control over the intensity distribution at the focus and could lead to better understanding of effects such as nonreciprocal writing and SSTF-material interactions.

  8. Wavevector multiplexed atomic quantum memory via spatially-resolved single-photon detection.

    Science.gov (United States)

    Parniak, Michał; Dąbrowski, Michał; Mazelanik, Mateusz; Leszczyński, Adam; Lipka, Michał; Wasilewski, Wojciech

    2017-12-15

    Parallelized quantum information processing requires tailored quantum memories to simultaneously handle multiple photons. The spatial degree of freedom is a promising candidate to facilitate such photonic multiplexing. Using a single-photon resolving camera, we demonstrate a wavevector multiplexed quantum memory based on a cold atomic ensemble. Observation of nonclassical correlations between Raman scattered photons is confirmed by an average value of the second-order correlation function [Formula: see text] in 665 separated modes simultaneously. The proposed protocol utilizing the multimode memory along with the camera will facilitate generation of multi-photon states, which are a necessity in quantum-enhanced sensing technologies and as an input to photonic quantum circuits.

  9. Convolutions

    Indian Academy of Sciences (India)

    Think of a simple game of chance like throwing a dice. There are six possible outcomes, 1,2,...,6, each with probability 1/6. The probability vector (or the probability distribution) corresponding to this is (1/6,1/6,...,1/6), which for brevity I write as 1. 6(1,1,...,1). Suppose we throw the dice twice and observe the sum of the two.

  10. Convolutions

    Indian Academy of Sciences (India)

    The word 'interactive' is in fashion these days. So I will leave a few things for you to check. Let f1 and f2 be two polynomials, say f1(x) = a0 + a1x + a2x2,. (1) f2(x) = b0 + b1x + b2x2 + b3x3. (2). (Here the coefficients a's and b's could be integers, rational, real, or complex numbers.) Their product f1 f2 is the polynomial f1 f2(x) ...

  11. Convolution-deconvolution in DIGES

    Energy Technology Data Exchange (ETDEWEB)

    Philippacopoulos, A.J.; Simos, N. [Brookhaven National Lab., Upton, NY (United States). Dept. of Advanced Technology

    1995-05-01

    Convolution and deconvolution operations is by all means a very important aspect of SSI analysis since it influences the input to the seismic analysis. This paper documents some of the convolution/deconvolution procedures which have been implemented into the DIGES code. The 1-D propagation of shear and dilatational waves in typical layered configurations involving a stack of layers overlying a rock is treated by DIGES in a similar fashion to that of available codes, e.g. CARES, SHAKE. For certain configurations, however, there is no need to perform such analyses since the corresponding solutions can be obtained in analytic form. Typical cases involve deposits which can be modeled by a uniform halfspace or simple layered halfspaces. For such cases DIGES uses closed-form solutions. These solutions are given for one as well as two dimensional deconvolution. The type of waves considered include P, SV and SH waves. The non-vertical incidence is given special attention since deconvolution can be defined differently depending on the problem of interest. For all wave cases considered, corresponding transfer functions are presented in closed-form. Transient solutions are obtained in the frequency domain. Finally, a variety of forms are considered for representing the free field motion both in terms of deterministic as well as probabilistic representations. These include (a) acceleration time histories, (b) response spectra (c) Fourier spectra and (d) cross-spectral densities.

  12. Convolution-deconvolution in DIGES

    International Nuclear Information System (INIS)

    Philippacopoulos, A.J.; Simos, N.

    1995-01-01

    Convolution and deconvolution operations is by all means a very important aspect of SSI analysis since it influences the input to the seismic analysis. This paper documents some of the convolution/deconvolution procedures which have been implemented into the DIGES code. The 1-D propagation of shear and dilatational waves in typical layered configurations involving a stack of layers overlying a rock is treated by DIGES in a similar fashion to that of available codes, e.g. CARES, SHAKE. For certain configurations, however, there is no need to perform such analyses since the corresponding solutions can be obtained in analytic form. Typical cases involve deposits which can be modeled by a uniform halfspace or simple layered halfspaces. For such cases DIGES uses closed-form solutions. These solutions are given for one as well as two dimensional deconvolution. The type of waves considered include P, SV and SH waves. The non-vertical incidence is given special attention since deconvolution can be defined differently depending on the problem of interest. For all wave cases considered, corresponding transfer functions are presented in closed-form. Transient solutions are obtained in the frequency domain. Finally, a variety of forms are considered for representing the free field motion both in terms of deterministic as well as probabilistic representations. These include (a) acceleration time histories, (b) response spectra (c) Fourier spectra and (d) cross-spectral densities

  13. The general theory of convolutional codes

    Science.gov (United States)

    Mceliece, R. J.; Stanley, R. P.

    1993-01-01

    This article presents a self-contained introduction to the algebraic theory of convolutional codes. This introduction is partly a tutorial, but at the same time contains a number of new results which will prove useful for designers of advanced telecommunication systems. Among the new concepts introduced here are the Hilbert series for a convolutional code and the class of compact codes.

  14. Symbol synchronization in convolutionally coded systems

    Science.gov (United States)

    Baumert, L. D.; Mceliece, R. J.; Van Tilborg, H. C. A.

    1979-01-01

    Alternate symbol inversion is sometimes applied to the output of convolutional encoders to guarantee sufficient richness of symbol transition for the receiver symbol synchronizer. A bound is given for the length of the transition-free symbol stream in such systems, and those convolutional codes are characterized in which arbitrarily long transition free runs occur.

  15. Model structure selection in convolutive mixtures

    DEFF Research Database (Denmark)

    Dyrholm, Mads; Makeig, S.; Hansen, Lars Kai

    2006-01-01

    The CICAAR algorithm (convolutive independent component analysis with an auto-regressive inverse model) allows separation of white (i.i.d) source signals from convolutive mixtures. We introduce a source color model as a simple extension to the CICAAR which allows for a more parsimonious represent......The CICAAR algorithm (convolutive independent component analysis with an auto-regressive inverse model) allows separation of white (i.i.d) source signals from convolutive mixtures. We introduce a source color model as a simple extension to the CICAAR which allows for a more parsimonious...... representation in many practical mixtures. The new filter-CICAAR allows Bayesian model selection and can help answer questions like: ’Are we actually dealing with a convolutive mixture?’. We try to answer this question for EEG data....

  16. Time-Domain Convolutive Blind Source Separation Employing Selective-Tap Adaptive Algorithms

    Directory of Open Access Journals (Sweden)

    Pan Qiongfeng

    2007-01-01

    Full Text Available We investigate novel algorithms to improve the convergence and reduce the complexity of time-domain convolutive blind source separation (BSS algorithms. First, we propose MMax partial update time-domain convolutive BSS (MMax BSS algorithm. We demonstrate that the partial update scheme applied in the MMax LMS algorithm for single channel can be extended to multichannel time-domain convolutive BSS with little deterioration in performance and possible computational complexity saving. Next, we propose an exclusive maximum selective-tap time-domain convolutive BSS algorithm (XM BSS that reduces the interchannel coherence of the tap-input vectors and improves the conditioning of the autocorrelation matrix resulting in improved convergence rate and reduced misalignment. Moreover, the computational complexity is reduced since only half of the tap inputs are selected for updating. Simulation results have shown a significant improvement in convergence rate compared to existing techniques.

  17. Time-Domain Convolutive Blind Source Separation Employing Selective-Tap Adaptive Algorithms

    Directory of Open Access Journals (Sweden)

    Qiongfeng Pan

    2007-04-01

    Full Text Available We investigate novel algorithms to improve the convergence and reduce the complexity of time-domain convolutive blind source separation (BSS algorithms. First, we propose MMax partial update time-domain convolutive BSS (MMax BSS algorithm. We demonstrate that the partial update scheme applied in the MMax LMS algorithm for single channel can be extended to multichannel time-domain convolutive BSS with little deterioration in performance and possible computational complexity saving. Next, we propose an exclusive maximum selective-tap time-domain convolutive BSS algorithm (XM BSS that reduces the interchannel coherence of the tap-input vectors and improves the conditioning of the autocorrelation matrix resulting in improved convergence rate and reduced misalignment. Moreover, the computational complexity is reduced since only half of the tap inputs are selected for updating. Simulation results have shown a significant improvement in convergence rate compared to existing techniques.

  18. Design of an omnidirectional single-point photodetector for large-scale spatial coordinate measurement

    Science.gov (United States)

    Xie, Hongbo; Mao, Chensheng; Ren, Yongjie; Zhu, Jigui; Wang, Chao; Yang, Lei

    2017-10-01

    In high precision and large-scale coordinate measurement, one commonly used approach to determine the coordinate of a target point is utilizing the spatial trigonometric relationships between multiple laser transmitter stations and the target point. A light receiving device at the target point is the key element in large-scale coordinate measurement systems. To ensure high-resolution and highly sensitive spatial coordinate measurement, a high-performance and miniaturized omnidirectional single-point photodetector (OSPD) is greatly desired. We report one design of OSPD using an aspheric lens, which achieves an enhanced reception angle of -5 deg to 45 deg in vertical and 360 deg in horizontal. As the heart of our OSPD, the aspheric lens is designed in a geometric model and optimized by LightTools Software, which enables the reflection of a wide-angle incident light beam into the single-point photodiode. The performance of home-made OSPD is characterized with working distances from 1 to 13 m and further analyzed utilizing developed a geometric model. The experimental and analytic results verify that our device is highly suitable for large-scale coordinate metrology. The developed device also holds great potential in various applications such as omnidirectional vision sensor, indoor global positioning system, and optical wireless communication systems.

  19. Image Super-Resolution Using Deep Convolutional Networks.

    Science.gov (United States)

    Dong, Chao; Loy, Chen Change; He, Kaiming; Tang, Xiaoou

    2016-02-01

    We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality, and achieves fast speed for practical on-line usage. We explore different network structures and parameter settings to achieve trade-offs between performance and speed. Moreover, we extend our network to cope with three color channels simultaneously, and show better overall reconstruction quality.

  20. Optical computed tomography for spatially isotropic four-dimensional imaging of live single cells.

    Science.gov (United States)

    Kelbauskas, Laimonas; Shetty, Rishabh; Cao, Bin; Wang, Kuo-Chen; Smith, Dean; Wang, Hong; Chao, Shi-Hui; Gangaraju, Sandhya; Ashcroft, Brian; Kritzer, Margaret; Glenn, Honor; Johnson, Roger H; Meldrum, Deirdre R

    2017-12-01

    Quantitative three-dimensional (3D) computed tomography (CT) imaging of living single cells enables orientation-independent morphometric analysis of the intricacies of cellular physiology. Since its invention, x-ray CT has become indispensable in the clinic for diagnostic and prognostic purposes due to its quantitative absorption-based imaging in true 3D that allows objects of interest to be viewed and measured from any orientation. However, x-ray CT has not been useful at the level of single cells because there is insufficient contrast to form an image. Recently, optical CT has been developed successfully for fixed cells, but this technology called Cell-CT is incompatible with live-cell imaging due to the use of stains, such as hematoxylin, that are not compatible with cell viability. We present a novel development of optical CT for quantitative, multispectral functional 4D (three spatial + one spectral dimension) imaging of living single cells. The method applied to immune system cells offers truly isotropic 3D spatial resolution and enables time-resolved imaging studies of cells suspended in aqueous medium. Using live-cell optical CT, we found a heterogeneous response to mitochondrial fission inhibition in mouse macrophages and differential basal remodeling of small (0.1 to 1 fl) and large (1 to 20 fl) nuclear and mitochondrial structures on a 20- to 30-s time scale in human myelogenous leukemia cells. Because of its robust 3D measurement capabilities, live-cell optical CT represents a powerful new tool in the biomedical research field.

  1. Convolutional Neural Network for Image Recognition

    CERN Document Server

    Seifnashri, Sahand

    2015-01-01

    The aim of this project is to use machine learning techniques especially Convolutional Neural Networks for image processing. These techniques can be used for Quark-Gluon discrimination using calorimeters data, but unfortunately I didn’t manage to get the calorimeters data and I just used the Jet data fromminiaodsim(ak4 chs). The Jet data was not good enough for Convolutional Neural Network which is designed for ’image’ recognition. This report is made of twomain part, part one is mainly about implementing Convolutional Neural Network on unphysical data such as MNIST digits and CIFAR-10 dataset and part 2 is about the Jet data.

  2. Spin- and energy-dependent tunneling through a single molecule with intramolecular spatial resolution.

    Science.gov (United States)

    Brede, Jens; Atodiresei, Nicolae; Kuck, Stefan; Lazić, Predrag; Caciuc, Vasile; Morikawa, Yoshitada; Hoffmann, Germar; Blügel, Stefan; Wiesendanger, Roland

    2010-07-23

    We investigate the spin- and energy-dependent tunneling through a single organic molecule (CoPc) adsorbed on a ferromagnetic Fe thin film, spatially resolved by low-temperature spin-polarized scanning tunneling microscopy. Interestingly, the metal ion as well as the organic ligand show a significant spin dependence of tunneling current flow. State-of-the-art ab initio calculations including also van der Waals interactions reveal a strong hybridization of molecular orbitals and substrate 3d states. The molecule is anionic due to a transfer of one electron, resulting in a nonmagnetic (S=0) state. Nevertheless, tunneling through the molecule exhibits a pronounced spin dependence due to spin-split molecule-surface hybrid states.

  3. SYN3D: a single-channel, spatial flux synthesis code for diffusion theory calculations

    Energy Technology Data Exchange (ETDEWEB)

    Adams, C. H.

    1976-07-01

    This report is a user's manual for SYN3D, a computer code which uses single-channel, spatial flux synthesis to calculate approximate solutions to two- and three-dimensional, finite-difference, multigroup neutron diffusion theory equations. SYN3D is designed to run in conjunction with any one of several one- and two-dimensional, finite-difference codes (required to generate the synthesis expansion functions) currently being used in the fast reactor community. The report describes the theory and equations, the use of the code, and the implementation on the IBM 370/195 and CDC 7600 of the version of SYN3D available through the Argonne Code Center.

  4. SYN3D: a single-channel, spatial flux synthesis code for diffusion theory calculations

    International Nuclear Information System (INIS)

    Adams, C.H.

    1976-07-01

    This report is a user's manual for SYN3D, a computer code which uses single-channel, spatial flux synthesis to calculate approximate solutions to two- and three-dimensional, finite-difference, multigroup neutron diffusion theory equations. SYN3D is designed to run in conjunction with any one of several one- and two-dimensional, finite-difference codes (required to generate the synthesis expansion functions) currently being used in the fast reactor community. The report describes the theory and equations, the use of the code, and the implementation on the IBM 370/195 and CDC 7600 of the version of SYN3D available through the Argonne Code Center

  5. PCA-based spatially adaptive denoising of CFA images for single-sensor digital cameras.

    Science.gov (United States)

    Zheng, Lei; Lukac, Rastislav; Wu, Xiaolin; Zhang, David

    2009-04-01

    Single-sensor digital color cameras use a process called color demosiacking to produce full color images from the data captured by a color filter array (CAF). The quality of demosiacked images is degraded due to the sensor noise introduced during the image acquisition process. The conventional solution to combating CFA sensor noise is demosiacking first, followed by a separate denoising processing. This strategy will generate many noise-caused color artifacts in the demosiacking process, which are hard to remove in the denoising process. Few denoising schemes that work directly on the CFA images have been presented because of the difficulties arisen from the red, green and blue interlaced mosaic pattern, yet a well-designed "denoising first and demosiacking later" scheme can have advantages such as less noise-caused color artifacts and cost-effective implementation. This paper presents a principle component analysis (PCA)-based spatially-adaptive denoising algorithm, which works directly on the CFA data using a supporting window to analyze the local image statistics. By exploiting the spatial and spectral correlations existing in the CFA image, the proposed method can effectively suppress noise while preserving color edges and details. Experiments using both simulated and real CFA images indicate that the proposed scheme outperforms many existing approaches, including those sophisticated demosiacking and denoising schemes, in terms of both objective measurement and visual evaluation.

  6. One-trial spatial learning: wild hummingbirds relocate a reward after a single visit.

    Science.gov (United States)

    Flores-Abreu, I Nuri; Hurly, T Andrew; Healy, Susan D

    2012-07-01

    Beaconing to rewarded locations is typically achieved by visual recognition of the actual goal. Spatial recognition, on the other hand, can occur in the absence of the goal itself, relying instead on the landmarks surrounding the goal location. Although the duration or frequency of experiences that an animal needs to learn the landmarks surrounding a goal have been extensively studied with a variety of laboratory tasks, little is known about the way in which wild vertebrates use them in their natural environment. Here, we allowed hummingbirds to feed once only from a rewarding flower (goal) before it was removed. When we presented a similar flower at a different height in another location, birds frequently returned to the location the flower had previously occupied (spatial recognition) before flying to the flower itself (beaconing). After experiencing three rewarded flowers, each in a different location, they were more likely to beacon to the current visible flower than they were to return to previously rewarded locations (without a visible flower). These data show that hummingbirds can encode a rewarded location on the basis of the surrounding landmarks after a single visit. After multiple goal location manipulations, however, the birds changed their strategy to beaconing presumably because they had learned that the flower itself reliably signalled reward.

  7. Experimental study of current loss and plasma formation in the Z machine post-hole convolute

    Directory of Open Access Journals (Sweden)

    M. R. Gomez

    2017-01-01

    Full Text Available The Z pulsed-power generator at Sandia National Laboratories drives high energy density physics experiments with load currents of up to 26 MA. Z utilizes a double post-hole convolute to combine the current from four parallel magnetically insulated transmission lines into a single transmission line just upstream of the load. Current loss is observed in most experiments and is traditionally attributed to inefficient convolute performance. The apparent loss current varies substantially for z-pinch loads with different inductance histories; however, a similar convolute impedance history is observed for all load types. This paper details direct spectroscopic measurements of plasma density, temperature, and apparent and actual plasma closure velocities within the convolute. Spectral measurements indicate a correlation between impedance collapse and plasma formation in the convolute. Absorption features in the spectra show the convolute plasma consists primarily of hydrogen, which likely forms from desorbed electrode contaminant species such as H_{2}O, H_{2}, and hydrocarbons. Plasma densities increase from 1×10^{16}  cm^{−3} (level of detectability just before peak current to over 1×10^{17}  cm^{−3} at stagnation (tens of ns later. The density seems to be highest near the cathode surface, with an apparent cathode to anode plasma velocity in the range of 35–50  cm/μs. Similar plasma conditions and convolute impedance histories are observed in experiments with high and low losses, suggesting that losses are driven largely by load dynamics, which determine the voltage on the convolute.

  8. Traffic sign recognition based on deep convolutional neural network

    Science.gov (United States)

    Yin, Shi-hao; Deng, Ji-cai; Zhang, Da-wei; Du, Jing-yuan

    2017-11-01

    Traffic sign recognition (TSR) is an important component of automated driving systems. It is a rather challenging task to design a high-performance classifier for the TSR system. In this paper, we propose a new method for TSR system based on deep convolutional neural network. In order to enhance the expression of the network, a novel structure (dubbed block-layer below) which combines network-in-network and residual connection is designed. Our network has 10 layers with parameters (block-layer seen as a single layer): the first seven are alternate convolutional layers and block-layers, and the remaining three are fully-connected layers. We train our TSR network on the German traffic sign recognition benchmark (GTSRB) dataset. To reduce overfitting, we perform data augmentation on the training images and employ a regularization method named "dropout". The activation function we employ in our network adopts scaled exponential linear units (SELUs), which can induce self-normalizing properties. To speed up the training, we use an efficient GPU to accelerate the convolutional operation. On the test dataset of GTSRB, we achieve the accuracy rate of 99.67%, exceeding the state-of-the-art results.

  9. Convolution on spaces of locally summable functions

    Directory of Open Access Journals (Sweden)

    Federica Andreano

    2008-01-01

    Full Text Available In this work we prove the existence of convolution on Marcinkiewicz spaces p(ℝ, 1≤p<∞, and, using pointwise approximate identities, we extend the classical definition of Hilbert transform to such spaces.

  10. Event Discrimination using Convolutional Neural Networks

    Science.gov (United States)

    Menon, Hareesh; Hughes, Richard; Daling, Alec; Winer, Brian

    2017-01-01

    Convolutional Neural Networks (CNNs) are computational models that have been shown to be effective at classifying different types of images. We present a method to use CNNs to distinguish events involving the production of a top quark pair and a Higgs boson from events involving the production of a top quark pair and several quark and gluon jets. To do this, we generate and simulate data using MADGRAPH and DELPHES for a general purpose LHC detector at 13 TeV. We produce images using a particle flow algorithm by binning the particles geometrically based on their position in the detector and weighting the bins by the energy of each particle within each bin, and by defining channels based on particle types (charged track, neutral hadronic, neutral EM, lepton, heavy flavor). Our classification results are competitive with standard machine learning techniques. We have also looked into the classification of the substructure of the events, in a process known as scene labeling. In this context, we look for the presence of boosted objects (such as top quarks) with substructure encompassed within single jets. Preliminary results on substructure classification will be presented.

  11. Convolutional neural networks applied to neutrino events in a liquid argon time projection chamber

    Energy Technology Data Exchange (ETDEWEB)

    Acciarri, R.; Adams, C.; An, R.; Asaadi, J.; Auger, M.; Bagby, L.; Baller, B.; Barr, G.; Bass, M.; Bay, F.; Bishai, M.; Blake, A.; Bolton, T.; Bugel, L.; Camilleri, L.; Caratelli, D.; Carls, B.; Fernandez, R. Castillo; Cavanna, F.; Chen, H.; Church, E.; Cianci, D.; Collin, G. H.; Conrad, J. M.; Convery, M.; Crespo-Anad?n, J. I.; Del Tutto, M.; Devitt, D.; Dytman, S.; Eberly, B.; Ereditato, A.; Sanchez, L. Escudero; Esquivel, J.; Fleming, B. T.; Foreman, W.; Furmanski, A. P.; Garvey, G. T.; Genty, V.; Goeldi, D.; Gollapinni, S.; Graf, N.; Gramellini, E.; Greenlee, H.; Grosso, R.; Guenette, R.; Hackenburg, A.; Hamilton, P.; Hen, O.; Hewes, J.; Hill, C.; Ho, J.; Horton-Smith, G.; James, C.; de Vries, J. Jan; Jen, C. -M.; Jiang, L.; Johnson, R. A.; Jones, B. J. P.; Joshi, J.; Jostlein, H.; Kaleko, D.; Karagiorgi, G.; Ketchum, W.; Kirby, B.; Kirby, M.; Kobilarcik, T.; Kreslo, I.; Laube, A.; Li, Y.; Lister, A.; Littlejohn, B. R.; Lockwitz, S.; Lorca, D.; Louis, W. C.; Luethi, M.; Lundberg, B.; Luo, X.; Marchionni, A.; Mariani, C.; Marshall, J.; Caicedo, D. A. Martinez; Meddage, V.; Miceli, T.; Mills, G. B.; Moon, J.; Mooney, M.; Moore, C. D.; Mousseau, J.; Murrells, R.; Naples, D.; Nienaber, P.; Nowak, J.; Palamara, O.; Paolone, V.; Papavassiliou, V.; Pate, S. F.; Pavlovic, Z.; Porzio, D.; Pulliam, G.; Qian, X.; Raaf, J. L.; Rafique, A.; Rochester, L.; von Rohr, C. Rudolf; Russell, B.; Schmitz, D. W.; Schukraft, A.; Seligman, W.; Shaevitz, M. H.; Sinclair, J.; Snider, E. L.; Soderberg, M.; S?ldner-Rembold, S.; Soleti, S. R.; Spentzouris, P.; Spitz, J.; St. John, J.; Strauss, T.; Szelc, A. M.; Tagg, N.; Terao, K.; Thomson, M.; Toups, M.; Tsai, Y. -T.; Tufanli, S.; Usher, T.; Van de Water, R. G.; Viren, B.; Weber, M.; Weston, J.; Wickremasinghe, D. A.; Wolbers, S.; Wongjirad, T.; Woodruff, K.; Yang, T.; Zeller, G. P.; Zennamo, J.; Zhang, C.

    2017-03-01

    We present several studies of convolutional neural networks applied to data coming from the MicroBooNE detector, a liquid argon time projection chamber (LArTPC). The algorithms studied include the classification of single particle images, the localization of single particle and neutrino interactions in an image, and the detection of a simulated neutrino event overlaid with cosmic ray backgrounds taken from real detector data. These studies demonstrate the potential of convolutional neural networks for particle identification or event detection on simulated neutrino interactions. We also address technical issues that arise when applying this technique to data from a large LArTPC at or near ground level.

  12. Performance assessment of the single photon emission microscope: high spatial resolution SPECT imaging of small animal organs

    OpenAIRE

    Mejia, J.; Reis, M.A.; Miranda, A.C.C.; Batista, I.R.; Barboza, M.R.F.; Shih, M.C.; Fu, G.; Chen, C.T.; Meng, L.J.; Bressan, R.A.; Amaro Jr, E.

    2013-01-01

    The single photon emission microscope (SPEM) is an instrument developed to obtain high spatial resolution single photon emission computed tomography (SPECT) images of small structures inside the mouse brain. SPEM consists of two independent imaging devices, which combine a multipinhole collimator, a high-resolution, thallium-doped cesium iodide [CsI(Tl)] columnar scintillator, a demagnifying/intensifier tube, and an electron-multiplying charge-coupling device (CCD). Collimators have 300- and ...

  13. Spatial assessment of wolf-dog hybridization in a single breeding period.

    Science.gov (United States)

    Pacheco, C; López-Bao, J V; García, E J; Lema, F J; Llaneza, L; Palacios, V; Godinho, R

    2017-02-14

    Understanding the dynamics of wolf-dog hybridization and delineating evidence-based conservation strategies requires information on the spatial extent of wolf-dog hybridization in real-time, which remains largely unknown. We collected 332 wolf-like scats over ca. 5,000km 2 in the NW Iberian Peninsula to evaluate wolf-dog hybridization at population level in a single breeding/pup-rearing season. Mitochondrial DNA (MtDNA) and 18 ancestry informative markers were used for species and individual identification, and to detect wolf-dog hybrids. Genetic relatedness was assessed between hybrids and wolves. We identified 130 genotypes, including 67 wolves and 7 hybrids. Three of the hybrids were backcrosses to dog whereas the others were backcrosses to wolf, the latter accounting for a 5.6% rate of introgression into the wolf population. Our results show a previously undocumented scenario of multiple and widespread wolf-dog hybridization events at the population level. However, there is a clear maintenance of wolf genetic identity, as evidenced by the sharp genetic identification of pure individuals, suggesting the resilience of wolf populations to a small amount of hybridization. We consider that real-time population level assessments of hybridization provide a new perspective into the debate on wolf conservation, with particular focus on current management guidelines applied in wolf-dog hybridization events.

  14. Spatial assessment of wolf-dog hybridization in a single breeding period

    Science.gov (United States)

    Pacheco, C.; López-Bao, J. V.; García, E. J.; Lema, F. J.; Llaneza, L.; Palacios, V.; Godinho, R.

    2017-01-01

    Understanding the dynamics of wolf-dog hybridization and delineating evidence-based conservation strategies requires information on the spatial extent of wolf-dog hybridization in real-time, which remains largely unknown. We collected 332 wolf-like scats over ca. 5,000km2 in the NW Iberian Peninsula to evaluate wolf-dog hybridization at population level in a single breeding/pup-rearing season. Mitochondrial DNA (MtDNA) and 18 ancestry informative markers were used for species and individual identification, and to detect wolf-dog hybrids. Genetic relatedness was assessed between hybrids and wolves. We identified 130 genotypes, including 67 wolves and 7 hybrids. Three of the hybrids were backcrosses to dog whereas the others were backcrosses to wolf, the latter accounting for a 5.6% rate of introgression into the wolf population. Our results show a previously undocumented scenario of multiple and widespread wolf-dog hybridization events at the population level. However, there is a clear maintenance of wolf genetic identity, as evidenced by the sharp genetic identification of pure individuals, suggesting the resilience of wolf populations to a small amount of hybridization. We consider that real-time population level assessments of hybridization provide a new perspective into the debate on wolf conservation, with particular focus on current management guidelines applied in wolf-dog hybridization events. PMID:28195213

  15. Application of a single-flicker online SSVEP BCI for spatial navigation.

    Science.gov (United States)

    Chen, Jingjing; Zhang, Dan; Engel, Andreas K; Gong, Qin; Maye, Alexander

    2017-01-01

    A promising approach for brain-computer interfaces (BCIs) employs the steady-state visual evoked potential (SSVEP) for extracting control information. Main advantages of these SSVEP BCIs are a simple and low-cost setup, little effort to adjust the system parameters to the user and comparatively high information transfer rates (ITR). However, traditional frequency-coded SSVEP BCIs require the user to gaze directly at the selected flicker stimulus, which is liable to cause fatigue or even photic epileptic seizures. The spatially coded SSVEP BCI we present in this article addresses this issue. It uses a single flicker stimulus that appears always in the extrafoveal field of view, yet it allows the user to control four control channels. We demonstrate the embedding of this novel SSVEP stimulation paradigm in the user interface of an online BCI for navigating a 2-dimensional computer game. Offline analysis of the training data reveals an average classification accuracy of 96.9±1.64%, corresponding to an information transfer rate of 30.1±1.8 bits/min. In online mode, the average classification accuracy reached 87.9±11.4%, which resulted in an ITR of 23.8±6.75 bits/min. We did not observe a strong relation between a subject's offline and online performance. Analysis of the online performance over time shows that users can reliably control the new BCI paradigm with stable performance over at least 30 minutes of continuous operation.

  16. Single-step collision-free trajectory planning of biped climbing robots in spatial trusses.

    Science.gov (United States)

    Zhu, Haifei; Guan, Yisheng; Chen, Shengjun; Su, Manjia; Zhang, Hong

    For a biped climbing robot with dual grippers to climb poles, trusses or trees, feasible collision-free climbing motion is inevitable and essential. In this paper, we utilize the sampling-based algorithm, Bi-RRT, to plan single-step collision-free motion for biped climbing robots in spatial trusses. To deal with the orientation limit of a 5-DoF biped climbing robot, a new state representation along with corresponding operations including sampling, metric calculation and interpolation is presented. A simple but effective model of a biped climbing robot in trusses is proposed, through which the motion planning of one climbing cycle is transformed to that of a manipulator. In addition, the pre- and post-processes are introduced to expedite the convergence of the Bi-RRT algorithm and to ensure the safe motion of the climbing robot near poles as well. The piecewise linear paths are smoothed by utilizing cubic B-spline curve fitting. The effectiveness and efficiency of the presented Bi-RRT algorithm for climbing motion planning are verified by simulations.

  17. Forecasting Flare Activity Using Deep Convolutional Neural Networks

    Science.gov (United States)

    Hernandez, T.

    2017-12-01

    Current operational flare forecasting relies on human morphological analysis of active regions and the persistence of solar flare activity through time (i.e. that the Sun will continue to do what it is doing right now: flaring or remaining calm). In this talk we present the results of applying deep Convolutional Neural Networks (CNNs) to the problem of solar flare forecasting. CNNs operate by training a set of tunable spatial filters that, in combination with neural layer interconnectivity, allow CNNs to automatically identify significant spatial structures predictive for classification and regression problems. We will start by discussing the applicability and success rate of the approach, the advantages it has over non-automated forecasts, and how mining our trained neural network provides a fresh look into the mechanisms behind magnetic energy storage and release.

  18. Convolutional Dictionary Learning: Acceleration and Convergence

    Science.gov (United States)

    Chun, Il Yong; Fessler, Jeffrey A.

    2018-04-01

    Convolutional dictionary learning (CDL or sparsifying CDL) has many applications in image processing and computer vision. There has been growing interest in developing efficient algorithms for CDL, mostly relying on the augmented Lagrangian (AL) method or the variant alternating direction method of multipliers (ADMM). When their parameters are properly tuned, AL methods have shown fast convergence in CDL. However, the parameter tuning process is not trivial due to its data dependence and, in practice, the convergence of AL methods depends on the AL parameters for nonconvex CDL problems. To moderate these problems, this paper proposes a new practically feasible and convergent Block Proximal Gradient method using a Majorizer (BPG-M) for CDL. The BPG-M-based CDL is investigated with different block updating schemes and majorization matrix designs, and further accelerated by incorporating some momentum coefficient formulas and restarting techniques. All of the methods investigated incorporate a boundary artifacts removal (or, more generally, sampling) operator in the learning model. Numerical experiments show that, without needing any parameter tuning process, the proposed BPG-M approach converges more stably to desirable solutions of lower objective values than the existing state-of-the-art ADMM algorithm and its memory-efficient variant do. Compared to the ADMM approaches, the BPG-M method using a multi-block updating scheme is particularly useful in single-threaded CDL algorithm handling large datasets, due to its lower memory requirement and no polynomial computational complexity. Image denoising experiments show that, for relatively strong additive white Gaussian noise, the filters learned by BPG-M-based CDL outperform those trained by the ADMM approach.

  19. Neighborhood Landscape Spatial Patterns and Land Surface Temperature: An Empirical Study on Single-Family Residential Areas in Austin, Texas

    Science.gov (United States)

    Kim, Jun-Hyun; Gu, Donghwan; Sohn, Wonmin; Kil, Sung-Ho; Kim, Hwanyong; Lee, Dong-Kun

    2016-01-01

    Rapid urbanization has accelerated land use and land cover changes, and generated the urban heat island effect (UHI). Previous studies have reported positive effects of neighborhood landscapes on mitigating urban surface temperatures. However, the influence of neighborhood landscape spatial patterns on enhancing cooling effects has not yet been fully investigated. The main objective of this study was to assess the relationships between neighborhood landscape spatial patterns and land surface temperatures (LST) by using multi-regression models considering spatial autocorrelation issues. To measure the influence of neighborhood landscape spatial patterns on LST, this study analyzed neighborhood environments of 15,862 single-family houses in Austin, Texas, USA. Using aerial photos, geographic information systems (GIS), and remote sensing, FRAGSTATS was employed to calculate values of several landscape indices used to measure neighborhood landscape spatial patterns. After controlling for the spatial autocorrelation effect, results showed that larger and better-connected landscape spatial patterns were positively correlated with lower LST values in neighborhoods, while more fragmented and isolated neighborhood landscape patterns were negatively related to the reduction of LST. PMID:27598186

  20. Neighborhood Landscape Spatial Patterns and Land Surface Temperature: An Empirical Study on Single-Family Residential Areas in Austin, Texas

    Directory of Open Access Journals (Sweden)

    Jun-Hyun Kim

    2016-09-01

    Full Text Available Rapid urbanization has accelerated land use and land cover changes, and generated the urban heat island effect (UHI. Previous studies have reported positive effects of neighborhood landscapes on mitigating urban surface temperatures. However, the influence of neighborhood landscape spatial patterns on enhancing cooling effects has not yet been fully investigated. The main objective of this study was to assess the relationships between neighborhood landscape spatial patterns and land surface temperatures (LST by using multi-regression models considering spatial autocorrelation issues. To measure the influence of neighborhood landscape spatial patterns on LST, this study analyzed neighborhood environments of 15,862 single-family houses in Austin, Texas, USA. Using aerial photos, geographic information systems (GIS, and remote sensing, FRAGSTATS was employed to calculate values of several landscape indices used to measure neighborhood landscape spatial patterns. After controlling for the spatial autocorrelation effect, results showed that larger and better-connected landscape spatial patterns were positively correlated with lower LST values in neighborhoods, while more fragmented and isolated neighborhood landscape patterns were negatively related to the reduction of LST.

  1. Neighborhood Landscape Spatial Patterns and Land Surface Temperature: An Empirical Study on Single-Family Residential Areas in Austin, Texas.

    Science.gov (United States)

    Kim, Jun-Hyun; Gu, Donghwan; Sohn, Wonmin; Kil, Sung-Ho; Kim, Hwanyong; Lee, Dong-Kun

    2016-09-02

    Rapid urbanization has accelerated land use and land cover changes, and generated the urban heat island effect (UHI). Previous studies have reported positive effects of neighborhood landscapes on mitigating urban surface temperatures. However, the influence of neighborhood landscape spatial patterns on enhancing cooling effects has not yet been fully investigated. The main objective of this study was to assess the relationships between neighborhood landscape spatial patterns and land surface temperatures (LST) by using multi-regression models considering spatial autocorrelation issues. To measure the influence of neighborhood landscape spatial patterns on LST, this study analyzed neighborhood environments of 15,862 single-family houses in Austin, Texas, USA. Using aerial photos, geographic information systems (GIS), and remote sensing, FRAGSTATS was employed to calculate values of several landscape indices used to measure neighborhood landscape spatial patterns. After controlling for the spatial autocorrelation effect, results showed that larger and better-connected landscape spatial patterns were positively correlated with lower LST values in neighborhoods, while more fragmented and isolated neighborhood landscape patterns were negatively related to the reduction of LST.

  2. Single-trial detection of visual evoked potentials by common spatial patterns and wavelet filtering for brain-computer interface.

    Science.gov (United States)

    Tu, Yiheng; Huang, Gan; Hung, Yeung Sam; Hu, Li; Hu, Yong; Zhang, Zhiguo

    2013-01-01

    Event-related potentials (ERPs) are widely used in brain-computer interface (BCI) systems as input signals conveying a subject's intention. A fast and reliable single-trial ERP detection method can be used to develop a BCI system with both high speed and high accuracy. However, most of single-trial ERP detection methods are developed for offline EEG analysis and thus have a high computational complexity and need manual operations. Therefore, they are not applicable to practical BCI systems, which require a low-complexity and automatic ERP detection method. This work presents a joint spatial-time-frequency filter that combines common spatial patterns (CSP) and wavelet filtering (WF) for improving the signal-to-noise (SNR) of visual evoked potentials (VEP), which can lead to a single-trial ERP-based BCI.

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

    CSIR Research Space (South Africa)

    Cronje, J

    2015-11-01

    Full Text Available The work in this paper address the problem of removing non-uniform motion blur from a single image. The motion vector for an image patch is estimated by using a convolutional neural network (CNN). All the predicted motion vectors are combined...

  4. Human Face Recognition Using Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Răzvan-Daniel Albu

    2009-10-01

    Full Text Available In this paper, I present a novel hybrid face recognition approach based on a convolutional neural architecture, designed to robustly detect highly variable face patterns. The convolutional network extracts successively larger features in a hierarchical set of layers. With the weights of the trained neural networks there are created kernel windows used for feature extraction in a 3-stage algorithm. I present experimental results illustrating the efficiency of the proposed approach. I use a database of 796 images of 159 individuals from Reims University which contains quite a high degree of variability in expression, pose, and facial details.

  5. Cascaded K-means convolutional feature learner and its application to face recognition

    Science.gov (United States)

    Zhou, Daoxiang; Yang, Dan; Zhang, Xiaohong; Huang, Sheng; Feng, Shu

    2017-09-01

    Currently, considerable efforts have been devoted to devise image representation. However, handcrafted methods need strong domain knowledge and show low generalization ability, and conventional feature learning methods require enormous training data and rich parameters tuning experience. A lightened feature learner is presented to solve these problems with application to face recognition, which shares similar topology architecture as a convolutional neural network. Our model is divided into three components: cascaded convolution filters bank learning layer, nonlinear processing layer, and feature pooling layer. Specifically, in the filters learning layer, we use K-means to learn convolution filters. Features are extracted via convoluting images with the learned filters. Afterward, in the nonlinear processing layer, hyperbolic tangent is employed to capture the nonlinear feature. In the feature pooling layer, to remove the redundancy information and incorporate the spatial layout, we exploit multilevel spatial pyramid second-order pooling technique to pool the features in subregions and concatenate them together as the final representation. Extensive experiments on four representative datasets demonstrate the effectiveness and robustness of our model to various variations, yielding competitive recognition results on extended Yale B and FERET. In addition, our method achieves the best identification performance on AR and labeled faces in the wild datasets among the comparative methods.

  6. Feedback equivalence of convolutional codes over finite rings

    Directory of Open Access Journals (Sweden)

    DeCastro-García Noemí

    2017-12-01

    Full Text Available The approach to convolutional codes from the linear systems point of view provides us with effective tools in order to construct convolutional codes with adequate properties that let us use them in many applications. In this work, we have generalized feedback equivalence between families of convolutional codes and linear systems over certain rings, and we show that every locally Brunovsky linear system may be considered as a representation of a code under feedback convolutional equivalence.

  7. Histopathological image classification with bilinear convolutional neural networks.

    Science.gov (United States)

    Chaofeng Wang; Jun Shi; Qi Zhang; Shihui Ying

    2017-07-01

    The computer-aided quantitative analysis for histopathological images has attracted considerable attention. The stain decomposition on histopathological images is usually recommended to address the issue of co-localization or aliasing of tissue substances. Although the convolutional neural networks (CNN) is a popular deep learning algorithm for various tasks on histopathological image analysis, it is only directly performed on histopathological images without considering stain decomposition. The bilinear CNN (BCNN) is a new CNN model for fine-grained classification. BCNN consists of two CNNs, whose convolutional-layer outputs are multiplied with outer product at each spatial location. In this work, we propose a novel BCNN-based method for classification of histopathological images, which first decomposes histopathological images into hematoxylin and eosin stain components, and then perform BCNN on the decomposed images to fuse and improve the feature representation performance. The experimental results on the colorectal cancer histopathological image dataset with eight classes indicate that the proposed BCNN-based algorithm is superior to the traditional CNN.

  8. Image Classification Based on Convolutional Denoising Sparse Autoencoder

    Directory of Open Access Journals (Sweden)

    Shuangshuang Chen

    2017-01-01

    Full Text Available Image classification aims to group images into corresponding semantic categories. Due to the difficulties of interclass similarity and intraclass variability, it is a challenging issue in computer vision. In this paper, an unsupervised feature learning approach called convolutional denoising sparse autoencoder (CDSAE is proposed based on the theory of visual attention mechanism and deep learning methods. Firstly, saliency detection method is utilized to get training samples for unsupervised feature learning. Next, these samples are sent to the denoising sparse autoencoder (DSAE, followed by convolutional layer and local contrast normalization layer. Generally, prior in a specific task is helpful for the task solution. Therefore, a new pooling strategy—spatial pyramid pooling (SPP fused with center-bias prior—is introduced into our approach. Experimental results on the common two image datasets (STL-10 and CIFAR-10 demonstrate that our approach is effective in image classification. They also demonstrate that none of these three components: local contrast normalization, SPP fused with center-prior, and l2 vector normalization can be excluded from our proposed approach. They jointly improve image representation and classification performance.

  9. Gradient Flow Convolutive Blind Source Separation

    DEFF Research Database (Denmark)

    Pedersen, Michael Syskind; Nielsen, Chinton Møller

    2004-01-01

    Experiments have shown that the performance of instantaneous gradient flow beamforming by Cauwenberghs et al. is reduced significantly in reverberant conditions. By expanding the gradient flow principle to convolutive mixtures, separation in a reverberant environment is possible. By use of a circ...

  10. Medical Text Classification Using Convolutional Neural Networks.

    Science.gov (United States)

    Hughes, Mark; Li, Irene; Kotoulas, Spyros; Suzumura, Toyotaro

    2017-01-01

    We present an approach to automatically classify clinical text at a sentence level. We are using deep convolutional neural networks to represent complex features. We train the network on a dataset providing a broad categorization of health information. Through a detailed evaluation, we demonstrate that our method outperforms several approaches widely used in natural language processing tasks by about 15%.

  11. Convolutional Neural Networks for SAR Image Segmentation

    DEFF Research Database (Denmark)

    Malmgren-Hansen, David; Nobel-Jørgensen, Morten

    2015-01-01

    Segmentation of Synthetic Aperture Radar (SAR) images has several uses, but it is a difficult task due to a number of properties related to SAR images. In this article we show how Convolutional Neural Networks (CNNs) can easily be trained for SAR image segmentation with good results. Besides...

  12. Single-grain cosmogenic Ne-21 concentrations in fluvial sediment reveal spatially variable erosion rates

    OpenAIRE

    Alexandru T. Codilean; P. Bishop; F. M. Stuart; T. B. Hoey; D. Fabel; S. P. H. T. Freeman;  

    2008-01-01

    We evaluated the hypothesis that the spatial variation in erosion in a catchment is refl ected in the distribution of the cosmogenic nuclide concentrations in sediments leaving the catchment. Using published data and four new 10Be measurements in fl uvial sediment collected from the outlets of small river catchments, we constrained the spatial variability of erosion rates in the Gaub River catchment in Namibia. We combined these catchment-averaged erosion rates, and the mean slope values with...

  13. Plane-wave decomposition by spherical-convolution microphone array

    Science.gov (United States)

    Rafaely, Boaz; Park, Munhum

    2004-05-01

    Reverberant sound fields are widely studied, as they have a significant influence on the acoustic performance of enclosures in a variety of applications. For example, the intelligibility of speech in lecture rooms, the quality of music in auditoria, the noise level in offices, and the production of 3D sound in living rooms are all affected by the enclosed sound field. These sound fields are typically studied through frequency response measurements or statistical measures such as reverberation time, which do not provide detailed spatial information. The aim of the work presented in this seminar is the detailed analysis of reverberant sound fields. A measurement and analysis system based on acoustic theory and signal processing, designed around a spherical microphone array, is presented. Detailed analysis is achieved by decomposition of the sound field into waves, using spherical Fourier transform and spherical convolution. The presentation will include theoretical review, simulation studies, and initial experimental results.

  14. 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%.

  15. Multi-Branch Fully Convolutional Network for Face Detection

    KAUST Repository

    Bai, Yancheng

    2017-07-20

    Face detection is a fundamental problem in computer vision. It is still a challenging task in unconstrained conditions due to significant variations in scale, pose, expressions, and occlusion. In this paper, we propose a multi-branch fully convolutional network (MB-FCN) for face detection, which considers both efficiency and effectiveness in the design process. Our MB-FCN detector can deal with faces at all scale ranges with only a single pass through the backbone network. As such, our MB-FCN model saves computation and thus is more efficient, compared to previous methods that make multiple passes. For each branch, the specific skip connections of the convolutional feature maps at different layers are exploited to represent faces in specific scale ranges. Specifically, small faces can be represented with both shallow fine-grained and deep powerful coarse features. With this representation, superior improvement in performance is registered for the task of detecting small faces. We test our MB-FCN detector on two public face detection benchmarks, including FDDB and WIDER FACE. Extensive experiments show that our detector outperforms state-of-the-art methods on all these datasets in general and by a substantial margin on the most challenging among them (e.g. WIDER FACE Hard subset). Also, MB-FCN runs at 15 FPS on a GPU for images of size 640 x 480 with no assumption on the minimum detectable face size.

  16. Limitations of the equivalence between spatial and ensemble estimators in the case of a single-tone excitation.

    Science.gov (United States)

    Monsef, Florian; Cozza, Andrea

    2011-10-01

    The ensemble-average value of the mean-square pressure is often assessed by using the spatial-average technique, underlying an equivalence principle between spatial and ensemble estimators. Using the ideal-diffuse-field model, the accuracy of the spatial-average method has been studied theoretically forty years ago in the case of a single-tone excitation. This study is revisited in the present work on the basis of a more realistic description of the sound field accounting for a finite number of plane waves. The analysis of the spatial-average estimator is based on the study of its convergence rate. Using experimental data from practical examples, it is shown that the classical expression underestimates the estimator uncertainty even for frequencies greater than Schroeder's frequency, and that the number of plane waves may act as lower bound on the spatial-average estimator accuracy. The comparison of the convergence rate with an ensemble-estimator shows that the two statistics cannot be regarded as equivalent in a general case. © 2011 Acoustical Society of America

  17. Convolution and non convolution Perfectly Matched Layer techniques optimized at grazing incidence for high-order wave propagation modelling

    Science.gov (United States)

    Martin, Roland; Komatitsch, Dimitri; Bruthiaux, Emilien; Gedney, Stephen D.

    2010-05-01

    by 40% in 2D comparing to the GFPML split formulation of [4]. Examples of waves propagating in heterogeneous thin slices in presence of free surface are shown. We also applied this CPML technique to more complex models like poroelastic [5] or viscoelastic [6] media based on a fourth-order staggered finite-difference method. For the two-dimensional Biot poroelastic equations we show its efficiency for both non dissipative and dissipative Biot porous models. For the three-dimensional viscoelastic seismic wave equation, the time marching equations of the standard linear solid mechanisms used do not need to be split and only the memory variables associated with velocity derivatives are stored at each time step. In the case of more than one damping mechanism, we are able to reduce memory storage by more than 70% in the PML regions in 3D simulations compared to split PMLs optimized at grazing incidence. Benchmarks of the CPML technique have been validated in poroelastic or viscoelastic thin mesh slices. These unsplit CPMLs are usually computed based on a second-order finite-difference time scheme. However, in many situations like very long time simulations, it is of interest to increase the accuracy of the method by increasing the order of the time marching and spatial discretizations. The CPML is not able to be increased at high orders because of its convolution formulation. In [7] we study then how to build a new unsplit PML (ADE-PML/Auxiliary Differential Equations PML) that remains optimized at grazing incidence based on a high-order time scheme like the fourth-order Runge-Kutta scheme. At second order in time we demonstrate that CPML and ADE-PML are equivalent. At second or high order discretization in time, explicit and semi-implicit solutions can be obtained with very good accuracy. References [1]Dimitri Komatitsch and Roland Martin. An unsplit convolutional Perfectly Matched Layer improved at grazing incidence for the differential anisotropic elastic wave equation

  18. Hierarchical Recurrent Neural Hashing for Image Retrieval With Hierarchical Convolutional Features.

    Science.gov (United States)

    Lu, Xiaoqiang; Chen, Yaxiong; Li, Xuelong

    Hashing has been an important and effective technology in image retrieval due to its computational efficiency and fast search speed. The traditional hashing methods usually learn hash functions to obtain binary codes by exploiting hand-crafted features, which cannot optimally represent the information of the sample. Recently, deep learning methods can achieve better performance, since deep learning architectures can learn more effective image representation features. However, these methods only use semantic features to generate hash codes by shallow projection but ignore texture details. In this paper, we proposed a novel hashing method, namely hierarchical recurrent neural hashing (HRNH), to exploit hierarchical recurrent neural network to generate effective hash codes. There are three contributions of this paper. First, a deep hashing method is proposed to extensively exploit both spatial details and semantic information, in which, we leverage hierarchical convolutional features to construct image pyramid representation. Second, our proposed deep network can exploit directly convolutional feature maps as input to preserve the spatial structure of convolutional feature maps. Finally, we propose a new loss function that considers the quantization error of binarizing the continuous embeddings into the discrete binary codes, and simultaneously maintains the semantic similarity and balanceable property of hash codes. Experimental results on four widely used data sets demonstrate that the proposed HRNH can achieve superior performance over other state-of-the-art hashing methods.Hashing has been an important and effective technology in image retrieval due to its computational efficiency and fast search speed. The traditional hashing methods usually learn hash functions to obtain binary codes by exploiting hand-crafted features, which cannot optimally represent the information of the sample. Recently, deep learning methods can achieve better performance, since deep

  19. Bilinear common spatial pattern for single-trial ERP-based rapid serial visual presentation triage.

    Science.gov (United States)

    Yu, K; Shen, K; Shao, S; Ng, W C; Li, X

    2012-08-01

    Common spatial pattern (CSP) analysis is a useful tool for the feature extraction of event-related potentials (ERP). However, CSP is essentially time invariant, and thus unable to exploit the temporal information of ERP. This paper proposes a variant of CSP, namely bilinear common spatial pattern (BCSP), which is capable of accommodating both spatial and temporal information. BCSP generalizes CSP through iteratively optimizing bilinear filters. These bilinear filters constitute a spatio-temporal subspace in which the separation between two conditions is maximized. The method is unique in the sense that it is mathematically intuitive and simple, as all the bilinear filters are obtained by maximizing the power ratio as CSP does. The proposed method was evaluated on 20 subjects' ERP data collected in rapid serial visual presentation triage experiments. The results show that BCSP achieved significantly higher average test accuracy (12.3% higher, p < 0.001).

  20. Small-Scale Spatial Analysis of In Situ Sea Temperature throughout a Single Coral Patch Reef

    Directory of Open Access Journals (Sweden)

    Kelvin D. Gorospe

    2011-01-01

    Full Text Available Thermal stress can cause geographically widespread bleaching events, during which corals become decoupled from their symbiotic algae. Bleaching, however, also can occur on smaller, spatially patchy scales, with corals on the same reef exhibiting varying bleaching responses. Thus, to investigate fine spatial scale sea temperature variation, temperature loggers were deployed on a 4 m grid on a patch reef in Kāne'ohe Bay, Oahu, Hawai‘i to monitor in situ, benthic temperature every 50 minutes at 85 locations for two years. Temperature variation on the reef was characterized using several summary indices related to coral thermal stress. Results show that stable, biologically significant temperature variation indeed exists at small scales and that depth, relative water flow, and substrate cover and type were not significant drivers of this variation. Instead, finer spatial and temporal scale advection processes at the benthic boundary layer are likely responsible. The implications for coral ecology and conservation are discussed.

  1. Improving the Separability of Deep Features with Discriminative Convolution Filters for RSI Classification

    Directory of Open Access Journals (Sweden)

    Na Liu

    2018-03-01

    Full Text Available The extraction of activation vectors (or deep features from the fully connected layers of a convolutional neural network (CNN model is widely used for remote sensing image (RSI representation. In this study, we propose to learn discriminative convolution filter (DCF based on class-specific separability criteria for linear transformation of deep features. In particular, two types of pretrained CNN called CaffeNet and VGG-VD16 are introduced to illustrate the generality of the proposed DCF. The activation vectors extracted from the fully connected layers of a CNN are rearranged into the form of an image matrix, from which a spatial arrangement of local patches is extracted using sliding window strategy. DCF learning is then performed on each local patch individually to obtain the corresponding discriminative convolution kernel through generalized eigenvalue decomposition. The proposed DCF learning characterizes that a convolutional kernel with small size (e.g., 3 × 3 pixels can be effectively learned on a small-size local patch (e.g., 8 × 8 pixels, thereby ensuring that the linear transformation of deep features can maintain low computational complexity. Experiments on two RSI datasets demonstrate the effectiveness of DCF in improving the classification performances of deep features without increasing dimensionality.

  2. Photosensitized production of singlet oxygen: spatially-resolved optical studies in single cells

    DEFF Research Database (Denmark)

    Breitenbach, Thomas; Kuimova, Marina; Gbur, Peter

    2009-01-01

    be monitored using viability assays. Time- and spatially-resolved optical measurements of both singlet oxygen and its precursor, the excited state sensitizer, reflect the complex and dynamic morphology of the cell. These experiments help elucidate photoinduced, oxygen-dependent events that compromise cell...

  3. The "when" and the "where" of single-trial allocentric spatial memory performance in young children: Insights into the development of episodic memory.

    Science.gov (United States)

    Ribordy Lambert, Farfalla; Lavenex, Pierre; Banta Lavenex, Pamela

    2017-03-01

    Allocentric spatial memory, "where" with respect to the surrounding environment, is one of the three fundamental components of episodic memory: what, where, when. Whereas basic allocentric spatial memory abilities are reliably observed in children after 2 years of age, coinciding with the offset of infantile amnesia, the resolution of allocentric spatial memory acquired over repeated trials improves from 2 to 4 years of age. Here, we first show that single-trial allocentric spatial memory performance improves in children from 3.5 to 7 years of age, during the typical period of childhood amnesia. Second, we show that large individual variation exists in children's performance at this age. Third, and most importantly, we show that improvements in single-trial allocentric spatial memory performance are due to an increasing ability to spatially and temporally separate locations and events. Such improvements in spatial and temporal processing abilities may contribute to the gradual offset of childhood amnesia. © 2016 Wiley Periodicals, Inc.

  4. Gas Classification Using Deep Convolutional Neural Networks.

    Science.gov (United States)

    Peng, Pai; Zhao, Xiaojin; Pan, Xiaofang; Ye, Wenbin

    2018-01-08

    In this work, we propose a novel Deep Convolutional Neural Network (DCNN) tailored for gas classification. Inspired by the great success of DCNN in the field of computer vision, we designed a DCNN with up to 38 layers. In general, the proposed gas neural network, named GasNet, consists of: six convolutional blocks, each block consist of six layers; a pooling layer; and a fully-connected layer. Together, these various layers make up a powerful deep model for gas classification. Experimental results show that the proposed DCNN method is an effective technique for classifying electronic nose data. We also demonstrate that the DCNN method can provide higher classification accuracy than comparable Support Vector Machine (SVM) methods and Multiple Layer Perceptron (MLP).

  5. 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.

  6. Epileptiform spike detection via convolutional neural networks

    DEFF Research Database (Denmark)

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

    2016-01-01

    The EEG of epileptic patients often contains sharp waveforms called "spikes", occurring between seizures. Detecting such spikes is crucial for diagnosing epilepsy. In this paper, we develop a convolutional neural network (CNN) for detecting spikes in EEG of epileptic patients in an automated...... fashion. The CNN has a convolutional architecture with filters of various sizes applied to the input layer, leaky ReLUs as activation functions, and a sigmoid output layer. Balanced mini-batches were applied to handle the imbalance in the data set. Leave-one-patient-out cross-validation was carried out...... to test the CNN and benchmark models on EEG data of five epilepsy patients. We achieved 0.947 AUC for the CNN, while the best performing benchmark model, Support Vector Machines with Gaussian kernel, achieved an AUC of 0.912....

  7. Chemometric strategies to unmix information and increase the spatial description of hyperspectral images: a single-cell case study.

    Science.gov (United States)

    Piqueras, S; Duponchel, L; Offroy, M; Jamme, F; Tauler, R; de Juan, A

    2013-07-02

    Hyperspectral images are analytical measurements that provide spatial and structural information. The spatial description of the samples is the specific asset of these measurements and the reason why they have become so important in (bio)chemical fields, where the microdistribution of sample constituents or the morphology or spatial pattern of sample elements constitute very relevant information. Often, because of the small size of the samples, the spatial detail provided by the image acquisition systems is insufficient. This work proposes a data processing strategy to overcome this instrumental limitation and increase the natural spatial detail present in the acquired raw images. The approach works by combining the information of a set of images, slightly shifted from each other with a motion step among them lower than the pixel size of the raw images. The data treatment includes the application of multivariate curve resolution (unmixing) multiset analysis to the set of collected images to obtain the distribution maps and spectral signatures of the sample constituents. These sets of maps are noise-filtered and compound-specific representations of all the relevant information in the pixel space and decrease the dimensionality of the original image from hundreds of spectral channels to few sets of maps, one per sample constituent or element. The information in each compound-specific set of maps is combined via a super-resolution post-processing algorithm, which takes into account the shifting, decimation, and point spread function of the instrument to reconstruct a single map per sample constituent with much higher spatial detail than that of the original image measurement.

  8. Vehicle Color Recognition using Convolutional Neural Network

    OpenAIRE

    Rachmadi, Reza Fuad; Purnama, I Ketut Eddy

    2015-01-01

    Vehicle color information is one of the important elements in ITS (Intelligent Traffic System). In this paper, we present a vehicle color recognition method using convolutional neural network (CNN). Naturally, CNN is designed to learn classification method based on shape information, but we proved that CNN can also learn classification based on color distribution. In our method, we convert the input image to two different color spaces, HSV and CIE Lab, and run it to some CNN architecture. The...

  9. Satellite image classification using convolutional learning

    Science.gov (United States)

    Nguyen, Thao; Han, Jiho; Park, Dong-Chul

    2013-10-01

    A satellite image classification method using Convolutional Neural Network (CNN) architecture is proposed in this paper. As a special case of deep learning, CNN classifies classes of images without any feature extraction step while other existing classification methods utilize rather complex feature extraction processes. Experiments on a set of satellite image data and the preliminary results show that the proposed classification method can be a promising alternative over existing feature extraction-based schemes in terms of classification accuracy and classification speed.

  10. Landcover Classification Using Deep Fully Convolutional Neural Networks

    Science.gov (United States)

    Wang, J.; Li, X.; Zhou, S.; Tang, J.

    2017-12-01

    Land cover classification has always been an essential application in remote sensing. Certain image features are needed for land cover classification whether it is based on pixel or object-based methods. Different from other machine learning methods, deep learning model not only extracts useful information from multiple bands/attributes, but also learns spatial characteristics. In recent years, deep learning methods have been developed rapidly and widely applied in image recognition, semantic understanding, and other application domains. However, there are limited studies applying deep learning methods in land cover classification. In this research, we used fully convolutional networks (FCN) as the deep learning model to classify land covers. The National Land Cover Database (NLCD) within the state of Kansas was used as training dataset and Landsat images were classified using the trained FCN model. We also applied an image segmentation method to improve the original results from the FCN model. In addition, the pros and cons between deep learning and several machine learning methods were compared and explored. Our research indicates: (1) FCN is an effective classification model with an overall accuracy of 75%; (2) image segmentation improves the classification results with better match of spatial patterns; (3) FCN has an excellent ability of learning which can attains higher accuracy and better spatial patterns compared with several machine learning methods.

  11. Deep convolutional neural network for prostate MR segmentation

    Science.gov (United States)

    Tian, Zhiqiang; Liu, Lizhi; Fei, Baowei

    2017-03-01

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

  12. Simultaneous multislice imaging for native myocardial T1mapping: Improved spatial coverage in a single breath-hold.

    Science.gov (United States)

    Weingärtner, Sebastian; Moeller, Steen; Schmitter, Sebastian; Auerbach, Edward; Kellman, Peter; Shenoy, Chetan; Akçakaya, Mehmet

    2017-08-01

    To develop a saturation recovery myocardial T 1 mapping method for the simultaneous multislice acquisition of three slices. Saturation pulse-prepared heart rate independent inversion recovery (SAPPHIRE) T 1 mapping was implemented with simultaneous multislice imaging using FLASH readouts for faster coverage of the myocardium. Controlled aliasing in parallel imaging (CAIPI) was used to achieve minimal noise amplification in three slices. Multiband reconstruction was performed using three linear reconstruction methods: Slice- and in-plane GRAPPA, CG-SENSE, and Tikhonov-regularized CG-SENSE. Accuracy, spatial variability, and interslice leakage were compared with single-band T 1 mapping in a phantom and in six healthy subjects. Multiband phantom T 1 times showed good agreement with single-band T 1 mapping for all three reconstruction methods (normalized root mean square error spatial variability compared with single-band imaging was lowest for GRAPPA (1.29-fold), with higher penalties for Tikhonov-regularized CG-SENSE (1.47-fold) and CG-SENSE (1.52-fold). In vivo multiband T 1 times showed no significant difference compared with single-band (T 1 time ± intersegmental variability: single-band, 1580 ± 119 ms; GRAPPA, 1572 ± 145 ms; CG-SENSE, 1579 ± 159 ms; Tikhonov, 1586 ± 150 ms [analysis of variance; P = 0.86]). Interslice leakage was smallest for GRAPPA (5.4%) and higher for CG-SENSE (6.2%) and Tikhonov-regularized CG-SENSE (7.9%). Multiband accelerated myocardial T 1 mapping demonstrated the potential for single-breath-hold T 1 quantification in 16 American Heart Association segments over three slices. A 1.2- to 1.4-fold higher in vivo spatial variability was observed, where GRAPPA-based reconstruction showed the highest homogeneity and the least interslice leakage. Magn Reson Med 78:462-471, 2017. © 2017 International Society for Magnetic Resonance in Medicine. © 2017 International Society for Magnetic Resonance in Medicine.

  13. Single-molecule diffusion and conformational dynamics by spatial integration of temporal fluctuations

    KAUST Repository

    Serag, Maged F.

    2014-10-06

    Single-molecule localization and tracking has been used to translate spatiotemporal information of individual molecules to map their diffusion behaviours. However, accurate analysis of diffusion behaviours and including other parameters, such as the conformation and size of molecules, remain as limitations to the method. Here, we report a method that addresses the limitations of existing single-molecular localization methods. The method is based on temporal tracking of the cumulative area occupied by molecules. These temporal fluctuations are tied to molecular size, rates of diffusion and conformational changes. By analysing fluorescent nanospheres and double-stranded DNA molecules of different lengths and topological forms, we demonstrate that our cumulative-area method surpasses the conventional single-molecule localization method in terms of the accuracy of determined diffusion coefficients. Furthermore, the cumulative-area method provides conformational relaxation times of structurally flexible chains along with diffusion coefficients, which together are relevant to work in a wide spectrum of scientific fields.

  14. The Urbanik generalized convolutions in the non-commutative ...

    Indian Academy of Sciences (India)

    −sν(dx) < ∞. Now we apply this construction to the Kendall convolution case, starting with the weakly stable measure δ1. Example 1. Let △ be the Kendall convolution, i.e. the generalized convolution with the probability kernel: δ1△δa = (1 − a)δ1 + aπ2 for a ∈ [0, 1] and π2 be the Pareto distribution with the density π2(dx) =.

  15. An Algorithm for the Convolution of Legendre Series

    KAUST Repository

    Hale, Nicholas

    2014-01-01

    An O(N2) algorithm for the convolution of compactly supported Legendre series is described. The algorithm is derived from the convolution theorem for Legendre polynomials and the recurrence relation satisfied by spherical Bessel functions. Combining with previous work yields an O(N 2) algorithm for the convolution of Chebyshev series. Numerical results are presented to demonstrate the improved efficiency over the existing algorithm. © 2014 Society for Industrial and Applied Mathematics.

  16. Detection of User Independent Single Trial ERPs in Brain Computer Interfaces: An Adaptive Spatial Filtering Approach

    DEFF Research Database (Denmark)

    Leza, Cristina; Puthusserypady, Sadasivan

    2017-01-01

    Brain Computer Interfaces (BCIs) use brain signals to communicate with the external world. The main challenges to address are speed, accuracy and adaptability. Here, a novel algorithm for P300 based BCI spelling system is presented, specifically suited for single-trial detection of Event...

  17. Temporal and spatial evolution characteristics of disturbance wave in a hypersonic boundary layer due to single-frequency entropy disturbance.

    Science.gov (United States)

    Wang, Zhenqing; Tang, Xiaojun; Lv, Hongqing; Shi, Jianqiang

    2014-01-01

    By using a high-order accurate finite difference scheme, direct numerical simulation of hypersonic flow over an 8° half-wedge-angle blunt wedge under freestream single-frequency entropy disturbance is conducted; the generation and the temporal and spatial nonlinear evolution of boundary layer disturbance waves are investigated. Results show that, under the freestream single-frequency entropy disturbance, the entropy state of boundary layer is changed sharply and the disturbance waves within a certain frequency range are induced in the boundary layer. Furthermore, the amplitudes of disturbance waves in the period phase are larger than that in the response phase and ablation phase and the frequency range in the boundary layer in the period phase is narrower than that in these two phases. In addition, the mode competition, dominant mode transformation, and disturbance energy transfer exist among different modes both in temporal and in spatial evolution. The mode competition changes the characteristics of nonlinear evolution of the unstable waves in the boundary layer. The development of the most unstable mode along streamwise relies more on the motivation of disturbance waves in the upstream than that of other modes on this motivation.

  18. Can zebrafish learn spatial tasks? An empirical analysis of place and single CS-US associative learning.

    Science.gov (United States)

    Karnik, Indraneel; Gerlai, Robert

    2012-08-01

    The zebrafish may be an ideal tool with which genes underlying learning and memory can be identified and functionally investigated. From a translational viewpoint, relational learning and episodic memory are particularly important as their impairment is the hallmark of prevalent human neurodegenerative diseases. Recent reports suggest that zebrafish are capable of solving complex relational-type associative learning tasks, namely spatial learning tasks. However, it is not known whether good performance in these tasks was truly based upon relational learning or upon a single CS-US association. Here we study whether zebrafish can find a rewarding stimulus (sight of conspecifics) based upon a single associative cue or/and upon the location of the reward using a method conceptually similar to 'context and cue dependent fear conditioning' employed with rodents. Our results confirm that zebrafish can form an association between a salient visual cue and the rewarding stimulus and at the same time they can also learn where the reward is presented. Although our results do not prove that zebrafish form a dynamic spatial map of their surroundings and use this map to locate their reward, they do show that these fish perform similarly to rodents whose hippocampal function is unimpaired. These results further strengthen the notion that complex cognitive abilities exist in the zebrafish and thus they may be analyzed using the excellent genetic tool set developed for this simple vertebrate. Copyright © 2012 Elsevier B.V. All rights reserved.

  19. Correlated spectroscopic imaging of calf muscle in three spatial dimensions using group sparse reconstruction of undersampled single and multichannel data.

    Science.gov (United States)

    Wilson, Neil E; Burns, Brian L; Iqbal, Zohaib; Thomas, M Albert

    2015-11-01

    To implement a 5D (three spatial + two spectral) correlated spectroscopic imaging sequence for application to human calf. Nonuniform sampling was applied across the two phase encoded dimensions and the indirect spectral dimension of an echo planar-correlated spectroscopic imaging sequence. Reconstruction was applied that minimized the group sparse mixed ℓ2,1-norm of the data. Multichannel data were compressed using a sensitivity map-based approach with a spatially dependent transform matrix and utilized the self-sparsity of the individual coil images to simplify the reconstruction. Single channel data with 8× and 16× undersampling are shown in the calf of a diabetic patient. A 15-channel scan with 12× undersampling of a healthy volunteer was reconstructed using 5 virtual channels and compared to a fully sampled single slice scan. Group sparse reconstruction faithfully reconstructs the lipid cross peaks much better than ℓ1 minimization. COSY spectra can be acquired over a 3D spatial volume with scan time under 15 min using echo planar readout with highly undersampled data and group sparse reconstruction. © 2015 Wiley Periodicals, Inc.

  20. 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.

  1. 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.

  2. Single Cell Responses to Spatially Controlled Photosensitized Production of Extracellular Singlet Oxygen

    DEFF Research Database (Denmark)

    Pedersen, Brian Wett; Sinks, Louise E.; Breitenbach, Thomas

    2011-01-01

    The response of individual HeLa cells to extracellularly produced singlet oxygen was examined. The spatial domain of singlet oxygen production was controlled using the combination of a membrane-impermeable Pd porphyrin-dendrimer, which served as a photosensitizer, and a focused laser, which served...... to localize the sensitized production of singlet oxygen. Cells in close proximity to the domain of singlet oxygen production showed morphological changes commonly associated with necrotic cell death. The elapsed post-irradiation “waiting period” before necrosis became apparent depended on (a) the distance...... between the cell membrane and the domain irradiated, (b) the incident laser fluence and, as such, the initial concentration of singlet oxygen produced, and (c) the lifetime of singlet oxygen. The data imply that singlet oxygen plays a key role in this process of light-induced cell death. The approach...

  3. Radiofrequency Ablation, MR Thermometry, and High-Spatial-Resolution MR Parametric Imaging with a Single, Minimally Invasive Device

    Science.gov (United States)

    Ertürk, M. Arcan; Sathyanarayana Hegde, Shashank

    2016-01-01

    Purpose To develop and demonstrate in vitro and in vivo a single interventional magnetic resonance (MR)–active device that integrates the functions of precise identification of a tissue site with the delivery of radiofrequency (RF) energy for ablation, high-spatial-resolution thermal mapping to monitor thermal dose, and quantitative MR imaging relaxometry to document ablation-induced tissue changes for characterizing ablated tissue. Materials and Methods All animal studies were approved by the institutional animal care and use committee. A loopless MR imaging antenna composed of a tuned microcable either 0.8 or 2.2 mm in diameter with an extended central conductor was switched between a 3-T MR imaging unit and an RF power source to monitor and perform RF ablation in bovine muscle and human artery samples in vitro and in rabbits in vivo. High-spatial-resolution (250–300-μm) proton resonance frequency shift MR thermometry was interleaved with ablations. Quantitative spin-lattice (T1) and spin-spin (T2) relaxation time MR imaging mapping was performed before and after ablation. These maps were compared with findings from gross tissue examination of the region of ablated tissue after MR imaging. Results High-spatial-resolution MR imaging afforded temperature mapping in less than 8 seconds for monitoring ablation temperatures in excess of 85°C delivered by the same device. This produced irreversible thermal injury and necrosis. Quantitative MR imaging relaxation time maps demonstrated up to a twofold variation in mean regional T1 and T2 after ablation versus before ablation. Conclusion A simple, integrated, minimally invasive interventional probe that provides image-guided therapy delivery, thermal mapping of dose, and detection of ablation-associated MR imaging parametric changes was developed and demonstrated. With this single-device approach, coupling-related safety concerns associated with multiple conductor approaches were avoided. © RSNA, 2016 Online

  4. Performance assessment of the single photon emission microscope: high spatial resolution SPECT imaging of small animal organs

    Directory of Open Access Journals (Sweden)

    J. Mejia

    2013-11-01

    Full Text Available The single photon emission microscope (SPEM is an instrument developed to obtain high spatial resolution single photon emission computed tomography (SPECT images of small structures inside the mouse brain. SPEM consists of two independent imaging devices, which combine a multipinhole collimator, a high-resolution, thallium-doped cesium iodide [CsI(Tl] columnar scintillator, a demagnifying/intensifier tube, and an electron-multiplying charge-coupling device (CCD. Collimators have 300- and 450-µm diameter pinholes on tungsten slabs, in hexagonal arrays of 19 and 7 holes. Projection data are acquired in a photon-counting strategy, where CCD frames are stored at 50 frames per second, with a radius of rotation of 35 mm and magnification factor of one. The image reconstruction software tool is based on the maximum likelihood algorithm. Our aim was to evaluate the spatial resolution and sensitivity attainable with the seven-pinhole imaging device, together with the linearity for quantification on the tomographic images, and to test the instrument in obtaining tomographic images of different mouse organs. A spatial resolution better than 500 µm and a sensitivity of 21.6 counts·s-1·MBq-1 were reached, as well as a correlation coefficient between activity and intensity better than 0.99, when imaging 99mTc sources. Images of the thyroid, heart, lungs, and bones of mice were registered using 99mTc-labeled radiopharmaceuticals in times appropriate for routine preclinical experimentation of <1 h per projection data set. Detailed experimental protocols and images of the aforementioned organs are shown. We plan to extend the instrument's field of view to fix larger animals and to combine data from both detectors to reduce the acquisition time or applied activity.

  5. Performance assessment of the single photon emission microscope: high spatial resolution SPECT imaging of small animal organs

    International Nuclear Information System (INIS)

    Mejia, J.; Reis, M.A.; Miranda, A.C.C.; Batista, I.R.; Barboza, M.R.F.; Shih, M.C.; Fu, G.; Chen, C.T.; Meng, L.J.; Bressan, R.A.; Amaro, E. Jr

    2013-01-01

    The single photon emission microscope (SPEM) is an instrument developed to obtain high spatial resolution single photon emission computed tomography (SPECT) images of small structures inside the mouse brain. SPEM consists of two independent imaging devices, which combine a multipinhole collimator, a high-resolution, thallium-doped cesium iodide [CsI(Tl)] columnar scintillator, a demagnifying/intensifier tube, and an electron-multiplying charge-coupling device (CCD). Collimators have 300- and 450-µm diameter pinholes on tungsten slabs, in hexagonal arrays of 19 and 7 holes. Projection data are acquired in a photon-counting strategy, where CCD frames are stored at 50 frames per second, with a radius of rotation of 35 mm and magnification factor of one. The image reconstruction software tool is based on the maximum likelihood algorithm. Our aim was to evaluate the spatial resolution and sensitivity attainable with the seven-pinhole imaging device, together with the linearity for quantification on the tomographic images, and to test the instrument in obtaining tomographic images of different mouse organs. A spatial resolution better than 500 µm and a sensitivity of 21.6 counts·s -1 ·MBq -1 were reached, as well as a correlation coefficient between activity and intensity better than 0.99, when imaging 99m Tc sources. Images of the thyroid, heart, lungs, and bones of mice were registered using 99m Tc-labeled radiopharmaceuticals in times appropriate for routine preclinical experimentation of <1 h per projection data set. Detailed experimental protocols and images of the aforementioned organs are shown. We plan to extend the instrument's field of view to fix larger animals and to combine data from both detectors to reduce the acquisition time or applied activity

  6. Performance assessment of the single photon emission microscope: high spatial resolution SPECT imaging of small animal organs

    Energy Technology Data Exchange (ETDEWEB)

    Mejia, J. [Hospital Israelita Albert Einstein, Instituto do Cérebro, São Paulo, SP (Brazil); Reis, M.A. [Hospital Israelita Albert Einstein, Instituto do Cérebro, São Paulo, SP (Brazil); Laboratório Interdisciplinar de Neurociências Clínicas, Departamento de Psiquiatria, Universidade Federal de São Paulo, São Paulo, SP (Brazil); Miranda, A.C.C. [Hospital Israelita Albert Einstein, Instituto do Cérebro, São Paulo, SP (Brazil); Batista, I.R. [Hospital Israelita Albert Einstein, Instituto do Cérebro, São Paulo, SP (Brazil); Laboratório Interdisciplinar de Neurociências Clínicas, Departamento de Psiquiatria, Universidade Federal de São Paulo, São Paulo, SP (Brazil); Barboza, M.R.F.; Shih, M.C. [Hospital Israelita Albert Einstein, Instituto do Cérebro, São Paulo, SP (Brazil); Fu, G. [GE Global Research, Schenectady, NY (United States); Chen, C.T. [Department of Radiology, University of Chicago, Chicago, IL (United States); Meng, L.J. [Department of Nuclear, Plasma and Radiological Engineering, University of Illinois, Urbana-Champaign, IL (United States); Bressan, R.A. [Hospital Israelita Albert Einstein, Instituto do Cérebro, São Paulo, SP (Brazil); Laboratório Interdisciplinar de Neurociências Clínicas, Departamento de Psiquiatria, Universidade Federal de São Paulo, São Paulo, SP (Brazil); Amaro, E. Jr [Hospital Israelita Albert Einstein, Instituto do Cérebro, São Paulo, SP (Brazil)

    2013-11-06

    The single photon emission microscope (SPEM) is an instrument developed to obtain high spatial resolution single photon emission computed tomography (SPECT) images of small structures inside the mouse brain. SPEM consists of two independent imaging devices, which combine a multipinhole collimator, a high-resolution, thallium-doped cesium iodide [CsI(Tl)] columnar scintillator, a demagnifying/intensifier tube, and an electron-multiplying charge-coupling device (CCD). Collimators have 300- and 450-µm diameter pinholes on tungsten slabs, in hexagonal arrays of 19 and 7 holes. Projection data are acquired in a photon-counting strategy, where CCD frames are stored at 50 frames per second, with a radius of rotation of 35 mm and magnification factor of one. The image reconstruction software tool is based on the maximum likelihood algorithm. Our aim was to evaluate the spatial resolution and sensitivity attainable with the seven-pinhole imaging device, together with the linearity for quantification on the tomographic images, and to test the instrument in obtaining tomographic images of different mouse organs. A spatial resolution better than 500 µm and a sensitivity of 21.6 counts·s{sup -1}·MBq{sup -1} were reached, as well as a correlation coefficient between activity and intensity better than 0.99, when imaging {sup 99m}Tc sources. Images of the thyroid, heart, lungs, and bones of mice were registered using {sup 99m}Tc-labeled radiopharmaceuticals in times appropriate for routine preclinical experimentation of <1 h per projection data set. Detailed experimental protocols and images of the aforementioned organs are shown. We plan to extend the instrument's field of view to fix larger animals and to combine data from both detectors to reduce the acquisition time or applied activity.

  7. Fourier transforms and convolutions for the experimentalist

    CERN Document Server

    Jennison, RC

    1961-01-01

    Fourier Transforms and Convolutions for the Experimentalist provides the experimentalist with a guide to the principles and practical uses of the Fourier transformation. It aims to bridge the gap between the more abstract account of a purely mathematical approach and the rule of thumb calculation and intuition of the practical worker. The monograph springs from a lecture course which the author has given in recent years and for which he has drawn upon a number of sources, including a set of notes compiled by the late Dr. I. C. Browne from a series of lectures given by Mr. J . A. Ratcliffe of t

  8. Convolutional neural networks and face recognition task

    Science.gov (United States)

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

    2017-09-01

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

  9. Insulator recognition based on convolution neural network

    Directory of Open Access Journals (Sweden)

    Yang Yanli

    2017-01-01

    Full Text Available Insulator fault detection plays an important role in maintaining the safety of transmission lines. Insulator recognition is a prerequisite for its fault detection. An insulator recognition algorithm based on convolution neural network (CNN is proposed. A dataset is established to train the constructed CNN. The correct rate is 98.52% for 1220 training samples and the accuracy rate of testing is 89.04% on 1305 samples. The classification result of the CNN is further used to segment the insulator image. The test results show that the proposed method can realize the effective segmentation of insulators.

  10. Bacterial colony counting by Convolutional Neural Networks.

    Science.gov (United States)

    Ferrari, Alessandro; Lombardi, Stefano; Signoroni, Alberto

    2015-01-01

    Counting bacterial colonies on microbiological culture plates is a time-consuming, error-prone, nevertheless fundamental task in microbiology. Computer vision based approaches can increase the efficiency and the reliability of the process, but accurate counting is challenging, due to the high degree of variability of agglomerated colonies. In this paper, we propose a solution which adopts Convolutional Neural Networks (CNN) for counting the number of colonies contained in confluent agglomerates, that scored an overall accuracy of the 92.8% on a large challenging dataset. The proposed CNN-based technique for estimating the cardinality of colony aggregates outperforms traditional image processing approaches, becoming a promising approach to many related applications.

  11. Target recognition based on convolutional neural network

    Science.gov (United States)

    Wang, Liqiang; Wang, Xin; Xi, Fubiao; Dong, Jian

    2017-11-01

    One of the important part of object target recognition is the feature extraction, which can be classified into feature extraction and automatic feature extraction. The traditional neural network is one of the automatic feature extraction methods, while it causes high possibility of over-fitting due to the global connection. The deep learning algorithm used in this paper is a hierarchical automatic feature extraction method, trained with the layer-by-layer convolutional neural network (CNN), which can extract the features from lower layers to higher layers. The features are more discriminative and it is beneficial to the object target recognition.

  12. Spatially selecting a single cell for lysis using light-induced electric fields.

    Science.gov (United States)

    Witte, Christian; Kremer, Clemens; Chanasakulniyom, Mayuree; Reboud, Julien; Wilson, Rab; Cooper, Jonathan M; Neale, Steven L

    2014-08-13

    An optoelectronic tweezing (OET) device, within an integrated microfluidic channel, is used to precisely select single cells for lysis among dense populations. Cells to be lysed are exposed to higher electrical fields than their neighbours by illuminating a photoconductive film underneath them. Using beam spot sizes as low as 2.5 μm, 100% lysis efficiency is reached in <1 min allowing the targeted lysis of cells. © 2014 The Authors. Published by WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

  13. Influence of gold coating and interplate voltage on the performance of chevron micro-channel plates for temporally and spatially resolved single particle detection

    Science.gov (United States)

    Hoendervanger, A. L.; Clément, D.; Aspect, A.; Westbrook, C. I.; Dowek, D.; Picard, Y. J.; Boiron, D.

    2013-02-01

    We present a study of two different sets of Micro-Channel Plates used for time and space resolved single particle detection. We investigate the effects of the gold coating and that of introducing an interplate voltage between the spatially separated plates. We find that the gold coating increases the count rate of the detector and the pulse amplitude as previously reported for non-spatially resolved setups. The interplate voltage also increases count rates. In addition, we find that a non-zero interplate voltage improves the spatial accuracy in determining the arrival position of incoming single particles (by ˜20%) while the gold coating has a negative effect (by ˜30%).

  14. Comprehensive Identification and Spatial Mapping of Habenular Neuronal Types Using Single-Cell RNA-Seq.

    Science.gov (United States)

    Pandey, Shristi; Shekhar, Karthik; Regev, Aviv; Schier, Alexander F

    2018-04-02

    The identification of cell types and marker genes is critical for dissecting neural development and function, but the size and complexity of the brain has hindered the comprehensive discovery of cell types. We combined single-cell RNA-seq (scRNA-seq) with anatomical brain registration to create a comprehensive map of the zebrafish habenula, a conserved forebrain hub involved in pain processing and learning. Single-cell transcriptomes of ∼13,000 habenular cells with 4× cellular coverage identified 18 neuronal types and dozens of marker genes. Registration of marker genes onto a reference atlas created a resource for anatomical and functional studies and enabled the mapping of active neurons onto neuronal types following aversive stimuli. Strikingly, despite brain growth and functional maturation, cell types were retained between the larval and adult habenula. This study provides a gene expression atlas to dissect habenular development and function and offers a general framework for the comprehensive characterization of other brain regions. Copyright © 2018 Elsevier Ltd. All rights reserved.

  15. Convolutional networks for vehicle track segmentation

    Science.gov (United States)

    Quach, Tu-Thach

    2017-10-01

    Existing methods to detect vehicle tracks in coherent change detection images, a product of combining two synthetic aperture radar images taken at different times of the same scene, rely on simple and fast models to label track pixels. These models, however, are unable to capture natural track features, such as continuity and parallelism. More powerful but computationally expensive models can be used in offline settings. We present an approach that uses dilated convolutional networks consisting of a series of 3×3 convolutions to segment vehicle tracks. The design of our networks considers the fact that remote sensing applications tend to operate in low power and have limited training data. As a result, we aim for small and efficient networks that can be trained end-to-end to learn natural track features entirely from limited training data. We demonstrate that our six-layer network, trained on just 90 images, is computationally efficient and improves the F-score on a standard dataset to 0.992, up from 0.959 obtained by the current state-of-the-art method.

  16. Modified Stieltjes Transform and Generalized Convolutions of Probability Distributions

    Directory of Open Access Journals (Sweden)

    Lev B. Klebanov

    2018-01-01

    Full Text Available The classical Stieltjes transform is modified in such a way as to generalize both Stieltjes and Fourier transforms. This transform allows the introduction of new classes of commutative and non-commutative generalized convolutions. A particular case of such a convolution for degenerate distributions appears to be the Wigner semicircle distribution.

  17. Solid state detector for high spatial resolution coupled to a single event acquisition system for slow neutron detection

    Science.gov (United States)

    Casinini, F.; Petrillo, C.; Sacchetti, F.

    2012-05-01

    In the next years the slow neutron scattering community is waiting for a continuous improvement of the neutron detectors because of the development of the new and more intense neutron sources and to obtain a better performance of the neutron instrumentation to face the higher demands and new capabilities necessary for the novel experiments. In particular detectors having a faster response and a better shape of the time response must be produced, while new and more flexible acquisition systems must be introduced in order to collect in the proper way the information carried by the scattered neutrons. At present inside the neutron detector community the lack for detectors having a spatial resolution below 1 mm is evident. In the past it has been already demonstrated that a silicon microstrip detector coupled to a Gadolinium foil, used as neutron converter, provides a good performance neutron detector. In the present paper we present a 128 channel detector which has been designed for operation in the thermal neutron region with 0.55 mm spatial resolution, 100 ns time resolution and 25 ns time stamp accuracy. We present a new approach for the acquisition of the neutron arrival time, based on a single event storage by manipulating the detector digital output using a programmable acquisition system which takes advantage from high performance industrial standard hardware employing a FPGA and a real-time on board processor. We suggest the use of the single neutron event storing to make the time to energy transformation more efficient in the case of time of flight inelastic scattering, where the conversion from angle and time to momentum and energy is necessary.

  18. Spatial averaging of velocity measurements in wall-bounded turbulence: single hot-wires

    International Nuclear Information System (INIS)

    Philip, Jimmy; Hutchins, Nicholas; Monty, Jason P; Marusic, Ivan

    2013-01-01

    Recent advancements in velocity measurements to understand high Reynolds number (Re) wall turbulence have pushed the boundaries of sensor size required to resolve the smallest scales. We present here a framework for studying the effect of finite sensor size on velocity measurements, and scrutinize in detail the behaviour of single-wire hot-wires. Starting with a general linear filter, expressions for the filtered correlation, spectrum and the corresponding variance are derived. Considering the special case of a box-type filter and a simple model for the two-point correlation, theoretical results are developed, which are favourably compared with the numerical simulation of hot-wires based on the turbulent channel flow direct numerical simulation databases. The results clarify the reason why previous studies found the approximate shape of the spectra not resolved by hot-wires as Gaussian. The length scale based on the correlation over the sensor length is found to be the appropriate length scale for characterizing averaging due to finite sensor size. The efficacy of the linear box filter is established by comparing the numerical simulation of hot-wires with experiments conducted at matched sensor lengths and Re in a channel flow, at least for hot-wire lengths of less than 40 in viscous scaling. Finally, a model of the streamwise two-point correlation is presented, which is employed to estimate the filtering effect on the peak of the streamwise velocity variances for a range of Re, and the model results compare favourably with that obtained from measurements. Even though the theoretical results are compared here in the case of wall turbulence, they are suitable for hot-wire measurements in turbulent flows in general. (paper)

  19. Single-molecule tracking of small GTPase Rac1 uncovers spatial regulation of membrane translocation and mechanism for polarized signaling

    Science.gov (United States)

    Das, Sulagna; Yin, Taofei; Yang, Qingfen; Zhang, Jingqiao; Wu, Yi I.; Yu, Ji

    2015-01-01

    Polarized Rac1 signaling is a hallmark of many cellular functions, including cell adhesion, motility, and cell division. The two steps of Rac1 activation are its translocation to the plasma membrane and the exchange of nucleotide from GDP to GTP. It is, however, unclear whether these two processes are regulated independent of each other and what their respective roles are in polarization of Rac1 signaling. We designed a single-particle tracking (SPT) method to quantitatively analyze the kinetics of Rac1 membrane translocation in living cells. We found that the rate of Rac1 translocation was significantly elevated in protrusions during cell spreading on collagen. Furthermore, combining FRET sensor imaging with SPT measurements in the same cell, the recruitment of Rac1 was found to be polarized to an extent similar to that of the nucleotide exchange process. Statistical analysis of single-molecule trajectories and optogenetic manipulation of membrane lipids revealed that Rac1 membrane translocation precedes nucleotide exchange, and is governed primarily by interactions with phospholipids, particularly PI(3,4,5)P3, instead of protein factors. Overall, the study highlights the significance of membrane translocation in spatial Rac1 signaling, which is in addition to the traditional view focusing primarily on GEF distribution and exchange reaction. PMID:25561548

  20. Temporal and spatial gait parameters in children with Cri du Chat Syndrome under single and dual task conditions.

    Science.gov (United States)

    Abbruzzese, Laurel D; Salazar, Rachel; Aubuchon, Maddie; Rao, Ashwini K

    2016-10-01

    To describe temporal and spatial gait characteristics in individuals with Cri du Chat syndrome (CdCS) and to explore the effects of performing concurrent manual tasks while walking. The gait parameters of 14 participants with CdCS (mean age 10.3, range 3-20 years) and 14 age-matched controls (mean age 10.1, range 3-20 years) were collected using the GAITRite ® instrumented walkway. All participants first walked without any concurrent tasks and then performed 2 motor dual task walking conditions (pitcher and tray). Individuals with CdCS took more frequent, smaller steps than controls, but, on average, had a comparable gait speed. In addition, there was a significant task by group interaction. Participants decreased gait speed, decreased cadence, decreased step length, and increased% time in double limb support under dual task conditions compared to single task conditions. However, the age-matched controls altered their gait for both manual tasks, and the participants with CdCS only altered their gait for the tray task. Although individuals with CdCS ambulate with a comparable gait speed to age-matched controls under single task conditions, they did not significantly alter their gait when carrying a pitcher with a cup of water inside, like controls. It is not clear whether or not individuals with CdCS had difficulty attending to task demands or had difficulty modifying their gait. Copyright © 2016 Elsevier B.V. All rights reserved.

  1. Spatial filtering technique to image and measure two-dimensional near-forward scattering from single particles.

    Science.gov (United States)

    Berg, Matthew J; Hill, Steven C; Videen, Gorden; Gurton, Kristan P

    2010-04-26

    This work describes the design and use of an optical apparatus to measure the far-field elastic light-scattering pattern for a single particle over two angular-dimensions. A spatial filter composed of a mirror with a small through-hole is used to enable collection of the pattern uncommonly close to the forward direction; to within tenths of a degree. Minor modifications of the design allow for the simultaneous measurement of a particle's image along with its two-dimensional scattering pattern. Example measurements are presented involving single micrometer-sized glass spherical particles confined in an electrodynamic trap and a dilute suspension of polystyrene latex particles in water. A small forward-angle technique, called Guinier analysis, is used to determine a particle-size estimate directly from the measured pattern without a priori knowledge of the particle refractive index. Comparison of these size estimates to those obtained by fitting the measurements to Mie theory reveals relative errors low as 2%.

  2. A single early life seizure impairs short-term memory but does not alter spatial learning, recognition memory, or anxiety

    Science.gov (United States)

    Cornejo, Brandon J.; Mesches, Michael H.; Benke, Timothy A.

    2008-01-01

    The impact of a single seizure on cognition remains controversial. We hypothesized that a single early life seizure (sELS) on rat post-natal day (P) 7 would alter only hippocampal-dependent learning and memory in mature (P60) rats. The Morris Water Maze (MWM), Novel Object and Novel Place Recognition (NOR/NPR) tasks, and Contextual Fear Conditioning (CFC) were used to assess learning and memory associated with hippocampal/prefrontal cortex, perirhinal/hippocampal cortex, and amygdala function, respectively. The Elevated Plus Maze (EPM) and Open Field Test (OFT) were used to assess anxiety associated with the septum. We report that sELS impaired hippocampal-dependent short-term memory but not spatial learning or recall. sELS did not disrupt performance in the NOR/NPR. CFC performance suggested intact amydgala function. sELS did not change anxiety levels as measured by the EPM or OFT. Our data suggests that the long-term cognitive impacts of sELS are largely limited to the hippocampus/prefrontal cortex. PMID:18678283

  3. Relationships among transforms, convolutions, and first variations

    Directory of Open Access Journals (Sweden)

    Jeong Gyoo Kim

    1999-01-01

    Full Text Available In this paper, we establish several interesting relationships involving the Fourier-Feynman transform, the convolution product, and the first variation for functionals F on Wiener space of the form F(x=f(〈α1,x〉,…,〈αn,x〉,                                                      (* where 〈αj,x〉 denotes the Paley-Wiener-Zygmund stochastic integral ∫0Tαj(tdx(t.

  4. Robust smile detection using convolutional neural networks

    Science.gov (United States)

    Bianco, Simone; Celona, Luigi; Schettini, Raimondo

    2016-11-01

    We present a fully automated approach for smile detection. Faces are detected using a multiview face detector and aligned and scaled using automatically detected eye locations. Then, we use a convolutional neural network (CNN) to determine whether it is a smiling face or not. To this end, we investigate different shallow CNN architectures that can be trained even when the amount of learning data is limited. We evaluate our complete processing pipeline on the largest publicly available image database for smile detection in an uncontrolled scenario. We investigate the robustness of the method to different kinds of geometric transformations (rotation, translation, and scaling) due to imprecise face localization, and to several kinds of distortions (compression, noise, and blur). To the best of our knowledge, this is the first time that this type of investigation has been performed for smile detection. Experimental results show that our proposal outperforms state-of-the-art methods on both high- and low-quality images.

  5. Reconstruction of Micropattern Detector Signals using Convolutional Neural Networks

    Science.gov (United States)

    Flekova, L.; Schott, M.

    2017-10-01

    Micropattern gaseous detector (MPGD) technologies, such as GEMs or MicroMegas, are particularly suitable for precision tracking and triggering in high rate environments. Given their relatively low production costs, MPGDs are an exemplary candidate for the next generation of particle detectors. Having acknowledged these advantages, both the ATLAS and CMS collaborations at the LHC are exploiting these new technologies for their detector upgrade programs in the coming years. When MPGDs are utilized for triggering purposes, the measured signals need to be precisely reconstructed within less than 200 ns, which can be achieved by the usage of FPGAs. In this work, we present a novel approach to identify reconstructed signals, their timing and the corresponding spatial position on the detector. In particular, we study the effect of noise and dead readout strips on the reconstruction performance. Our approach leverages the potential of convolutional neural network (CNNs), which have recently manifested an outstanding performance in a range of modeling tasks. The proposed neural network architecture of our CNN is designed simply enough, so that it can be modeled directly by an FPGA and thus provide precise information on reconstructed signals already in trigger level.

  6. Mapping spatial patterns with morphological image processing

    Science.gov (United States)

    Peter Vogt; Kurt H. Riitters; Christine Estreguil; Jacek Kozak; Timothy G. Wade; James D. Wickham

    2006-01-01

    We use morphological image processing for classifying spatial patterns at the pixel level on binary land-cover maps. Land-cover pattern is classified as 'perforated,' 'edge,' 'patch,' and 'core' with higher spatial precision and thematic accuracy compared to a previous approach based on image convolution, while retaining the...

  7. Spatially Extended and High-Velocity Dispersion Molecular Component in Spiral Galaxies: Single-Dish Versus Interferometric Observations

    Science.gov (United States)

    Caldú-Primo, Anahi; Schruba, Andreas; Walter, Fabian; Leroy, Adam; Bolatto, Alberto D.; Vogel, Stuart

    2015-02-01

    Recent studies of the molecular medium in nearby galaxies have provided mounting evidence that the molecular gas can exist in two phases: one that is clumpy and organized as molecular clouds and another one that is more diffuse. This last component has a higher velocity dispersion than the clumpy one. In order to investigate these two molecular components further, we compare the fluxes and line widths of CO in NGC 4736 and NGC 5055, two nearby spiral galaxies for which high-quality interferometric as well as single-dish data sets are available. Our analysis leads to two main results: (1) employing three different methods, we determine the flux recovery of the interferometer as compared to the single-dish to be within a range of 35%-74% for NGC 4736 and 81%-92% for NGC 5055, and (2) when focusing on high (S/N ≥ 5) lines of sight (LOSs), the single-dish line widths are larger by ˜(40 ± 20)% than the ones derived from interferometric data, which is in agreement with stacking all LOSs. These results point to a molecular gas component that is distributed over spatial scales larger than 30″(˜1 kpc), and is therefore filtered out by the interferometer. The available observations do not allow us to distinguish between a truly diffuse gas morphology and a uniform distribution of small clouds that are separated by less than the synthesized beam size (˜3″ or ˜100 pc), as they would both be invisible for the interferometer. This high velocity dispersion component has a dispersion similar to what is found in the atomic medium, as traced through observations of the H i line.

  8. Spatially extended and high-velocity dispersion molecular component in spiral galaxies: Single-dish versus interferometric observations

    International Nuclear Information System (INIS)

    Caldú-Primo, Anahi; Walter, Fabian; Schruba, Andreas; Leroy, Adam; Bolatto, Alberto D.; Vogel, Stuart

    2015-01-01

    Recent studies of the molecular medium in nearby galaxies have provided mounting evidence that the molecular gas can exist in two phases: one that is clumpy and organized as molecular clouds and another one that is more diffuse. This last component has a higher velocity dispersion than the clumpy one. In order to investigate these two molecular components further, we compare the fluxes and line widths of CO in NGC 4736 and NGC 5055, two nearby spiral galaxies for which high-quality interferometric as well as single-dish data sets are available. Our analysis leads to two main results: (1) employing three different methods, we determine the flux recovery of the interferometer as compared to the single-dish to be within a range of 35%–74% for NGC 4736 and 81%–92% for NGC 5055, and (2) when focusing on high (S/N ≥ 5) lines of sight (LOSs), the single-dish line widths are larger by ∼(40 ± 20)% than the ones derived from interferometric data, which is in agreement with stacking all LOSs. These results point to a molecular gas component that is distributed over spatial scales larger than 30″(∼1 kpc), and is therefore filtered out by the interferometer. The available observations do not allow us to distinguish between a truly diffuse gas morphology and a uniform distribution of small clouds that are separated by less than the synthesized beam size (∼3″ or ∼100 pc), as they would both be invisible for the interferometer. This high velocity dispersion component has a dispersion similar to what is found in the atomic medium, as traced through observations of the H i line.

  9. Algorithm for extracting multiple object waves without Fourier transform from a single image recorded by spatial frequency-division multiplexing and its application to digital holography

    Science.gov (United States)

    Tahara, Tatsuki; Akamatsu, Takanori; Arai, Yasuhiko; Shimobaba, Tomoyoshi; Ito, Tomoyoshi; Kakue, Takashi

    2017-11-01

    We propose a novel algorithm that does not require any Fourier transform to extract multiple object waves in a single image recorded with spatial frequency-division multiplexing. Smoothing is utilized to extract the desired object-wave information from a spatially multiplexed image. Numerical and experimental results show its validity and applicability for image and Fresnel digital holography. Our investigations clarify the speeding up of both the object-wave extractions and multiple object-image reconstructions quantitatively.

  10. An Improved Convolutional Neural Network on Crowd Density Estimation

    Directory of Open Access Journals (Sweden)

    Pan Shao-Yun

    2016-01-01

    Full Text Available In this paper, a new method is proposed for crowd density estimation. An improved convolutional neural network is combined with traditional texture feature. The data calculated by the convolutional layer can be treated as a new kind of features.So more useful information of images can be extracted by different features.In the meantime, the size of image has little effect on the result of convolutional neural network. Experimental results indicate that our scheme has adequate performance to allow for its use in real world applications.

  11. Dual-Branch Deep Convolution Neural Network for Polarimetric SAR Image Classification

    Directory of Open Access Journals (Sweden)

    Fei Gao

    2017-04-01

    Full Text Available The deep convolution neural network (CNN, which has prominent advantages in feature learning, can learn and extract features from data automatically. Existing polarimetric synthetic aperture radar (PolSAR image classification methods based on the CNN only consider the polarization information of the image, instead of incorporating the image’s spatial information. In this paper, a novel method based on a dual-branch deep convolution neural network (Dual-CNN is proposed to realize the classification of PolSAR images. The proposed method is built on two deep CNNs: one is used to extract the polarization features from the 6-channel real matrix (6Ch which is derived from the complex coherency matrix. The other is utilized to extract the spatial features of a Pauli RGB (Red Green Blue image. These extracted features are first combined into a fully connected layer sharing the polarization and spatial property. Then, the Softmax classifier is employed to classify these features. The experiments are conducted on the Airborne Synthetic Aperture Radar (AIRSAR data of Flevoland and the results show that the classification accuracy on 14 types of land cover is up to 98.56%. Such results are promising in comparison with other state-of-the-art methods.

  12. A Parallel Strategy for Convolutional Neural Network Based on Heterogeneous Cluster for Mobile Information System

    Directory of Open Access Journals (Sweden)

    Jilin Zhang

    2017-01-01

    Full Text Available With the development of the mobile systems, we gain a lot of benefits and convenience by leveraging mobile devices; at the same time, the information gathered by smartphones, such as location and environment, is also valuable for business to provide more intelligent services for customers. More and more machine learning methods have been used in the field of mobile information systems to study user behavior and classify usage patterns, especially convolutional neural network. With the increasing of model training parameters and data scale, the traditional single machine training method cannot meet the requirements of time complexity in practical application scenarios. The current training framework often uses simple data parallel or model parallel method to speed up the training process, which is why heterogeneous computing resources have not been fully utilized. To solve these problems, our paper proposes a delay synchronization convolutional neural network parallel strategy, which leverages the heterogeneous system. The strategy is based on both synchronous parallel and asynchronous parallel approaches; the model training process can reduce the dependence on the heterogeneous architecture in the premise of ensuring the model convergence, so the convolution neural network framework is more adaptive to different heterogeneous system environments. The experimental results show that the proposed delay synchronization strategy can achieve at least three times the speedup compared to the traditional data parallelism.

  13. Single Spatial-Mode Room-Temperature-Operated 3.0 to 3.4 micrometer Diode Lasers

    Science.gov (United States)

    Frez, Clifford F.; Soibel, Alexander; Belenky, Gregory; Shterengas, Leon; Kipshidze, Gela

    2010-01-01

    Compact, highly efficient, 3.0 to 3.4 m light emitters are in demand for spectroscopic analysis and identification of chemical substances (including methane and formaldehyde), infrared countermeasures technologies, and development of advanced infrared scene projectors. The need for these light emitters can be currently addressed either by bulky solid-state light emitters with limited power conversion efficiency, or cooled Interband Cascade (IC) semiconductor lasers. Researchers here have developed a breakthrough approach to fabrication of diode mid-IR lasers that have several advantages over IC lasers used for the Mars 2009 mission. This breakthrough is due to a novel design utilizing the strain-engineered quantum-well (QW) active region and quinternary barriers, and due to optimization of device material composition and growth conditions (growth temperatures and rates). However, in their present form, these GaSb-based laser diodes cannot be directly used as a part of sensor systems. The device spectrum is too broad to perform spectroscopic analysis of gas species, and operating currents and voltages are too high. In the current work, the emitters were fabricated as narrow-ridge waveguide index-guided lasers rather than broad stripe-gain guided multimode Fabry-Perot (FP) lasers as was done previously. These narrow-ridge waveguide mid-IR lasers exhibit much lower power consumptions, and can operate in a single spatial mode that is necessary for demonstration of single-mode distributed feedback (DBF) devices for spectroscopic applications. These lasers will enable a new generation of compact, tunable diode laser spectrometers with lower power consumption, reduced complexity, and significantly reduced development costs. These lasers can be used for the detection of HCN, C2H2, methane, and ethane.

  14. 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...

  15. Classification of urine sediment based on convolution neural network

    Science.gov (United States)

    Pan, Jingjing; Jiang, Cunbo; Zhu, Tiantian

    2018-04-01

    By designing a new convolution neural network framework, this paper breaks the constraints of the original convolution neural network framework requiring large training samples and samples of the same size. Move and cropping the input images, generate the same size of the sub-graph. And then, the generated sub-graph uses the method of dropout, increasing the diversity of samples and preventing the fitting generation. Randomly select some proper subset in the sub-graphic set and ensure that the number of elements in the proper subset is same and the proper subset is not the same. The proper subsets are used as input layers for the convolution neural network. Through the convolution layer, the pooling, the full connection layer and output layer, we can obtained the classification loss rate of test set and training set. In the red blood cells, white blood cells, calcium oxalate crystallization classification experiment, the classification accuracy rate of 97% or more.

  16. Convolutive ICA for Spatio-Temporal Analysis of EEG

    DEFF Research Database (Denmark)

    Dyrholm, Mads; Makeig, Scott; Hansen, Lars Kai

    2007-01-01

    We present a new algorithm for maximum likelihood convolutive ICA (cICA) in which sources are unmixed using stable IIR filters determined implicitly by estimating an FIR filter model of the mixing process. By intro- ducing a FIR model for the sources we show how the order of the filters in the co......We present a new algorithm for maximum likelihood convolutive ICA (cICA) in which sources are unmixed using stable IIR filters determined implicitly by estimating an FIR filter model of the mixing process. By intro- ducing a FIR model for the sources we show how the order of the filters...... in the convolutive model can be correctly detected using Bayesian model selection. We demonstrate a framework for deconvolving an EEG ICA subspace. Initial results suggest that in some cases convolutive mixing may be a more realistic model for EEG signals than the instantaneous ICA model....

  17. ANNA: A Convolutional Neural Network Code for Spectroscopic Analysis

    Science.gov (United States)

    Lee-Brown, Donald; Anthony-Twarog, Barbara J.; Twarog, Bruce A.

    2018-01-01

    We present ANNA, a Python-based convolutional neural network code for the automated analysis of stellar spectra. ANNA provides a flexible framework that allows atmospheric parameters such as temperature and metallicity to be determined with accuracies comparable to those of established but less efficient techniques. ANNA performs its parameterization extremely quickly; typically several thousand spectra can be analyzed in less than a second. Additionally, the code incorporates features which greatly speed up the training process necessary for the neural network to measure spectra accurately, resulting in a tool that can easily be run on a single desktop or laptop computer. Thus, ANNA is useful in an era when spectrographs increasingly have the capability to collect dozens to hundreds of spectra each night. This talk will cover the basic features included in ANNA and demonstrate its performance in two use cases: an open cluster abundance analysis involving several hundred spectra, and a metal-rich field star study. Applicability of the code to large survey datasets will also be discussed.

  18. A convolution-superposition dose calculation engine for GPUs

    Energy Technology Data Exchange (ETDEWEB)

    Hissoiny, Sami; Ozell, Benoit; Despres, Philippe [Departement de genie informatique et genie logiciel, Ecole polytechnique de Montreal, 2500 Chemin de Polytechnique, Montreal, Quebec H3T 1J4 (Canada); Departement de radio-oncologie, CRCHUM-Centre hospitalier de l' Universite de Montreal, 1560 rue Sherbrooke Est, Montreal, Quebec H2L 4M1 (Canada)

    2010-03-15

    Purpose: Graphic processing units (GPUs) are increasingly used for scientific applications, where their parallel architecture and unprecedented computing power density can be exploited to accelerate calculations. In this paper, a new GPU implementation of a convolution/superposition (CS) algorithm is presented. Methods: This new GPU implementation has been designed from the ground-up to use the graphics card's strengths and to avoid its weaknesses. The CS GPU algorithm takes into account beam hardening, off-axis softening, kernel tilting, and relies heavily on raytracing through patient imaging data. Implementation details are reported as well as a multi-GPU solution. Results: An overall single-GPU acceleration factor of 908x was achieved when compared to a nonoptimized version of the CS algorithm implemented in PlanUNC in single threaded central processing unit (CPU) mode, resulting in approximatively 2.8 s per beam for a 3D dose computation on a 0.4 cm grid. A comparison to an established commercial system leads to an acceleration factor of approximately 29x or 0.58 versus 16.6 s per beam in single threaded mode. An acceleration factor of 46x has been obtained for the total energy released per mass (TERMA) calculation and a 943x acceleration factor for the CS calculation compared to PlanUNC. Dose distributions also have been obtained for a simple water-lung phantom to verify that the implementation gives accurate results. Conclusions: These results suggest that GPUs are an attractive solution for radiation therapy applications and that careful design, taking the GPU architecture into account, is critical in obtaining significant acceleration factors. These results potentially can have a significant impact on complex dose delivery techniques requiring intensive dose calculations such as intensity-modulated radiation therapy (IMRT) and arc therapy. They also are relevant for adaptive radiation therapy where dose results must be obtained rapidly.

  19. Autostereoscopic three-dimensional display by combining a single spatial light modulator and a zero-order nulled grating

    Science.gov (United States)

    Su, Yanfeng; Cai, Zhijian; Liu, Quan; Lu, Yifan; Guo, Peiliang; Shi, Lingyan; Wu, Jianhong

    2018-04-01

    In this paper, an autostereoscopic three-dimensional (3D) display system based on synthetic hologram reconstruction is proposed and implemented. The system uses a single phase-only spatial light modulator to load the synthetic hologram of the left and right stereo images, and the parallax angle between two reconstructed stereo images is enlarged by a grating to meet the split angle requirement of normal stereoscopic vision. To realize the crosstalk-free autostereoscopic 3D display with high light utilization efficiency, the groove parameters of the grating are specifically designed by the rigorous coupled-wave theory for suppressing the zero-order diffraction, and then the zero-order nulled grating is fabricated by the holographic lithography and the ion beam etching. Furthermore, the diffraction efficiency of the fabricated grating is measured under the illumination of a laser beam with a wavelength of 532 nm. Finally, the experimental verification system for the proposed autostereoscopic 3D display is presented. The experimental results prove that the proposed system is able to generate stereoscopic 3D images with good performances.

  20. Convolutional Codes with Maximum Column Sum Rank for Network Streaming

    OpenAIRE

    Mahmood, Rafid; Badr, Ahmed; Khisti, Ashish

    2015-01-01

    The column Hamming distance of a convolutional code determines the error correction capability when streaming over a class of packet erasure channels. We introduce a metric known as the column sum rank, that parallels column Hamming distance when streaming over a network with link failures. We prove rank analogues of several known column Hamming distance properties and introduce a new family of convolutional codes that maximize the column sum rank up to the code memory. Our construction invol...

  1. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

    OpenAIRE

    Radford, Alec; Metz, Luke; Chintala, Soumith

    2015-01-01

    In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between the success of CNNs for supervised learning and unsupervised learning. We introduce a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrate that they ar...

  2. On the Fresnel sine integral and the convolution

    Directory of Open Access Journals (Sweden)

    Adem Kılıçman

    2003-01-01

    Full Text Available The Fresnel sine integral S(x, the Fresnel cosine integral C(x, and the associated functions S+(x, S−(x, C+(x, and C−(x are defined as locally summable functions on the real line. Some convolutions and neutrix convolutions of the Fresnel sine integral and its associated functions with x+r, xr are evaluated.

  3. Radial Structure Scaffolds Convolution Patterns of Developing Cerebral Cortex

    Directory of Open Access Journals (Sweden)

    Mir Jalil Razavi

    2017-08-01

    Full Text Available Commonly-preserved radial convolution is a prominent characteristic of the mammalian cerebral cortex. Endeavors from multiple disciplines have been devoted for decades to explore the causes for this enigmatic structure. However, the underlying mechanisms that lead to consistent cortical convolution patterns still remain poorly understood. In this work, inspired by prior studies, we propose and evaluate a plausible theory that radial convolution during the early development of the brain is sculptured by radial structures consisting of radial glial cells (RGCs and maturing axons. Specifically, the regionally heterogeneous development and distribution of RGCs controlled by Trnp1 regulate the convex and concave convolution patterns (gyri and sulci in the radial direction, while the interplay of RGCs' effects on convolution and axons regulates the convex (gyral convolution patterns. This theory is assessed by observations and measurements in literature from multiple disciplines such as neurobiology, genetics, biomechanics, etc., at multiple scales to date. Particularly, this theory is further validated by multimodal imaging data analysis and computational simulations in this study. We offer a versatile and descriptive study model that can provide reasonable explanations of observations, experiments, and simulations of the characteristic mammalian cortical folding.

  4. Single-frequency operation of a broad-area laser diode by injection locking of a complex spatial mode via a double phase conjugate mirror

    NARCIS (Netherlands)

    van Voorst, P.D.; Offerhaus, Herman L.; Boller, Klaus J.

    2006-01-01

    We demonstrate what is believed to be the first phase-coherent locking of a high-power broad-area diode to a single-frequency master laser. We use photorefractive double phase conjugation to lock the diode in a selfoptimized complex spatial mode while the photorefractive crystal diffracts that

  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).

  6. 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.

  7. Multiscale Convolutional Neural Networks for Hand Detection

    Directory of Open Access Journals (Sweden)

    Shiyang Yan

    2017-01-01

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

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

    Directory of Open Access Journals (Sweden)

    Chunyong Ma

    2018-01-01

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

  9. Quantifying the brain's sheet structure with normalized convolution.

    Science.gov (United States)

    Tax, Chantal M W; Westin, Carl-Fredrik; Dela Haije, Tom; Fuster, Andrea; Viergever, Max A; Calabrese, Evan; Florack, Luc; Leemans, Alexander

    2017-07-01

    The hypothesis that brain pathways form 2D sheet-like structures layered in 3D as "pages of a book" has been a topic of debate in the recent literature. This hypothesis was mainly supported by a qualitative evaluation of "path neighborhoods" reconstructed with diffusion MRI (dMRI) tractography. Notwithstanding the potentially important implications of the sheet structure hypothesis for our understanding of brain structure and development, it is still considered controversial by many for lack of quantitative analysis. A means to quantify sheet structure is therefore necessary to reliably investigate its occurrence in the brain. Previous work has proposed the Lie bracket as a quantitative indicator of sheet structure, which could be computed by reconstructing path neighborhoods from the peak orientations of dMRI orientation density functions. Robust estimation of the Lie bracket, however, is challenging due to high noise levels and missing peak orientations. We propose a novel method to estimate the Lie bracket that does not involve the reconstruction of path neighborhoods with tractography. This method requires the computation of derivatives of the fiber peak orientations, for which we adopt an approach called normalized convolution. With simulations and experimental data we show that the new approach is more robust with respect to missing peaks and noise. We also demonstrate that the method is able to quantify to what extent sheet structure is supported for dMRI data of different species, acquired with different scanners, diffusion weightings, dMRI sampling schemes, and spatial resolutions. The proposed method can also be used with directional data derived from other techniques than dMRI, which will facilitate further validation of the existence of sheet structure. Copyright © 2017 Elsevier B.V. All rights reserved.

  10. Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images.

    Science.gov (United States)

    Pereira, Sergio; Pinto, Adriano; Alves, Victor; Silva, Carlos A

    2016-05-01

    Among brain tumors, gliomas are the most common and aggressive, leading to a very short life expectancy in their highest grade. Thus, treatment planning is a key stage to improve the quality of life of oncological patients. Magnetic resonance imaging (MRI) is a widely used imaging technique to assess these tumors, but the large amount of data produced by MRI prevents manual segmentation in a reasonable time, limiting the use of precise quantitative measurements in the clinical practice. So, automatic and reliable segmentation methods are required; however, the large spatial and structural variability among brain tumors make automatic segmentation a challenging problem. In this paper, we propose an automatic segmentation method based on Convolutional Neural Networks (CNN), exploring small 3 ×3 kernels. The use of small kernels allows designing a deeper architecture, besides having a positive effect against overfitting, given the fewer number of weights in the network. We also investigated the use of intensity normalization as a pre-processing step, which though not common in CNN-based segmentation methods, proved together with data augmentation to be very effective for brain tumor segmentation in MRI images. Our proposal was validated in the Brain Tumor Segmentation Challenge 2013 database (BRATS 2013), obtaining simultaneously the first position for the complete, core, and enhancing regions in Dice Similarity Coefficient metric (0.88, 0.83, 0.77) for the Challenge data set. Also, it obtained the overall first position by the online evaluation platform. We also participated in the on-site BRATS 2015 Challenge using the same model, obtaining the second place, with Dice Similarity Coefficient metric of 0.78, 0.65, and 0.75 for the complete, core, and enhancing regions, respectively.

  11. Lidar Cloud Detection with Fully Convolutional Networks

    Science.gov (United States)

    Cromwell, E.; Flynn, D.

    2017-12-01

    The vertical distribution of clouds from active remote sensing instrumentation is a widely used data product from global atmospheric measuring sites. The presence of clouds can be expressed as a binary cloud mask and is a primary input for climate modeling efforts and cloud formation studies. Current cloud detection algorithms producing these masks do not accurately identify the cloud boundaries and tend to oversample or over-represent the cloud. This translates as uncertainty for assessing the radiative impact of clouds and tracking changes in cloud climatologies. The Atmospheric Radiation Measurement (ARM) program has over 20 years of micro-pulse lidar (MPL) and High Spectral Resolution Lidar (HSRL) instrument data and companion automated cloud mask product at the mid-latitude Southern Great Plains (SGP) and the polar North Slope of Alaska (NSA) atmospheric observatory. Using this data, we train a fully convolutional network (FCN) with semi-supervised learning to segment lidar imagery into geometric time-height cloud locations for the SGP site and MPL instrument. We then use transfer learning to train a FCN for (1) the MPL instrument at the NSA site and (2) for the HSRL. In our semi-supervised approach, we pre-train the classification layers of the FCN with weakly labeled lidar data. Then, we facilitate end-to-end unsupervised pre-training and transition to fully supervised learning with ground truth labeled data. Our goal is to improve the cloud mask accuracy and precision for the MPL instrument to 95% and 80%, respectively, compared to the current cloud mask algorithms of 89% and 50%. For the transfer learning based FCN for the HSRL instrument, our goal is to achieve a cloud mask accuracy of 90% and a precision of 80%.

  12. Streambank erosion rates and loads within a single watershed: Bridging the gap between temporal and spatial scales

    Science.gov (United States)

    The importance of streambank erosion to watershed-scale sediment export is being increasingly recognized. However few studies have quantified bank erosion and watershed sediment flux at the basin scale across temporal and spatial scales. In this study we evaluated the spatial distribution, extent, a...

  13. Detecting atrial fibrillation by deep convolutional neural networks.

    Science.gov (United States)

    Xia, Yong; Wulan, Naren; Wang, Kuanquan; Zhang, Henggui

    2018-02-01

    Atrial fibrillation (AF) is the most common cardiac arrhythmia. The incidence of AF increases with age, causing high risks of stroke and increased morbidity and mortality. Efficient and accurate diagnosis of AF based on the ECG is valuable in clinical settings and remains challenging. In this paper, we proposed a novel method with high reliability and accuracy for AF detection via deep learning. The short-term Fourier transform (STFT) and stationary wavelet transform (SWT) were used to analyze ECG segments to obtain two-dimensional (2-D) matrix input suitable for deep convolutional neural networks. Then, two different deep convolutional neural network models corresponding to STFT output and SWT output were developed. Our new method did not require detection of P or R peaks, nor feature designs for classification, in contrast to existing algorithms. Finally, the performances of the two models were evaluated and compared with those of existing algorithms. Our proposed method demonstrated favorable performances on ECG segments as short as 5 s. The deep convolutional neural network using input generated by STFT, presented a sensitivity of 98.34%, specificity of 98.24% and accuracy of 98.29%. For the deep convolutional neural network using input generated by SWT, a sensitivity of 98.79%, specificity of 97.87% and accuracy of 98.63% was achieved. The proposed method using deep convolutional neural networks shows high sensitivity, specificity and accuracy, and, therefore, is a valuable tool for AF detection. Copyright © 2017 Elsevier Ltd. All rights reserved.

  14. Deep convolutional neural networks for annotating gene expression patterns in the mouse brain.

    Science.gov (United States)

    Zeng, Tao; Li, Rongjian; Mukkamala, Ravi; Ye, Jieping; Ji, Shuiwang

    2015-05-07

    Profiling gene expression in brain structures at various spatial and temporal scales is essential to understanding how genes regulate the development of brain structures. The Allen Developing Mouse Brain Atlas provides high-resolution 3-D in situ hybridization (ISH) gene expression patterns in multiple developing stages of the mouse brain. Currently, the ISH images are annotated with anatomical terms manually. In this paper, we propose a computational approach to annotate gene expression pattern images in the mouse brain at various structural levels over the course of development. We applied deep convolutional neural network that was trained on a large set of natural images to extract features from the ISH images of developing mouse brain. As a baseline representation, we applied invariant image feature descriptors to capture local statistics from ISH images and used the bag-of-words approach to build image-level representations. Both types of features from multiple ISH image sections of the entire brain were then combined to build 3-D, brain-wide gene expression representations. We employed regularized learning methods for discriminating gene expression patterns in different brain structures. Results show that our approach of using convolutional model as feature extractors achieved superior performance in annotating gene expression patterns at multiple levels of brain structures throughout four developing ages. Overall, we achieved average AUC of 0.894 ± 0.014, as compared with 0.820 ± 0.046 yielded by the bag-of-words approach. Deep convolutional neural network model trained on natural image sets and applied to gene expression pattern annotation tasks yielded superior performance, demonstrating its transfer learning property is applicable to such biological image sets.

  15. Aerial Images and Convolutional Neural Network for Cotton Bloom Detection

    Directory of Open Access Journals (Sweden)

    Rui Xu

    2018-02-01

    Full Text Available Monitoring flower development can provide useful information for production management, estimating yield and selecting specific genotypes of crops. The main goal of this study was to develop a methodology to detect and count cotton flowers, or blooms, using color images acquired by an unmanned aerial system. The aerial images were collected from two test fields in 4 days. A convolutional neural network (CNN was designed and trained to detect cotton blooms in raw images, and their 3D locations were calculated using the dense point cloud constructed from the aerial images with the structure from motion method. The quality of the dense point cloud was analyzed and plots with poor quality were excluded from data analysis. A constrained clustering algorithm was developed to register the same bloom detected from different images based on the 3D location of the bloom. The accuracy and incompleteness of the dense point cloud were analyzed because they affected the accuracy of the 3D location of the blooms and thus the accuracy of the bloom registration result. The constrained clustering algorithm was validated using simulated data, showing good efficiency and accuracy. The bloom count from the proposed method was comparable with the number counted manually with an error of −4 to 3 blooms for the field with a single plant per plot. However, more plots were underestimated in the field with multiple plants per plot due to hidden blooms that were not captured by the aerial images. The proposed methodology provides a high-throughput method to continuously monitor the flowering progress of cotton.

  16. Two dimensional convolute integers for machine vision and image recognition

    Science.gov (United States)

    Edwards, Thomas R.

    1988-01-01

    Machine vision and image recognition require sophisticated image processing prior to the application of Artificial Intelligence. Two Dimensional Convolute Integer Technology is an innovative mathematical approach for addressing machine vision and image recognition. This new technology generates a family of digital operators for addressing optical images and related two dimensional data sets. The operators are regression generated, integer valued, zero phase shifting, convoluting, frequency sensitive, two dimensional low pass, high pass and band pass filters that are mathematically equivalent to surface fitted partial derivatives. These operators are applied non-recursively either as classical convolutions (replacement point values), interstitial point generators (bandwidth broadening or resolution enhancement), or as missing value calculators (compensation for dead array element values). These operators show frequency sensitive feature selection scale invariant properties. Such tasks as boundary/edge enhancement and noise or small size pixel disturbance removal can readily be accomplished. For feature selection tight band pass operators are essential. Results from test cases are given.

  17. Hand gesture recognition based on convolutional neural networks

    Science.gov (United States)

    Hu, Yu-lu; Wang, Lian-ming

    2017-11-01

    Hand gesture has been considered a natural, intuitive and less intrusive way for Human-Computer Interaction (HCI). Although many algorithms for hand gesture recognition have been proposed in literature, robust algorithms have been pursued. A recognize algorithm based on the convolutional neural networks is proposed to recognize ten kinds of hand gestures, which include rotation and turnover samples acquired from different persons. When 6000 hand gesture images were used as training samples, and 1100 as testing samples, a 98% recognition rate was achieved with the convolutional neural networks, which is higher than that with some other frequently-used recognition algorithms.

  18. Very deep recurrent convolutional neural network for object recognition

    Science.gov (United States)

    Brahimi, Sourour; Ben Aoun, Najib; Ben Amar, Chokri

    2017-03-01

    In recent years, Computer vision has become a very active field. This field includes methods for processing, analyzing, and understanding images. The most challenging problems in computer vision are image classification and object recognition. This paper presents a new approach for object recognition task. This approach exploits the success of the Very Deep Convolutional Neural Network for object recognition. In fact, it improves the convolutional layers by adding recurrent connections. This proposed approach was evaluated on two object recognition benchmarks: Pascal VOC 2007 and CIFAR-10. The experimental results prove the efficiency of our method in comparison with the state of the art methods.

  19. Convolutional LSTM Networks for Subcellular Localization of Proteins

    DEFF Research Database (Denmark)

    Nielsen, Henrik; Sønderby, Søren Kaae; Sønderby, Casper Kaae

    2015-01-01

    Machine learning is widely used to analyze biological sequence data. Non-sequential models such as SVMs or feed-forward neural networks are often used although they have no natural way of handling sequences of varying length. Recurrent neural networks such as the long short term memory (LSTM) model...... convolutional filters and experiment with an attention mechanism which lets the LSTM focus on specific parts of the protein. Lastly we introduce new visualizations of both the convolutional filters and the attention mechanisms and show how they can be used to extract biologically relevant knowledge from...

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

    Directory of Open Access Journals (Sweden)

    Namatēvs Ivars

    2017-12-01

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

  1. Retrieval of Sentence Sequences for an Image Stream via Coherence Recurrent Convolutional Networks.

    Science.gov (United States)

    Park, Cesc Chunseong; Kim, Youngjin; Kim, Gunhee

    2018-04-01

    We propose an approach for retrieving a sequence of natural sentences for an image stream. Since general users often take a series of pictures on their experiences, much online visual information exists in the form of image streams, for which it would better take into consideration of the whole image stream to produce natural language descriptions. While almost all previous studies have dealt with the relation between a single image and a single natural sentence, our work extends both input and output dimension to a sequence of images and a sequence of sentences. For retrieving a coherent flow of multiple sentences for a photo stream, we propose a multimodal neural architecture called coherence recurrent convolutional network (CRCN), which consists of convolutional neural networks, bidirectional long short-term memory (LSTM) networks, and an entity-based local coherence model. Our approach directly learns from vast user-generated resource of blog posts as text-image parallel training data. We collect more than 22 K unique blog posts with 170 K associated images for the travel topics of NYC, Disneyland , Australia, and Hawaii. We demonstrate that our approach outperforms other state-of-the-art image captioning methods for text sequence generation, using both quantitative measures and user studies via Amazon Mechanical Turk.

  2. 3D convolutional neural network for automatic detection of lung nodules in chest CT

    Science.gov (United States)

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

    2017-03-01

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

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

    Science.gov (United States)

    Kang, Guixia; Liu, Kui; 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.

  4. View-invariant gait recognition method by three-dimensional convolutional neural network

    Science.gov (United States)

    Xing, Weiwei; Li, Ying; Zhang, Shunli

    2018-01-01

    Gait as an important biometric feature can identify a human at a long distance. View change is one of the most challenging factors for gait recognition. To address the cross view issues in gait recognition, we propose a view-invariant gait recognition method by three-dimensional (3-D) convolutional neural network. First, 3-D convolutional neural network (3DCNN) is introduced to learn view-invariant feature, which can capture the spatial information and temporal information simultaneously on normalized silhouette sequences. Second, a network training method based on cross-domain transfer learning is proposed to solve the problem of the limited gait training samples. We choose the C3D as the basic model, which is pretrained on the Sports-1M and then fine-tune C3D model to adapt gait recognition. In the recognition stage, we use the fine-tuned model to extract gait features and use Euclidean distance to measure the similarity of gait sequences. Sufficient experiments are carried out on the CASIA-B dataset and the experimental results demonstrate that our method outperforms many other methods.

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

    Science.gov (United States)

    Du, Chao-ben; Gao, She-sheng

    2018-01-01

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

  6. Adaptive Estimation of Active Contour Parameters Using Convolutional Neural Networks and Texture Analysis.

    Science.gov (United States)

    Hoogi, Assaf; Subramaniam, Arjun; Veerapaneni, Rishi; Rubin, Daniel L

    2017-03-01

    In this paper, we propose a generalization of the level set segmentation approach by supplying a novel method for adaptive estimation of active contour parameters. The presented segmentation method is fully automatic once the lesion has been detected. First, the location of the level set contour relative to the lesion is estimated using a convolutional neural network (CNN). The CNN has two convolutional layers for feature extraction, which lead into dense layers for classification. Second, the output CNN probabilities are then used to adaptively calculate the parameters of the active contour functional during the segmentation process. Finally, the adaptive window size surrounding each contour point is re-estimated by an iterative process that considers lesion size and spatial texture. We demonstrate the capabilities of our method on a dataset of 164 MRI and 112 CT images of liver lesions that includes low contrast and heterogeneous lesions as well as noisy images. To illustrate the strength of our method, we evaluated it against state of the art CNN-based and active contour techniques. For all cases, our method, as assessed by Dice similarity coefficients, performed significantly better than currently available methods. An average Dice improvement of 0.27 was found across the entire dataset over all comparisons. We also analyzed two challenging subsets of lesions and obtained a significant Dice improvement of 0.24 with our method (p <;0.001, Wilcoxon).

  7. Constructing fine-granularity functional brain network atlases via deep convolutional autoencoder.

    Science.gov (United States)

    Zhao, Yu; Dong, Qinglin; Chen, Hanbo; Iraji, Armin; Li, Yujie; Makkie, Milad; Kou, Zhifeng; Liu, Tianming

    2017-12-01

    State-of-the-art functional brain network reconstruction methods such as independent component analysis (ICA) or sparse coding of whole-brain fMRI data can effectively infer many thousands of volumetric brain network maps from a large number of human brains. However, due to the variability of individual brain networks and the large scale of such networks needed for statistically meaningful group-level analysis, it is still a challenging and open problem to derive group-wise common networks as network atlases. Inspired by the superior spatial pattern description ability of the deep convolutional neural networks (CNNs), a novel deep 3D convolutional autoencoder (CAE) network is designed here to extract spatial brain network features effectively, based on which an Apache Spark enabled computational framework is developed for fast clustering of larger number of network maps into fine-granularity atlases. To evaluate this framework, 10 resting state networks (RSNs) were manually labeled from the sparsely decomposed networks of Human Connectome Project (HCP) fMRI data and 5275 network training samples were obtained, in total. Then the deep CAE models are trained by these functional networks' spatial maps, and the learned features are used to refine the original 10 RSNs into 17 network atlases that possess fine-granularity functional network patterns. Interestingly, it turned out that some manually mislabeled outliers in training networks can be corrected by the deep CAE derived features. More importantly, fine granularities of networks can be identified and they reveal unique network patterns specific to different brain task states. By further applying this method to a dataset of mild traumatic brain injury study, it shows that the technique can effectively identify abnormal small networks in brain injury patients in comparison with controls. In general, our work presents a promising deep learning and big data analysis solution for modeling functional connectomes, with

  8. General Purpose Convolution Algorithm in S4 Classes by Means of FFT

    Directory of Open Access Journals (Sweden)

    Peter Ruckdeschel

    2014-08-01

    By means of object orientation this default algorithm is overloaded by more specific algorithms where possible, in particular where explicit convolution formulae are available. Our focus is on R package distr which implements this approach, overloading operator + for convolution; based on this convolution, we define a whole arithmetics of mathematical operations acting on distribution objects, comprising operators +, -, *, /, and ^.

  9. Efficient forward propagation of time-sequences in convolutional neural networks using Deep Shifting

    NARCIS (Netherlands)

    K.L. Groenland (Koen); S.M. Bohte (Sander)

    2016-01-01

    textabstractWhen a Convolutional Neural Network is used for on-the-fly evaluation of continuously updating time-sequences, many redundant convolution operations are performed. We propose the method of Deep Shifting, which remembers previously calculated results of convolution operations in order

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

    Science.gov (United States)

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

    2017-09-01

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

  11. The Urbanik generalized convolutions in the non-commutative ...

    Indian Academy of Sciences (India)

    preserves probability measures on the real line R. An alternative definition associates it to the sum of .... Barbara Jasiulis-Gołdyn and Anna Kula. DEFINITION 1. An associative and commutative binary operation ⊛ on the set P+ is called a generalized convolution on P. + ...... which are translation-invariant and weakly ...

  12. Robust Fusion of Irregularly Sampled Data Using Adaptive Normalized Convolution

    NARCIS (Netherlands)

    Pham, T.Q.; Van Vliet, L.J.; Schutte, K.

    2006-01-01

    We present a novel algorithm for image fusion from irregularly sampled data. The method is based on the framework of normalized convolution (NC), in which the local signal is approximated through a projection onto a subspace. The use of polynomial basis functions in this paper makes NC equivalent to

  13. Diffraction and Dirchlet problem for parameter-elliptic convolution ...

    African Journals Online (AJOL)

    In this paper we evaluate the difference between the inverse operators of a Dirichlet problem and of a diffraction problem for parameter-elliptic convolution operators with constant symbols. We prove that the inverse operator of a Dirichlet problem can be obtained as a limit case of such a diffraction problem. Quaestiones ...

  14. Weak Poincar\\'e Inequality for Convolution Probability Measures

    OpenAIRE

    Cheng, Li-Juan; Zhang, Shao-Qin

    2014-01-01

    By using Lyapunov conditions, weak Poincar\\'e inequalities are established for some probability measures on a manifold $(M,g)$. These results are further applied to the convolution of two probability measures on $\\R^d$. Along with explicit results we study concrete examples.

  15. Review of the convolution algorithm for evaluating service integrated systems

    DEFF Research Database (Denmark)

    Iversen, Villy Bæk

    1997-01-01

    In this paper we give a review of the applicability of the convolution algorithm. By this we are able to evaluate communication networks end--to--end with e.g. BPP multi-ratetraffic models insensitive to the holding time distribution. Rearrangement, minimum allocation, and maximum allocation...

  16. Multipliers of Ap((0 ,((0 ,((0,∞)) with order convolution

    Indian Academy of Sciences (India)

    R. Narasimhan (Krishtel eMaging) 1461 1996 Oct 15 13:05:22

    I under the order convolution product denoted by ∗ and total variation norm. Then the. Banach space L1(I) of all measures in M(I) which are absolutely continuous with respect to the Lebesgue measure on I becomes a commutative semisimple Banach algebra in the inherited product ∗. More specifically, for f, g ∈ L1(I),.

  17. Infimal convolution in Efimov-Stečkin Banach spaces

    Czech Academy of Sciences Publication Activity Database

    Fabian, Marián

    2008-01-01

    Roč. 339, č. 1 (2008), s. 735-739 ISSN 0022-247X R&D Projects: GA AV ČR(CZ) IAA100190610 Institutional research plan: CEZ:AV0Z10190503 Keywords : reflexive Banach space * Kadec-Klee norm * infimal convolution Subject RIV: BA - General Mathematics Impact factor: 1.046, year: 2008

  18. CICAAR - Convolutive ICA with an Auto-Regressive Inverse Model

    DEFF Research Database (Denmark)

    Dyrholm, Mads; Hansen, Lars Kai

    2004-01-01

    We invoke an auto-regressive IIR inverse model for convolutive ICA and derive expressions for the likelihood and its gradient. We argue that optimization will give a stable inverse. When there are more sensors than sources the mixing model parameters are estimated in a second step by least squares...

  19. Symbol Stream Combining in a Convolutionally Coded System

    Science.gov (United States)

    Mceliece, R. J.; Pollara, F.; Swanson, L.

    1985-01-01

    Symbol stream combining has been proposed as a method for arraying signals received at different antennas. If convolutional coding and Viterbi decoding are used, it is shown that a Viterbi decoder based on the proposed weighted sum of symbol streams yields maximum likelihood decisions.

  20. A combination of differential equations and convolution in ...

    Indian Academy of Sciences (India)

    Keywords. Dynamical model; likelihood; convolution; HIV. Abstract. Nonlinear dynamical method of projecting the transmission of an epidemic is accurate if the input parameters and initial value variables are reliable. Here, such a model is proposed for predicting an epidemic. A method to supplement two variables and two ...

  1. Unsupervised pre-training for fully convolutional neural networks

    NARCIS (Netherlands)

    Wiehman, Stiaan; Kroon, Steve; Villiers, De Hendrik

    2017-01-01

    Unsupervised pre-Training of neural networks has been shown to act as a regularization technique, improving performance and reducing model variance. Recently, fully convolutional networks (FCNs) have shown state-of-The-Art results on various semantic segmentation tasks. Unfortunately, there is no

  2. Deep convolutional neural networks for detection of rail surface defects

    NARCIS (Netherlands)

    Faghih Roohi, S.; Hajizadeh, S.; Nunez Vicencio, Alfredo; Babuska, R.; De Schutter, B.H.K.; Estevez, Pablo A.; Angelov, Plamen P.; Del Moral Hernandez, Emilio

    2016-01-01

    In this paper, we propose a deep convolutional neural network solution to the analysis of image data for the detection of rail surface defects. The images are obtained from many hours of automated video recordings. This huge amount of data makes it impossible to manually inspect the images and

  3. Blind Identification of Convolutive MIMO Systems with 3 Sources and 2 Sensors

    Directory of Open Access Journals (Sweden)

    De Lathauwer Lieven

    2002-01-01

    Full Text Available We address the problem of blind identification of a convolutive Multiple-Input Multiple-Output (MIMO system with more inputs than outputs, and in particular, the 3-input 2-output case. We assume that the inputs are temporally white, non-Gaussian distributed, and spatially independent. Solutions for the scalar MIMO case, within scaling and permutation ambiguities, have been proposed in the past, based on the canonical decomposition of tensors constructed from higher-order cross-cumulants of the system output. In this paper, we look at the problem in the frequency domain, where, for each frequency we construct a number of tensors based on cross-polyspectra of the output. These tensors lead to the system frequency response within frequency dependent scaling and permutation ambiguities. We propose ways to resolve these ambiguities, and show that it is possible to obtain the system response within a scalar and a linear phase.

  4. Constrained Convolutional Sparse Coding for Parametric Based Reconstruction of Line Drawings

    KAUST Repository

    Shaheen, Sara

    2017-12-25

    Convolutional sparse coding (CSC) plays an essential role in many computer vision applications ranging from image compression to deep learning. In this work, we spot the light on a new application where CSC can effectively serve, namely line drawing analysis. The process of drawing a line drawing can be approximated as the sparse spatial localization of a number of typical basic strokes, which in turn can be cast as a non-standard CSC model that considers the line drawing formation process from parametric curves. These curves are learned to optimize the fit between the model and a specific set of line drawings. Parametric representation of sketches is vital in enabling automatic sketch analysis, synthesis and manipulation. A couple of sketch manipulation examples are demonstrated in this work. Consequently, our novel method is expected to provide a reliable and automatic method for parametric sketch description. Through experiments, we empirically validate the convergence of our method to a feasible solution.

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

    Science.gov (United States)

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

    2016-10-01

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

  6. Limitations of a convolution method for modeling geometric uncertainties in radiation therapy: the radiobiological dose-per-fraction effect

    International Nuclear Information System (INIS)

    Song, William; Battista, Jerry; Van Dyk, Jake

    2004-01-01

    The convolution method can be used to model the effect of random geometric uncertainties into planned dose distributions used in radiation treatment planning. This is effectively done by linearly adding infinitesimally small doses, each with a particular geometric offset, over an assumed infinite number of fractions. However, this process inherently ignores the radiobiological dose-per-fraction effect since only the summed physical dose distribution is generated. The resultant potential error on predicted radiobiological outcome [quantified in this work with tumor control probability (TCP), equivalent uniform dose (EUD), normal tissue complication probability (NTCP), and generalized equivalent uniform dose (gEUD)] has yet to be thoroughly quantified. In this work, the results of a Monte Carlo simulation of geometric displacements are compared to those of the convolution method for random geometric uncertainties of 0, 1, 2, 3, 4, and 5 mm (standard deviation). The α/β CTV ratios of 0.8, 1.5, 3, 5, and 10 Gy are used to represent the range of radiation responses for different tumors, whereas a single α/β OAR ratio of 3 Gy is used to represent all the organs at risk (OAR). The analysis is performed on a four-field prostate treatment plan of 18 MV x rays. The fraction numbers are varied from 1-50, with isoeffective adjustments of the corresponding dose-per-fractions to maintain a constant tumor control, using the linear-quadratic cell survival model. The average differences in TCP and EUD of the target, and in NTCP and gEUD of the OAR calculated from the convolution and Monte Carlo methods reduced asymptotically as the total fraction number increased, with the differences reaching negligible levels beyond the treatment fraction number of ≥20. The convolution method generally overestimates the radiobiological indices, as compared to the Monte Carlo method, for the target volume, and underestimates those for the OAR. These effects are interconnected and attributed

  7. An Implementation of Error Minimization Data Transmission in OFDM using Modified Convolutional Code

    Directory of Open Access Journals (Sweden)

    Hendy Briantoro

    2016-04-01

    Full Text Available This paper presents about error minimization in OFDM system. In conventional system, usually using channel coding such as BCH Code or Convolutional Code. But, performance BCH Code or Convolutional Code is not good in implementation of OFDM System. Error bits of OFDM system without channel coding is 5.77%. Then, we used convolutional code with code rate 1/2, it can reduce error bitsonly up to 3.85%. So, we proposed OFDM system with Modified Convolutional Code. In this implementation, we used Software Define Radio (SDR, namely Universal Software Radio Peripheral (USRP NI 2920 as the transmitter and receiver. The result of OFDM system using Modified Convolutional Code with code rate is able recover all character received so can decrease until 0% error bit. Increasing performance of Modified Convolutional Code is about 1 dB in BER of 10-4 from BCH Code and Convolutional Code. So, performance of Modified Convolutional better than BCH Code or Convolutional Code. Keywords: OFDM, BCH Code, Convolutional Code, Modified Convolutional Code, SDR, USRP

  8. DeepCotton: in-field cotton segmentation using deep fully convolutional network

    Science.gov (United States)

    Li, Yanan; Cao, Zhiguo; Xiao, Yang; Cremers, Armin B.

    2017-09-01

    Automatic ground-based in-field cotton (IFC) segmentation is a challenging task in precision agriculture, which has not been well addressed. Nearly all the existing methods rely on hand-crafted features. Their limited discriminative power results in unsatisfactory performance. To address this, a coarse-to-fine cotton segmentation method termed "DeepCotton" is proposed. It contains two modules, fully convolutional network (FCN) stream and interference region removal stream. First, FCN is employed to predict initially coarse map in an end-to-end manner. The convolutional networks involved in FCN guarantee powerful feature description capability, simultaneously, the regression analysis ability of neural network assures segmentation accuracy. To our knowledge, we are the first to introduce deep learning to IFC segmentation. Second, our proposed "UP" algorithm composed of unary brightness transformation and pairwise region comparison is used for obtaining interference map, which is executed to refine the coarse map. The experiments on constructed IFC dataset demonstrate that our method outperforms other state-of-the-art approaches, either in different common scenarios or single/multiple plants. More remarkable, the "UP" algorithm greatly improves the property of the coarse result, with the average amplifications of 2.6%, 2.4% on accuracy and 8.1%, 5.5% on intersection over union for common scenarios and multiple plants, separately.

  9. Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks.

    Science.gov (United States)

    Maninis, Kevis-Kokitsi; Pont-Tuset, Jordi; Arbelaez, Pablo; Van Gool, Luc

    2018-04-01

    We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs). COB is computationally efficient, because it requires a single CNN forward pass for multi-scale contour detection and it uses a novel sparse boundary representation for hierarchical segmentation; it gives a significant leap in performance over the state-of-the-art, and it generalizes very well to unseen categories and datasets. Particularly, we show that learning to estimate not only contour strength but also orientation provides more accurate results. We perform extensive experiments for low-level applications on BSDS, PASCAL Context, PASCAL Segmentation, and NYUD to evaluate boundary detection performance, showing that COB provides state-of-the-art contours and region hierarchies in all datasets. We also evaluate COB on high-level tasks when coupled with multiple pipelines for object proposals, semantic contours, semantic segmentation, and object detection on MS-COCO, SBD, and PASCAL; showing that COB also improves the results for all tasks.

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

    Science.gov (United States)

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

    2017-08-01

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

  11. Multineuron spike train analysis with R-convolution linear combination kernel.

    Science.gov (United States)

    Tezuka, Taro

    2018-06-01

    A spike train kernel provides an effective way of decoding information represented by a spike train. Some spike train kernels have been extended to multineuron spike trains, which are simultaneously recorded spike trains obtained from multiple neurons. However, most of these multineuron extensions were carried out in a kernel-specific manner. In this paper, a general framework is proposed for extending any single-neuron spike train kernel to multineuron spike trains, based on the R-convolution kernel. Special subclasses of the proposed R-convolution linear combination kernel are explored. These subclasses have a smaller number of parameters and make optimization tractable when the size of data is limited. The proposed kernel was evaluated using Gaussian process regression for multineuron spike trains recorded from an animal brain. It was compared with the sum kernel and the population Spikernel, which are existing ways of decoding multineuron spike trains using kernels. The results showed that the proposed approach performs better than these kernels and also other commonly used neural decoding methods. Copyright © 2018 Elsevier Ltd. All rights reserved.

  12. Deep convolutional neural networks as strong gravitational lens detectors

    Science.gov (United States)

    Schaefer, C.; Geiger, M.; Kuntzer, T.; Kneib, J.-P.

    2018-03-01

    Context. Future large-scale surveys with high-resolution imaging will provide us with approximately 105 new strong galaxy-scale lenses. These strong-lensing systems will be contained in large data amounts, however, which are beyond the capacity of human experts to visually classify in an unbiased way. Aim. We present a new strong gravitational lens finder based on convolutional neural networks (CNNs). The method was applied to the strong-lensing challenge organized by the Bologna Lens Factory. It achieved first and third place, respectively, on the space-based data set and the ground-based data set. The goal was to find a fully automated lens finder for ground-based and space-based surveys that minimizes human inspection. Methods: We compared the results of our CNN architecture and three new variations ("invariant" "views" and "residual") on the simulated data of the challenge. Each method was trained separately five times on 17 000 simulated images, cross-validated using 3000 images, and then applied to a test set with 100 000 images. We used two different metrics for evaluation, the area under the receiver operating characteristic curve (AUC) score, and the recall with no false positive (Recall0FP). Results: For ground-based data, our best method achieved an AUC score of 0.977 and a Recall0FP of 0.50. For space-based data, our best method achieved an AUC score of 0.940 and a Recall0FP of 0.32. Adding dihedral invariance to the CNN architecture diminished the overall score on space-based data, but achieved a higher no-contamination recall. We found that using committees of five CNNs produced the best recall at zero contamination and consistently scored better AUC than a single CNN. Conclusions: We found that for every variation of our CNN lensfinder, we achieved AUC scores close to 1 within 6%. A deeper network did not outperform simpler CNN models either. This indicates that more complex networks are not needed to model the simulated lenses. To verify this, more

  13. A single-spatial-mode semiconductor laser based on InAs/InGaAs quantum dots with a diffraction filter of optical modes

    International Nuclear Information System (INIS)

    Gordeev, N. Yu.; Novikov, I. I.; Kuznetsov, A. M.; Shernyakov, Yu. M.; Maximov, M. V.; Zhukov, A. E.; Chunareva, A. V.; Payusov, A. S.; Livshits, D. A.; Kovsh, A. R.

    2010-01-01

    The concept of a diffraction optical filter is used for prevention of high-order mode oscillation in a design of stripe laser diodes with an active region based on InAs/InGaAs quantum dots emitting in the 1.3-μm wavelength range grown on GaAs substrates. Incorporation of such a filter made it possible to increase the width of the stripe and obtain an output power as high as 700 mW with retention of a single-spatial-mode character of lasing.

  14. A rehabilitation program based on music practice for patients with unilateral spatial neglect: a single-case study.

    Science.gov (United States)

    Guilbert, Alma; Clément, Sylvain; Moroni, Christine

    2017-02-01

    Two major limitations of unilateral spatial neglect (USN) rehabilitation methods are actually reported: a lack of long-term efficiency and a lack of generalization to daily life. The aim of our case study was to underline how a multisensory method-music practice-could avoid these limitations. Mrs BV suffered from a chronic severe USN. She had rehabilitation sessions of music practice over 8 weeks. An improvement of her USN was found on paper-pencil tests but also in daily activities. Benefits subsisted 4 months after rehabilitation. Music practice seemed to avoid the major limitations of USN rehabilitations and could represent a promising tool.

  15. Infimal Convolution Regularisation Functionals of BV and Lp Spaces

    KAUST Repository

    Burger, Martin

    2016-02-03

    We study a general class of infimal convolution type regularisation functionals suitable for applications in image processing. These functionals incorporate a combination of the total variation seminorm and Lp norms. A unified well-posedness analysis is presented and a detailed study of the one-dimensional model is performed, by computing exact solutions for the corresponding denoising problem and the case p=2. Furthermore, the dependency of the regularisation properties of this infimal convolution approach to the choice of p is studied. It turns out that in the case p=2 this regulariser is equivalent to the Huber-type variant of total variation regularisation. We provide numerical examples for image decomposition as well as for image denoising. We show that our model is capable of eliminating the staircasing effect, a well-known disadvantage of total variation regularisation. Moreover as p increases we obtain almost piecewise affine reconstructions, leading also to a better preservation of hat-like structures.

  16. Hamiltonian Cycle Enumeration via Fermion-Zeon Convolution

    Science.gov (United States)

    Staples, G. Stacey

    2017-12-01

    Beginning with a simple graph having finite vertex set V, operators are induced on fermion and zeon algebras by the action of the graph's adjacency matrix and combinatorial Laplacian on the vector space spanned by the graph's vertices. When the graph is simple (undirected with no loops or multiple edges), the matrices are symmetric and the induced operators are self-adjoint. The goal of the current paper is to recover a number of known graph-theoretic results from quantum observables constructed as linear operators on fermion and zeon Fock spaces. By considering an "indeterminate" fermion/zeon Fock space, a fermion-zeon convolution operator is defined whose trace recovers the number of Hamiltonian cycles in the graph. This convolution operator is a quantum observable whose expectation reveals the number of Hamiltonian cycles in the graph.

  17. Combining morphometric features and convolutional networks fusion for glaucoma diagnosis

    Science.gov (United States)

    Perdomo, Oscar; Arevalo, John; González, Fabio A.

    2017-11-01

    Glaucoma is an eye condition that leads to loss of vision and blindness. Ophthalmoscopy exam evaluates the shape, color and proportion between the optic disc and physiologic cup, but the lack of agreement among experts is still the main diagnosis problem. The application of deep convolutional neural networks combined with automatic extraction of features such as: the cup-to-disc distance in the four quadrants, the perimeter, area, eccentricity, the major radio, the minor radio in optic disc and cup, in addition to all the ratios among the previous parameters may help with a better automatic grading of glaucoma. This paper presents a strategy to merge morphological features and deep convolutional neural networks as a novel methodology to support the glaucoma diagnosis in eye fundus images.

  18. 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.

  19. Self-Taught convolutional neural networks for short text clustering.

    Science.gov (United States)

    Xu, Jiaming; Xu, Bo; Wang, Peng; Zheng, Suncong; Tian, Guanhua; Zhao, Jun; Xu, Bo

    2017-04-01

    Short text clustering is a challenging problem due to its sparseness of text representation. Here we propose a flexible Self-Taught Convolutional neural network framework for Short Text Clustering (dubbed STC 2 ), which can flexibly and successfully incorporate more useful semantic features and learn non-biased deep text representation in an unsupervised manner. In our framework, the original raw text features are firstly embedded into compact binary codes by using one existing unsupervised dimensionality reduction method. Then, word embeddings are explored and fed into convolutional neural networks to learn deep feature representations, meanwhile the output units are used to fit the pre-trained binary codes in the training process. Finally, we get the optimal clusters by employing K-means to cluster the learned representations. Extensive experimental results demonstrate that the proposed framework is effective, flexible and outperform several popular clustering methods when tested on three public short text datasets. Copyright © 2017 Elsevier Ltd. All rights reserved.

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

    Directory of Open Access Journals (Sweden)

    Hui-Zhen Zhao

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

  1. Spatial filtering nearly eliminates the side-lobes in single- and multi-photon 4pi-type-C super-resolution fluorescence microscopy

    Science.gov (United States)

    Kavya, M.; Regmi, Raju; Mondal, Partha P.

    2013-09-01

    Super-resolution microscopy has tremendously progressed our understanding of cellular biophysics and biochemistry. Specifically, 4pi fluorescence microscopy technique stands out because of its axial super-resolution capability. All types of 4pi-microscopy techniques work well in conjugation with deconvolution techniques to get rid of artifacts due to side-lobes. In this regard, we propose a technique based on spatial filter in a 4pi-type-C confocal setup to get rid of these artifacts. Using a special spatial filter, we have reduced the depth-of-focus. Interference of two similar depth-of-focus beams in a 4π geometry result in substantial reduction of side-lobes. Studies show a reduction of side-lobes by 46% and 76% for single and two photon variant compared to 4pi - type - C confocal system. This is incredible considering the resolving capability of the existing 4pi - type - C confocal microscopy. Moreover, the main lobe is found to be 150 nm for the proposed spatial filtering technique as compared to 690 nm of the state-of-art confocal system. Reconstruction of experimentally obtained 2PE - 4pi data of green fluorescent protein (GFP)-tagged mitocondrial network shows near elimination of artifacts arising out of side-lobes. Proposed technique may find interesting application in fluorescence microscopy, nano-lithography, and cell biology.

  2. Single fluoxetine treatment before but not after stress prevents stress-induced hippocampal long-term depression and spatial memory retrieval impairment in rats

    Science.gov (United States)

    Han, Huili; Dai, Chunfang; Dong, Zhifang

    2015-01-01

    A growing body of evidence has shown that chronic treatment with fluoxetine, a widely prescribed medication for treatment of depression, can affect synaptic plasticity in the adult central nervous system. However, it is not well understood whether acute fluoxetine influences synaptic plasticity, especially on hippocampal CA1 long-term depression (LTD), and if so, whether it subsequently impacts hippocampal-dependent spatial memory. Here, we reported that LTD facilitated by elevated-platform stress in hippocampal slices was completely prevented by fluoxetine administration (10 mg/kg, i.p.) 30 min before stress. The LTD was not, however, significantly inhibited by fluoxetine administration immediately after stress. Similarly, fluoxetine incubation (10 μM) during electrophysiological recordings also displayed no influence on the stress-facilitated LTD. In addition, behavioral results showed that a single fluoxetine treatment 30 min before but not after acute stress fully reversed the impairment of spatial memory retrieval in the Morris water maze paradigm. Taken together, these results suggest that acute fluoxetine treatment only before, but not after stress, can prevent hippocampal CA1 LTD and spatial memory retrieval impairment caused by behavioral stress in adult animals. PMID:26218751

  3. Spatial distribution of surface EMG on trapezius and lumbar muscles of violin and cello players in single note playing.

    Science.gov (United States)

    Afsharipour, Babak; Petracca, Francesco; Gasparini, Mauro; Merletti, Roberto

    2016-12-01

    Musicians activate their muscles in different patterns, depending on their posture, the instrument being played, and their experience level. Bipolar surface electrodes have been used in the past to monitor such activity, but this method is highly sensitive to the location of the electrode pair. In this work, the spatial distribution of surface EMG (sEMG) of the right trapezius and right and left erector spinae muscles were studied in 16 violin players and 11 cello players. Musicians played their instrument one string at a time in sitting position with/without backrest support. A 64 sEMG electrode (16×4) grid, 10mm inter-electrode distance (IED), was placed over the middle and lower trapezius (MT and LT) of the bowing arm. Two 16×2 electrode grids (IED=10mm) were placed on the left and right erector spinae muscles. Subjects played each of the four strings of the instrument either in large (1bow/s) or detaché tip/tail (8bows/s) bowing in two sessions (two days). In each of two days, measurements were repeated after half an hour of exercise to see the effect of exercise on the muscle activity and signal stability. A "muscle activity index" (MAI) was defined as the spatial average of the segmented active region of the RMS map. Spatial maps were automatically segmented using the watershed algorithm and thresholding. Results showed that, for violin players, sliding the bow upward from the tip toward the tail results in a higher MAI for the trapezius muscle than a downward bow. On the contrary, in cello players, higher MAI is produced in the tail to tip movement. For both instruments, an increasing MAI in the trapezius was observed as the string position became increasingly lateral, from string 1 (most medial) toward string 4 (most lateral). Half an hour of performance did not cause significant differences between the signal quality and the MAI values measured before and after the exercise. The MAI of the left and right erector spinae was smaller in the case of

  4. Optimization of Convolutional Neural Network using Microcanonical Annealing Algorithm

    OpenAIRE

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

    2016-01-01

    Convolutional neural network (CNN) is one of the most prominent architectures and algorithm in Deep Learning. It shows a remarkable improvement in the recognition and classification of objects. This method has also been proven to be very effective in a variety of computer vision and machine learning problems. As in other deep learning, however, training the CNN is interesting yet challenging. Recently, some metaheuristic algorithms have been used to optimize CNN using Genetic Algorithm, Parti...

  5. On a generalized Hankel type convolution of generalized functions

    Indian Academy of Sciences (India)

    Springer Verlag Heidelberg #4 2048 1996 Dec 15 10:16:45

    with x ◦ y denoting the hµ, ν-translation on the positive real line. (The analogue of the translation consider for the definition of the usual convolution *.) The function g(x ◦ y) will be called the hµ, ν translate of g(x); provided g(x) is locally bounded on 0

  6. A quantum algorithm for Viterbi decoding of classical convolutional codes

    OpenAIRE

    Grice, Jon R.; Meyer, David A.

    2014-01-01

    We present a quantum Viterbi algorithm (QVA) with better than classical performance under certain conditions. In this paper the proposed algorithm is applied to decoding classical convolutional codes, for instance; large constraint length $Q$ and short decode frames $N$. Other applications of the classical Viterbi algorithm where $Q$ is large (e.g. speech processing) could experience significant speedup with the QVA. The QVA exploits the fact that the decoding trellis is similar to the butter...

  7. Exponential estimates for stochastic convolutions in 2-smooth Banach spaces

    Czech Academy of Sciences Publication Activity Database

    Seidler, Jan

    2010-01-01

    Roč. 15, č. 50 (2010), s. 1556-1573 ISSN 1083-6489 R&D Projects: GA ČR GA201/07/0237 Institutional research plan: CEZ:AV0Z10750506 Keywords : stochastic convolutions in 2-smooth spaces * Burkholder-Davis-Gundy inequality * exponential tail estimates Subject RIV: BA - General Mathematics Impact factor: 0.946, year: 2010 http://library.utia.cas.cz/separaty/2010/SI/seidler-0348352.pdf

  8. General Dirichlet Series, Arithmetic Convolution Equations and Laplace Transforms

    Czech Academy of Sciences Publication Activity Database

    Glöckner, H.; Lucht, L.G.; Porubský, Štefan

    2009-01-01

    Roč. 193, č. 2 (2009), s. 109-129 ISSN 0039-3223 R&D Projects: GA ČR GA201/07/0191 Institutional research plan: CEZ:AV0Z10300504 Keywords : arithmetic function * Dirichlet convolution * polynomial equation * analytic equation * topological algebra * holomorphic functional calculus * implicit function theorem * Laplace transform * semigroup * complex measure Subject RIV: BA - General Mathematics Impact factor: 0.645, year: 2009 http://arxiv.org/abs/0712.3172

  9. Fully convolutional neural networks for polyp segmentation in colonoscopy

    OpenAIRE

    Rosa Brandao, P.; Mazomenos, E.; Ciuti, G.; Bianchi, F.; Menciassi, A.; Dario, P.; Koulaouzidis, A.; Arezzo, A.; Stoyanov, D.

    2017-01-01

    Colorectal cancer (CRC) is one of the most common and deadliest forms of cancer, accounting for nearly 10% of all forms of cancer in the world. Even though colonoscopy is considered the most effective method for screening and diagnosis, the success of the procedure is highly dependent on the operator skills and level of hand-eye coordination. In this work, we propose to adapt fully convolution neural networks (FCN), to identify and segment polyps in colonoscopy images. We converted three esta...

  10. Semi-Supervised Deep Learning for Fully Convolutional Networks

    OpenAIRE

    Baur, Christoph; Albarqouni, Shadi; Navab, Nassir

    2017-01-01

    Deep learning usually requires large amounts of labeled training data, but annotating data is costly and tedious. The framework of semi-supervised learning provides the means to use both labeled data and arbitrary amounts of unlabeled data for training. Recently, semi-supervised deep learning has been intensively studied for standard CNN architectures. However, Fully Convolutional Networks (FCNs) set the state-of-the-art for many image segmentation tasks. To the best of our knowledge, there i...

  11. Recursive Autoconvolution for Unsupervised Learning of Convolutional Neural Networks

    OpenAIRE

    Knyazev, Boris; Barth, Erhardt; Martinetz, Thomas

    2016-01-01

    In visual recognition tasks, such as image classification, unsupervised learning exploits cheap unlabeled data and can help to solve these tasks more efficiently. We show that the recursive autoconvolution operator, adopted from physics, boosts existing unsupervised methods by learning more discriminative filters. We take well established convolutional neural networks and train their filters layer-wise. In addition, based on previous works we design a network which extracts more than 600k fea...

  12. Fast convolutional sparse coding using matrix inversion lemma

    Czech Academy of Sciences Publication Activity Database

    Šorel, Michal; Šroubek, Filip

    2016-01-01

    Roč. 55, č. 1 (2016), s. 44-51 ISSN 1051-2004 R&D Projects: GA ČR GA13-29225S Institutional support: RVO:67985556 Keywords : Convolutional sparse coding * Feature learning * Deconvolution networks * Shift-invariant sparse coding Subject RIV: JD - Computer Applications, Robotics Impact factor: 2.337, year: 2016 http://library.utia.cas.cz/separaty/2016/ZOI/sorel-0459332.pdf

  13. Taxonomic Classification for Living Organisms Using Convolutional Neural Networks

    OpenAIRE

    Khawaldeh, Saed; Pervaiz, Usama; Elsharnoby, Mohammed; Alchalabi, Alaa Eddin; Al-Zubi, Nayel

    2017-01-01

    Taxonomic classification has a wide-range of applications such as finding out more about evolutionary history. Compared to the estimated number of organisms that nature harbors, humanity does not have a thorough comprehension of to which specific classes they belong. The classification of living organisms can be done in many machine learning techniques. However, in this study, this is performed using convolutional neural networks. Moreover, a DNA encoding technique is incorporated in the algo...

  14. Production and reception of meaningful sound in Foville's 'encompassing convolution'.

    Science.gov (United States)

    Schiller, F

    1999-04-01

    In the history of neurology. Achille Louis Foville (1799-1879) is a name deserving to be remembered. In the course of time, his circonvolution d'enceinte of 1844 (surrounding the Sylvian fissure) became the 'convolution encompassing' every aspect of aphasiology, including amusia, ie., the localization in a coherent semicircle of semicircle of cerebral cortext serving the production and perception of language, song and instrumental music in health and disease.

  15. Efficient Convolutional Neural Network with Binary Quantization Layer

    OpenAIRE

    Ravanbakhsh, Mahdyar; Mousavi, Hossein; Nabi, Moin; Marcenaro, Lucio; Regazzoni, Carlo

    2016-01-01

    In this paper we introduce a novel method for segmentation that can benefit from general semantics of Convolutional Neural Network (CNN). Our segmentation proposes visually and semantically coherent image segments. We use binary encoding of CNN features to overcome the difficulty of the clustering on the high-dimensional CNN feature space. These binary encoding can be embedded into the CNN as an extra layer at the end of the network. This results in real-time segmentation. To the best of our ...

  16. Convolutional Neural Networks for Page Segmentation of Historical Document Images

    OpenAIRE

    Chen, Kai; Seuret, Mathias

    2017-01-01

    This paper presents a Convolutional Neural Network (CNN) based page segmentation method for handwritten historical document images. We consider page segmentation as a pixel labeling problem, i.e., each pixel is classified as one of the predefined classes. Traditional methods in this area rely on carefully hand-crafted features or large amounts of prior knowledge. In contrast, we propose to learn features from raw image pixels using a CNN. While many researchers focus on developing deep CNN ar...

  17. Solving singular convolution equations using the inverse fast Fourier transform

    Czech Academy of Sciences Publication Activity Database

    Krajník, E.; Montesinos, V.; Zizler, P.; Zizler, Václav

    2012-01-01

    Roč. 57, č. 5 (2012), s. 543-550 ISSN 0862-7940 R&D Projects: GA AV ČR IAA100190901 Institutional research plan: CEZ:AV0Z10190503 Keywords : singular convolution equations * fast Fourier transform * tempered distribution Subject RIV: BA - General Mathematics Impact factor: 0.222, year: 2012 http://www.springerlink.com/content/m8437t3563214048/

  18. AFM tip-sample convolution effects for cylinder protrusions

    Science.gov (United States)

    Shen, Jian; Zhang, Dan; Zhang, Fei-Hu; Gan, Yang

    2017-11-01

    A thorough understanding about the AFM tip geometry dependent artifacts and tip-sample convolution effect is essential for reliable AFM topographic characterization and dimensional metrology. Using rigid sapphire cylinder protrusions (diameter: 2.25 μm, height: 575 nm) as the model system, a systematic and quantitative study about the imaging artifacts of four types of tips-two different pyramidal tips, one tetrahedral tip and one super sharp whisker tip-is carried out through comparing tip geometry dependent variations in AFM topography of cylinders and constructing the rigid tip-cylinder convolution models. We found that the imaging artifacts and the tip-sample convolution effect are critically related to the actual inclination of the working cantilever, the tip geometry, and the obstructive contacts between the working tip's planes/edges and the cylinder. Artifact-free images can only be obtained provided that all planes and edges of the working tip are steeper than the cylinder sidewalls. The findings reported here will contribute to reliable AFM characterization of surface features of micron or hundreds of nanometers in height that are frequently met in semiconductor, biology and materials fields.

  19. On the growth and form of cortical convolutions

    Science.gov (United States)

    Tallinen, Tuomas; Chung, Jun Young; Rousseau, François; Girard, Nadine; Lefèvre, Julien; Mahadevan, L.

    2016-06-01

    The rapid growth of the human cortex during development is accompanied by the folding of the brain into a highly convoluted structure. Recent studies have focused on the genetic and cellular regulation of cortical growth, but understanding the formation of the gyral and sulcal convolutions also requires consideration of the geometry and physical shaping of the growing brain. To study this, we use magnetic resonance images to build a 3D-printed layered gel mimic of the developing smooth fetal brain; when immersed in a solvent, the outer layer swells relative to the core, mimicking cortical growth. This relative growth puts the outer layer into mechanical compression and leads to sulci and gyri similar to those in fetal brains. Starting with the same initial geometry, we also build numerical simulations of the brain modelled as a soft tissue with a growing cortex, and show that this also produces the characteristic patterns of convolutions over a realistic developmental course. All together, our results show that although many molecular determinants control the tangential expansion of the cortex, the size, shape, placement and orientation of the folds arise through iterations and variations of an elementary mechanical instability modulated by early fetal brain geometry.

  20. Edgeworth Expansion Based Model for the Convolutional Noise pdf

    Directory of Open Access Journals (Sweden)

    Yonatan Rivlin

    2014-01-01

    Full Text Available Recently, the Edgeworth expansion up to order 4 was used to represent the convolutional noise probability density function (pdf in the conditional expectation calculations where the source pdf was modeled with the maximum entropy density approximation technique. However, the applied Lagrange multipliers were not the appropriate ones for the chosen model for the convolutional noise pdf. In this paper we use the Edgeworth expansion up to order 4 and up to order 6 to model the convolutional noise pdf. We derive the appropriate Lagrange multipliers, thus obtaining new closed-form approximated expressions for the conditional expectation and mean square error (MSE as a byproduct. Simulation results indicate hardly any equalization improvement with Edgeworth expansion up to order 4 when using optimal Lagrange multipliers over a nonoptimal set. In addition, there is no justification for using the Edgeworth expansion up to order 6 over the Edgeworth expansion up to order 4 for the 16QAM and easy channel case. However, Edgeworth expansion up to order 6 leads to improved equalization performance compared to the Edgeworth expansion up to order 4 for the 16QAM and hard channel case as well as for the case where the 64QAM is sent via an easy channel.

  1. Nuclear norm regularized convolutional Max Pos@Top machine

    KAUST Repository

    Li, Qinfeng

    2016-11-18

    In this paper, we propose a novel classification model for the multiple instance data, which aims to maximize the number of positive instances ranked before the top-ranked negative instances. This method belongs to a recently emerged performance, named as Pos@Top. Our proposed classification model has a convolutional structure that is composed by four layers, i.e., the convolutional layer, the activation layer, the max-pooling layer and the full connection layer. In this paper, we propose an algorithm to learn the convolutional filters and the full connection weights to maximize the Pos@Top measure over the training set. Also, we try to minimize the rank of the filter matrix to explore the low-dimensional space of the instances in conjunction with the classification results. The rank minimization is conducted by the nuclear norm minimization of the filter matrix. In addition, we develop an iterative algorithm to solve the corresponding problem. We test our method on several benchmark datasets. The experimental results show the superiority of our method compared with other state-of-the-art Pos@Top maximization methods.

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

    Science.gov (United States)

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

    2016-10-01

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

  3. 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.

  4. Korean letter handwritten recognition using deep convolutional neural network on android platform

    Science.gov (United States)

    Purnamawati, S.; Rachmawati, D.; Lumanauw, G.; Rahmat, R. F.; Taqyuddin, R.

    2018-03-01

    Currently, popularity of Korean culture attracts many people to learn everything about Korea, particularly its language. To acquire Korean Language, every single learner needs to be able to understand Korean non-Latin character. A digital approach needs to be carried out in order to make Korean learning process easier. This study is done by using Deep Convolutional Neural Network (DCNN). DCNN performs the recognition process on the image based on the model that has been trained such as Inception-v3 Model. Subsequently, re-training process using transfer learning technique with the trained and re-trained value of model is carried though in order to develop a new model with a better performance without any specific systemic errors. The testing accuracy of this research results in 86,9%.

  5. Imaging in scattering media using correlation image sensors and sparse convolutional coding

    KAUST Repository

    Heide, Felix

    2014-10-17

    Correlation image sensors have recently become popular low-cost devices for time-of-flight, or range cameras. They usually operate under the assumption of a single light path contributing to each pixel. We show that a more thorough analysis of the sensor data from correlation sensors can be used can be used to analyze the light transport in much more complex environments, including applications for imaging through scattering and turbid media. The key of our method is a new convolutional sparse coding approach for recovering transient (light-in-flight) images from correlation image sensors. This approach is enabled by an analysis of sparsity in complex transient images, and the derivation of a new physically-motivated model for transient images with drastically improved sparsity.

  6. Airborne single particle mass spectrometers (SPLAT II & miniSPLAT) and new software for data visualization and analysis in a geo-spatial context.

    Science.gov (United States)

    Zelenyuk, Alla; Imre, Dan; Wilson, Jacqueline; Zhang, Zhiyuan; Wang, Jun; Mueller, Klaus

    2015-02-01

    Understanding the effect of aerosols on climate requires knowledge of the size and chemical composition of individual aerosol particles-two fundamental properties that determine an aerosol's optical properties and ability to serve as cloud condensation or ice nuclei. Here we present our aircraft-compatible single particle mass spectrometers, SPLAT II and its new, miniaturized version, miniSPLAT that measure in-situ and in real-time the size and chemical composition of individual aerosol particles with extremely high sensitivity, temporal resolution, and sizing precision on the order of a monolayer. Although miniSPLAT's size, weight, and power consumption are significantly smaller, its performance is on par with SPLAT II. Both instruments operate in dual data acquisition mode to measure, in addition to single particle size and composition, particle number concentrations, size distributions, density, and asphericity with high temporal resolution. We also present ND-Scope, our newly developed interactive visual analytics software package. ND-Scope is designed to explore and visualize the vast amount of complex, multidimensional data acquired by our single particle mass spectrometers, along with other aerosol and cloud characterization instruments on-board aircraft. We demonstrate that ND-Scope makes it possible to visualize the relationships between different observables and to view the data in a geo-spatial context, using the interactive and fully coupled Google Earth and Parallel Coordinates displays. Here we illustrate the utility of ND-Scope to visualize the spatial distribution of atmospheric particles of different compositions, and explore the relationship between individual particle compositions and their activity as cloud condensation nuclei.

  7. Estimation of the spatial distribution of traps using space-charge-limited current measurements in an organic single crystal

    KAUST Repository

    Dacuña, Javier

    2012-09-06

    We used a mobility edge transport model and solved the drift-diffusion equation to characterize the space-charge-limited current of a rubrene single-crystal hole-only diode. The current-voltage characteristics suggest that current is injection-limited at high voltage when holes are injected from the bottom contact (reverse bias). In contrast, the low-voltage regime shows that the current is higher when holes are injected from the bottom contact as compared to hole injection from the top contact (forward bias), which does not exhibit injection-limited current in the measured voltage range. This behavior is attributed to an asymmetric distribution of trap states in the semiconductor, specifically, a distribution of traps located near the top contact. Accounting for a localized trap distribution near the contact allows us to reproduce the temperature-dependent current-voltage characteristics in forward and reverse bias simultaneously, i.e., with a single set of model parameters. We estimated that the local trap distribution contains 1.19×1011 cm -2 states and decays as exp(-x/32.3nm) away from the semiconductor-contact interface. The local trap distribution near one contact mainly affects injection from the same contact, hence breaking the symmetry in the charge transport. The model also provides information of the band mobility, energy barrier at the contacts, and bulk trap distribution with their corresponding confidence intervals. © 2012 American Physical Society.

  8. Spatially multiplexed orbital-angular-momentum-encoded single photon and classical channels in a free-space optical communication link.

    Science.gov (United States)

    Ren, Yongxiong; Liu, Cong; Pang, Kai; Zhao, Jiapeng; Cao, Yinwen; Xie, Guodong; Li, Long; Liao, Peicheng; Zhao, Zhe; Tur, Moshe; Boyd, Robert W; Willner, Alan E

    2017-12-01

    We experimentally demonstrate spatial multiplexing of an orbital angular momentum (OAM)-encoded quantum channel and a classical Gaussian beam with a different wavelength and orthogonal polarization. Data rates as large as 100 MHz are achieved by encoding on two different OAM states by employing a combination of independently modulated laser diodes and helical phase holograms. The influence of OAM mode spacing, encoding bandwidth, and interference from the co-propagating Gaussian beam on registered photon count rates and quantum bit error rates is investigated. Our results show that the deleterious effects of intermodal crosstalk effects on system performance become less important for OAM mode spacing Δ≥2 (corresponding to a crosstalk value of less than -18.5  dB). The use of OAM domain can additionally offer at least 10.4 dB isolation besides that provided by wavelength and polarization, leading to a further suppression of interference from the classical channel.

  9. A deep convolutional neural network for classification of red blood cells in sickle cell anemia.

    Science.gov (United States)

    Xu, Mengjia; Papageorgiou, Dimitrios P; Abidi, Sabia Z; Dao, Ming; Zhao, Hong; Karniadakis, George Em

    2017-10-01

    Sickle cell disease (SCD) is a hematological disorder leading to blood vessel occlusion accompanied by painful episodes and even death. Red blood cells (RBCs) of SCD patients have diverse shapes that reveal important biomechanical and bio-rheological characteristics, e.g. their density, fragility, adhesive properties, etc. Hence, having an objective and effective way of RBC shape quantification and classification will lead to better insights and eventual better prognosis of the disease. To this end, we have developed an automated, high-throughput, ex-vivo RBC shape classification framework that consists of three stages. First, we present an automatic hierarchical RBC extraction method to detect the RBC region (ROI) from the background, and then separate touching RBCs in the ROI images by applying an improved random walk method based on automatic seed generation. Second, we apply a mask-based RBC patch-size normalization method to normalize the variant size of segmented single RBC patches into uniform size. Third, we employ deep convolutional neural networks (CNNs) to realize RBC classification; the alternating convolution and pooling operations can deal with non-linear and complex patterns. Furthermore, we investigate the specific shape factor quantification for the classified RBC image data in order to develop a general multiscale shape analysis. We perform several experiments on raw microscopy image datasets from 8 SCD patients (over 7,000 single RBC images) through a 5-fold cross validation method both for oxygenated and deoxygenated RBCs. We demonstrate that the proposed framework can successfully classify sickle shape RBCs in an automated manner with high accuracy, and we also provide the corresponding shape factor analysis, which can be used synergistically with the CNN analysis for more robust predictions. Moreover, the trained deep CNN exhibits good performance even for a deoxygenated dataset and distinguishes the subtle differences in texture alteration

  10. Automatic labeling of molecular biomarkers of immunohistochemistry images using fully convolutional networks

    Science.gov (United States)

    Ward, Rabab K.; van Niekerk, Dirk; Guillaud, Martial

    2018-01-01

    This paper addresses the problem of quantifying biomarkers in multi-stained tissues based on the color and spatial information of microscopy images of the tissue. A deep learning-based method that can automatically localize and quantify the regions expressing biomarker(s) in any selected area on a whole slide image is proposed. The deep learning network, which we refer to as Whole Image (WI)-Net, is a fully convolutional network whose input is the true RGB color image of a tissue and output is a map showing the locations of each biomarker. The WI-Net relies on a different network, Nuclei (N)-Net, which is a convolutional neural network that classifies each nucleus separately according to the biomarker(s) it expresses. In this study, images of immunohistochemistry (IHC)-stained slides were collected and used. Images of nuclei (4679 RGB images) were manually labeled based on the expressing biomarkers in each nucleus (as p16 positive, Ki-67 positive, p16 and Ki-67 positive, p16 and Ki-67 negative). The labeled nuclei images were used to train the N-Net (obtaining an accuracy of 92% in a test set). The trained N-Net was then extended to WI-Net that generated a map of all biomarkers in any selected sub-image of the whole slide image acquired by the scanner (instead of classifying every nucleus image). The results of our method compare well with the manual labeling by humans (average F-score of 0.96). In addition, we carried a layer-based immunohistochemical analysis of cervical epithelium, and showed that our method can be used by pathologists to differentiate between different grades of cervical intraepithelial neoplasia by quantitatively assessing the percentage of proliferating cells in the different layers of HPV positive lesions. PMID:29351281

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

    Science.gov (United States)

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

    2016-01-01

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

  12. Phonon Confinement Induced Non-Concomitant Near-Infrared Emission along a Single ZnO Nanowire: Spatial Evolution Study of Phononic and Photonic Properties

    Directory of Open Access Journals (Sweden)

    Po-Hsun Shih

    2017-10-01

    Full Text Available The impact of mixed defects on ZnO phononic and photonic properties at the nanoscale is only now being investigated. Here we report an effective strategy to study the distribution of defects along the growth direction of a single ZnO nanowire (NW, performed qualitatively as well as quantitatively using energy dispersive spectroscopy (EDS, confocal Raman-, and photoluminescence (PL-mapping technique. A non-concomitant near-infrared (NIR emission of 1.53 ± 0.01 eV was observed near the bottom region of 2.05 ± 0.05 μm along a single ZnO NW and could be successfully explained by the radiative recombination of shallowly trapped electrons V_O^(** with deeply trapped holes at V_Zn^''. A linear chain model modified from a phonon confinement model was used to describe the growth of short-range correlations between the mean distance of defects and its evolution with spatial position along the axial growth direction by fitting the E2H mode. Our results are expected to provide new insights into improving the study of the photonic and photonic properties of a single nanowire.

  13. Model selection for convolutive ICA with an application to spatiotemporal analysis of EEG

    DEFF Research Database (Denmark)

    Dyrholm, Mads; Makeig, S.; Hansen, Lars Kai

    2007-01-01

    We present a new algorithm for maximum likelihood convolutive independent component analysis (ICA) in which components are unmixed using stable autoregressive filters determined implicitly by estimating a convolutive model of the mixing process. By introducing a convolutive mixing model...... for the components, we show how the order of the filters in the model can be correctly detected using Bayesian model selection. We demonstrate a framework for deconvolving a subspace of independent components in electroencephalography (EEG). Initial results suggest that in some cases, convolutive mixing may...

  14. Sign changes in linear combinations of derivatives and convolutions of Polya frequency functions

    Directory of Open Access Journals (Sweden)

    Steven Nahmias

    1979-01-01

    combinations of derivatives and convolutions of Polya frequency functions using the variation diminishing properties of totally positive functions. These constitute extensions of earlier results of Karlin and Proschan.

  15. Single-beam image encryption using spatially separated ciphertexts based on interference principle in the Fresnel domain

    Science.gov (United States)

    Wang, Qu; Guo, Qing; Lei, Liang; Zhou, Jinyun

    2014-12-01

    A new optical security system for image encryption based on optical interference principle and translation property of Fresnel transform (FrT) has been proposed in this article. The algorithm of this proposal is specially designed for single-beam optical decryption and can thoroughly resolve the silhouette problem existing in the previous interference-based scheme. Different from earlier schemes using interference of phase-only masks (POMs), the inverse FrT of primitive image is digitally decomposed into a random POM and a complex field distribution. Information associated with the primitive images can be completely smoothed away by the modulation of this random POM. Through the translation property of FrT, two linear phase-only terms are then used to modulate the obtained random POM and the complex distribution, respectively. Two complex ciphertexts are generated by performing digital inverse FrT again. One cannot recover any visible information of secret image using only one ciphertext. Moreover, to recover the primitive image correctly, the correct ciphertexts must be placed in the certain positions of input plane of decryption system, respectively. As additional keys, position center coordinates of ciphertexts can increase the security strength of this encryption system against brute force attacks greatly. Numerical simulations have been given to verify the performance and feasibility of this proposal. To further enhance the application value of this algorithm, an alternative approach based on Fourier transform has also been discussed briefly.

  16. Spatial distribution of bacterial communities on volumetric and planar anodes in single-chamber air-cathode microbial fuel cells

    KAUST Repository

    Vargas, Ignacio T.

    2013-05-29

    Pyrosequencing was used to characterize bacterial communities in air-cathode microbial fuel cells across a volumetric (graphite fiber brush) and a planar (carbon cloth) anode, where different physical and chemical gradients would be expected associated with the distance between anode location and the air cathode. As expected, the stable operational voltage and the coulombic efficiency (CE) were higher for the volumetric anode than the planar anode (0.57V and CE=22% vs. 0.51V and CE=12%). The genus Geobacter was the only known exoelectrogen among the observed dominant groups, comprising 57±4% of recovered sequences for the brush and 27±5% for the carbon-cloth anode. While the bacterial communities differed between the two anode materials, results showed that Geobacter spp. and other dominant bacterial groups were homogenously distributed across both planar and volumetric anodes. This lends support to previous community analysis interpretations based on a single biofilm sampling location in these systems. © 2013 Wiley Periodicals, Inc.

  17. Optimization of a DPP-BOTDA sensor with 25 cm spatial resolution over 60 km standard single-mode fiber using Simplex codes and optical pre-amplification.

    Science.gov (United States)

    Soto, Marcelo A; Taki, Mohammad; Bolognini, Gabriele; Di Pasquale, Fabrizio

    2012-03-26

    Sub-meter distributed optical fiber sensing based on Brillouin optical time-domain analysis with differential pulse-width pairs (DPP-BOTDA) is combined with the use of optical pre-amplification and pulse coding. In order to provide significant measurement SNR enhancement and to avoid distortions in the Brillouin gain spectrum due to acoustic-wave pre-excitation, the pulse width and duty cycle of Simplex coding based on return-to-zero pulses are optimized through simulations. In addition, the use of linear optical pre-amplification increases the receiver sensitivity and the overall dynamic range of DPP-BOTDA measurements. Experimental results demonstrate for first time a spatial resolution of ~25 cm over a 60 km standard single-mode fiber (equivalent to ~240 k discrete sensing points) with temperature resolution of 1.2°C and strain resolution of 24 με.

  18. An efficient finite element time‐domain formulation for the elastic second‐order wave equation: A non‐split complex frequency shifted convolutional PML

    DEFF Research Database (Denmark)

    Matzen, René

    2011-01-01

    formulation based on the second‐order wave equation with displacements as the only unknowns to annihilate spurious reflections from near‐grazing waves. The derived variational form allows for the use of e.g. finite element and the spectral element methods as spatial discretization schemes. A recursive...... convolution update scheme of second‐order accuracy is employed such that highly stable, effective time integration with the Newmark‐beta (implicit and explicit with mass lumping) method is achieved. The implementation requires minor modifications of existing displacement‐based finite element software......The perfectly matched layer (PML) technique has demonstrated very high efficiency as absorbing boundary condition for the elastic wave equation recast as a first‐order system in velocity and stress in attenuating non‐grazing bulk and surface waves. This paper develops a novel convolutional PML...

  19. Joint Craniomaxillofacial Bone Segmentation and Landmark Digitization by Context-Guided Fully Convolutional Networks.

    Science.gov (United States)

    Zhang, Jun; Liu, Mingxia; Wang, Li; Chen, Si; Yuan, Peng; Li, Jianfu; Shen, Steve Guo-Fang; Tang, Zhen; Chen, Ken-Chung; Xia, James J; Shen, Dinggang

    2017-09-01

    Generating accurate 3D models from cone-beam computed tomography (CBCT) images is an important step in developing treatment plans for patients with craniomaxillofacial (CMF) deformities. This process often involves bone segmentation and landmark digitization. Since anatomical landmarks generally lie on the boundaries of segmented bone regions, the tasks of bone segmentation and landmark digitization could be highly correlated. However, most existing methods simply treat them as two standalone tasks, without considering their inherent association. In addition, these methods usually ignore the spatial context information ( i.e. , displacements from voxels to landmarks) in CBCT images. To this end, we propose a context-guided fully convolutional network (FCN) for joint bone segmentation and landmark digitization. Specifically, we first train an FCN to learn the displacement maps to capture the spatial context information in CBCT images. Using the learned displacement maps as guidance information, we further develop a multi-task FCN to jointly perform bone segmentation and landmark digitization. Our method has been evaluated on 107 subjects from two centers, and the experimental results show that our method is superior to the state-of-the-art methods in both bone segmentation and landmark digitization.

  20. Acute Aldosterone-mediated Signaling Networks in Distal Convoluted Tubules

    DEFF Research Database (Denmark)

    Cheng, Lei; Wu, Qi; Olesen, Emma T. B.

    2017-01-01

    The kidney distal convoluted tubule (DCT) plays an important role in modulating body sodium balance and blood pressure. Long-term effects of aldosterone to increase sodium reabsorption in the DCT are well described. However, potential effects of aldosterone to acutely modulate DCT function via non...... in abundance following aldosterone treatment. The EGFR, ERK1/2, AKT, GSK3B and P70S6K were predicted to be important pathway nodes based on the quantitative proteomics data using network analysis. Ex vivo studies in isolated mouse cortical tubules demonstrated an increase in phosphorylated (active) NCC...

  1. Phase transitions in glassy systems via convolutional neural networks

    Science.gov (United States)

    Fang, Chao

    Machine learning is a powerful approach commonplace in industry to tackle large data sets. Most recently, it has found its way into condensed matter physics, allowing for the first time the study of, e.g., topological phase transitions and strongly-correlated electron systems. The study of spin glasses is plagued by finite-size effects due to the long thermalization times needed. Here we use convolutional neural networks in an attempt to detect a phase transition in three-dimensional Ising spin glasses. Our results are compared to traditional approaches.

  2. Convolutional neural networks for synthetic aperture radar classification

    Science.gov (United States)

    Profeta, Andrew; Rodriguez, Andres; Clouse, H. Scott

    2016-05-01

    For electro-optical object recognition, convolutional neural networks (CNNs) are the state-of-the-art. For large datasets, CNNs are able to learn meaningful features used for classification. However, their application to synthetic aperture radar (SAR) has been limited. In this work we experimented with various CNN architectures on the MSTAR SAR dataset. As the input to the CNN we used the magnitude and phase (2 channels) of the SAR imagery. We used the deep learning toolboxes CAFFE and Torch7. Our results show that we can achieve 93% accuracy on the MSTAR dataset using CNNs.

  3. Blind separation of more sources than sensors in convolutive mixtures

    DEFF Research Database (Denmark)

    Olsson, Rasmus Kongsgaard; Hansen, Lars Kai

    2006-01-01

    We demonstrate that blind separation of more sources than sensors can be performed based solely on the second order statistics of the observed mixtures. This a generalization of well-known robust algorithms that are suited for equal number of sources and sensors. It is assumed that the sources...... are non-stationary and sparsely distributed in the time-frequency plane. The mixture model is convolutive, i.e. acoustic setups such as the cocktail party problem are contained. The limits of identifiability are determined in the framework of the PARAFAC model. In the experimental section...

  4. Salient regions detection using convolutional neural networks and color volume

    Science.gov (United States)

    Liu, Guang-Hai; Hou, Yingkun

    2018-03-01

    Convolutional neural network is an important technique in machine learning, pattern recognition and image processing. In order to reduce the computational burden and extend the classical LeNet-5 model to the field of saliency detection, we propose a simple and novel computing model based on LeNet-5 network. In the proposed model, hue, saturation and intensity are utilized to extract depth cues, and then we integrate depth cues and color volume to saliency detection following the basic structure of the feature integration theory. Experimental results show that the proposed computing model outperforms some existing state-of-the-art methods on MSRA1000 and ECSSD datasets.

  5. Taxonomic Classification for Living Organisms Using Convolutional Neural Networks.

    Science.gov (United States)

    Khawaldeh, Saed; Pervaiz, Usama; Elsharnoby, Mohammed; Alchalabi, Alaa Eddin; Al-Zubi, Nayel

    2017-11-17

    Taxonomic classification has a wide-range of applications such as finding out more about evolutionary history. Compared to the estimated number of organisms that nature harbors, humanity does not have a thorough comprehension of to which specific classes they belong. The classification of living organisms can be done in many machine learning techniques. However, in this study, this is performed using convolutional neural networks. Moreover, a DNA encoding technique is incorporated in the algorithm to increase performance and avoid misclassifications. The algorithm proposed outperformed the state of the art algorithms in terms of accuracy and sensitivity, which illustrates a high potential for using it in many other applications in genome analysis.

  6. Stochastic convolutions driven by martingales: maximal inequalities and exponential integrability

    Czech Academy of Sciences Publication Activity Database

    Hausenblas, E.; Seidler, Jan

    2008-01-01

    Roč. 26, č. 1 (2008), s. 98-119 ISSN 0736-2994 Grant - others:Austrian Academy of Sciences(AT) APART 700; GA ČR(CZ) GA201/04/0750; GA ČR(CZ) GA201/01/1197; GA MSM(CZ) Kontakt 2001-05 Program:GA; GA Institutional research plan: CEZ:AV0Z10750506 Source of funding: V - iné verejné zdroje ; V - iné verejné zdroje Keywords : maximal inequality * exponential tail estimates * stochastic convolution Subject RIV: BA - General Mathematics Impact factor: 0.528, year: 2008

  7. Fast Convolutional Sparse Coding in the Dual Domain

    KAUST Repository

    Affara, Lama Ahmed

    2017-09-27

    Convolutional sparse coding (CSC) is an important building block of many computer vision applications ranging from image and video compression to deep learning. We present two contributions to the state of the art in CSC. First, we significantly speed up the computation by proposing a new optimization framework that tackles the problem in the dual domain. Second, we extend the original formulation to higher dimensions in order to process a wider range of inputs, such as color inputs, or HOG features. Our results show a significant speedup compared to the current state of the art in CSC.

  8. Large scale tissue histopathology image classification, segmentation, and visualization via deep convolutional activation features.

    Science.gov (United States)

    Xu, Yan; Jia, Zhipeng; Wang, Liang-Bo; Ai, Yuqing; Zhang, Fang; Lai, Maode; Chang, Eric I-Chao

    2017-05-26

    Histopathology image analysis is a gold standard for cancer recognition and diagnosis. Automatic analysis of histopathology images can help pathologists diagnose tumor and cancer subtypes, alleviating the workload of pathologists. There are two basic types of tasks in digital histopathology image analysis: image classification and image segmentation. Typical problems with histopathology images that hamper automatic analysis include complex clinical representations, limited quantities of training images in a dataset, and the extremely large size of singular images (usually up to gigapixels). The property of extremely large size for a single image also makes a histopathology image dataset be considered large-scale, even if the number of images in the dataset is limited. In this paper, we propose leveraging deep convolutional neural network (CNN) activation features to perform classification, segmentation and visualization in large-scale tissue histopathology images. Our framework transfers features extracted from CNNs trained by a large natural image database, ImageNet, to histopathology images. We also explore the characteristics of CNN features by visualizing the response of individual neuron components in the last hidden layer. Some of these characteristics reveal biological insights that have been verified by pathologists. According to our experiments, the framework proposed has shown state-of-the-art performance on a brain tumor dataset from the MICCAI 2014 Brain Tumor Digital Pathology Challenge and a colon cancer histopathology image dataset. The framework proposed is a simple, efficient and effective system for histopathology image automatic analysis. We successfully transfer ImageNet knowledge as deep convolutional activation features to the classification and segmentation of histopathology images with little training data. CNN features are significantly more powerful than expert-designed features.

  9. Predicting Response to Neoadjuvant Chemotherapy with PET Imaging Using Convolutional Neural Networks

    Science.gov (United States)

    Ypsilantis, Petros-Pavlos; Siddique, Musib; Sohn, Hyon-Mok; Davies, Andrew; Cook, Gary; Goh, Vicky; Montana, Giovanni

    2015-01-01

    Imaging of cancer with 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) has become a standard component of diagnosis and staging in oncology, and is becoming more important as a quantitative monitor of individual response to therapy. In this article we investigate the challenging problem of predicting a patient’s response to neoadjuvant chemotherapy from a single 18F-FDG PET scan taken prior to treatment. We take a “radiomics” approach whereby a large amount of quantitative features is automatically extracted from pretherapy PET images in order to build a comprehensive quantification of the tumor phenotype. While the dominant methodology relies on hand-crafted texture features, we explore the potential of automatically learning low- to high-level features directly from PET scans. We report on a study that compares the performance of two competing radiomics strategies: an approach based on state-of-the-art statistical classifiers using over 100 quantitative imaging descriptors, including texture features as well as standardized uptake values, and a convolutional neural network, 3S-CNN, trained directly from PET scans by taking sets of adjacent intra-tumor slices. Our experimental results, based on a sample of 107 patients with esophageal cancer, provide initial evidence that convolutional neural networks have the potential to extract PET imaging representations that are highly predictive of response to therapy. On this dataset, 3S-CNN achieves an average 80.7% sensitivity and 81.6% specificity in predicting non-responders, and outperforms other competing predictive models. PMID:26355298

  10. Predicting Response to Neoadjuvant Chemotherapy with PET Imaging Using Convolutional Neural Networks.

    Directory of Open Access Journals (Sweden)

    Petros-Pavlos Ypsilantis

    Full Text Available Imaging of cancer with 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET has become a standard component of diagnosis and staging in oncology, and is becoming more important as a quantitative monitor of individual response to therapy. In this article we investigate the challenging problem of predicting a patient's response to neoadjuvant chemotherapy from a single 18F-FDG PET scan taken prior to treatment. We take a "radiomics" approach whereby a large amount of quantitative features is automatically extracted from pretherapy PET images in order to build a comprehensive quantification of the tumor phenotype. While the dominant methodology relies on hand-crafted texture features, we explore the potential of automatically learning low- to high-level features directly from PET scans. We report on a study that compares the performance of two competing radiomics strategies: an approach based on state-of-the-art statistical classifiers using over 100 quantitative imaging descriptors, including texture features as well as standardized uptake values, and a convolutional neural network, 3S-CNN, trained directly from PET scans by taking sets of adjacent intra-tumor slices. Our experimental results, based on a sample of 107 patients with esophageal cancer, provide initial evidence that convolutional neural networks have the potential to extract PET imaging representations that are highly predictive of response to therapy. On this dataset, 3S-CNN achieves an average 80.7% sensitivity and 81.6% specificity in predicting non-responders, and outperforms other competing predictive models.

  11. FULLY CONVOLUTIONAL NETWORKS FOR MULTI-MODALITY ISOINTENSE INFANT BRAIN IMAGE SEGMENTATION.

    Science.gov (United States)

    Nie, Dong; Wang, Li; Gao, Yaozong; Shen, Dinggang

    The segmentation of infant brain tissue images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) plays an important role in studying early brain development. In the isointense phase (approximately 6-8 months of age), WM and GM exhibit similar levels of intensity in both T1 and T2 MR images, resulting in extremely low tissue contrast and thus making the tissue segmentation very challenging. The existing methods for tissue segmentation in this isointense phase usually employ patch-based sparse labeling on single T1, T2 or fractional anisotropy (FA) modality or their simply-stacked combinations without fully exploring the multi-modality information. To address the challenge, in this paper, we propose to use fully convolutional networks (FCNs) for the segmentation of isointense phase brain MR images. Instead of simply stacking the three modalities, we train one network for each modality image, and then fuse their high-layer features together for final segmentation. Specifically, we conduct a convolution-pooling stream for multimodality information from T1, T2, and FA images separately, and then combine them in high-layer for finally generating the segmentation maps as the outputs. We compared the performance of our approach with that of the commonly used segmentation methods on a set of manually segmented isointense phase brain images. Results showed that our proposed model significantly outperformed previous methods in terms of accuracy. In addition, our results also indicated a better way of integrating multi-modality images, which leads to performance improvement.

  12. Deep convolutional neural networks for multi-modality isointense infant brain image segmentation.

    Science.gov (United States)

    Zhang, Wenlu; Li, Rongjian; Deng, Houtao; Wang, Li; Lin, Weili; Ji, Shuiwang; Shen, Dinggang

    2015-03-01

    The segmentation of infant brain tissue images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) plays an important role in studying early brain development in health and disease. In the isointense stage (approximately 6-8 months of age), WM and GM exhibit similar levels of intensity in both T1 and T2 MR images, making the tissue segmentation very challenging. Only a small number of existing methods have been designed for tissue segmentation in this isointense stage; however, they only used a single T1 or T2 images, or the combination of T1 and T2 images. In this paper, we propose to use deep convolutional neural networks (CNNs) for segmenting isointense stage brain tissues using multi-modality MR images. CNNs are a type of deep models in which trainable filters and local neighborhood pooling operations are applied alternatingly on the raw input images, resulting in a hierarchy of increasingly complex features. Specifically, we used multi-modality information from T1, T2, and fractional anisotropy (FA) images as inputs and then generated the segmentation maps as outputs. The multiple intermediate layers applied convolution, pooling, normalization, and other operations to capture the highly nonlinear mappings between inputs and outputs. We compared the performance of our approach with that of the commonly used segmentation methods on a set of manually segmented isointense stage brain images. Results showed that our proposed model significantly outperformed prior methods on infant brain tissue segmentation. In addition, our results indicated that integration of multi-modality images led to significant performance improvement. Copyright © 2014 Elsevier Inc. All rights reserved.

  13. Siamese convolutional networks for tracking the spine motion

    Science.gov (United States)

    Liu, Yuan; Sui, Xiubao; Sun, Yicheng; Liu, Chengwei; Hu, Yong

    2017-09-01

    Deep learning models have demonstrated great success in various computer vision tasks such as image classification and object tracking. However, tracking the lumbar spine by digitalized video fluoroscopic imaging (DVFI), which can quantitatively analyze the motion mode of spine to diagnose lumbar instability, has not yet been well developed due to the lack of steady and robust tracking method. In this paper, we propose a novel visual tracking algorithm of the lumbar vertebra motion based on a Siamese convolutional neural network (CNN) model. We train a full-convolutional neural network offline to learn generic image features. The network is trained to learn a similarity function that compares the labeled target in the first frame with the candidate patches in the current frame. The similarity function returns a high score if the two images depict the same object. Once learned, the similarity function is used to track a previously unseen object without any adapting online. In the current frame, our tracker is performed by evaluating the candidate rotated patches sampled around the previous frame target position and presents a rotated bounding box to locate the predicted target precisely. Results indicate that the proposed tracking method can detect the lumbar vertebra steadily and robustly. Especially for images with low contrast and cluttered background, the presented tracker can still achieve good tracking performance. Further, the proposed algorithm operates at high speed for real time tracking.

  14. Digital image correlation based on a fast convolution strategy

    Science.gov (United States)

    Yuan, Yuan; Zhan, Qin; Xiong, Chunyang; Huang, Jianyong

    2017-10-01

    In recent years, the efficiency of digital image correlation (DIC) methods has attracted increasing attention because of its increasing importance for many engineering applications. Based on the classical affine optical flow (AOF) algorithm and the well-established inverse compositional Gauss-Newton algorithm, which is essentially a natural extension of the AOF algorithm under a nonlinear iterative framework, this paper develops a set of fast convolution-based DIC algorithms for high-efficiency subpixel image registration. Using a well-developed fast convolution technique, the set of algorithms establishes a series of global data tables (GDTs) over the digital images, which allows the reduction of the computational complexity of DIC significantly. Using the pre-calculated GDTs, the subpixel registration calculations can be implemented efficiently in a look-up-table fashion. Both numerical simulation and experimental verification indicate that the set of algorithms significantly enhances the computational efficiency of DIC, especially in the case of a dense data sampling for the digital images. Because the GDTs need to be computed only once, the algorithms are also suitable for efficiently coping with image sequences that record the time-varying dynamics of specimen deformations.

  15. Classifying images using restricted Boltzmann machines and convolutional neural networks

    Science.gov (United States)

    Zhao, Zhijun; Xu, Tongde; Dai, Chenyu

    2017-07-01

    To improve the feature recognition ability of deep model transfer learning, we propose a hybrid deep transfer learning method for image classification based on restricted Boltzmann machines (RBM) and convolutional neural networks (CNNs). It integrates learning abilities of two models, which conducts subject classification by exacting structural higher-order statistics features of images. While the method transfers the trained convolutional neural networks to the target datasets, fully-connected layers can be replaced by restricted Boltzmann machine layers; then the restricted Boltzmann machine layers and Softmax classifier are retrained, and BP neural network can be used to fine-tuned the hybrid model. The restricted Boltzmann machine layers has not only fully integrated the whole feature maps, but also learns the statistical features of target datasets in the view of the biggest logarithmic likelihood, thus removing the effects caused by the content differences between datasets. The experimental results show that the proposed method has improved the accuracy of image classification, outperforming other methods on Pascal VOC2007 and Caltech101 datasets.

  16. Development of a morphological convolution operator for bearing fault detection

    Science.gov (United States)

    Li, Yifan; Liang, Xihui; Liu, Weiwei; Wang, Yan

    2018-05-01

    This paper presents a novel signal processing scheme, namely morphological convolution operator (MCO) lifted morphological undecimated wavelet (MUDW), for rolling element bearing fault detection. In this scheme, a MCO is first designed to fully utilize the advantage of the closing & opening gradient operator and the closing-opening & opening-closing gradient operator for feature extraction as well as the merit of excellent denoising characteristics of the convolution operator. The MCO is then introduced into MUDW for the purpose of improving the fault detection ability of the reported MUDWs. Experimental vibration signals collected from a train wheelset test rig and the bearing data center of Case Western Reserve University are employed to evaluate the effectiveness of the proposed MCO lifted MUDW on fault detection of rolling element bearings. The results show that the proposed approach has a superior performance in extracting fault features of defective rolling element bearings. In addition, comparisons are performed between two reported MUDWs and the proposed MCO lifted MUDW. The MCO lifted MUDW outperforms both of them in detection of outer race faults and inner race faults of rolling element bearings.

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

    Science.gov (United States)

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

    2017-05-01

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

  18. Real-Time Video Convolutional Face Finder on Embedded Platforms

    Directory of Open Access Journals (Sweden)

    Franck Mamalet

    2007-03-01

    Full Text Available A high-level optimization methodology is applied for implementing the well-known convolutional face finder (CFF algorithm for real-time applications on mobile phones, such as teleconferencing, advanced user interfaces, image indexing, and security access control. CFF is based on a feature extraction and classification technique which consists of a pipeline of convolutions and subsampling operations. The design of embedded systems requires a good trade-off between performance and code size due to the limited amount of available resources. The followed methodology copes with the main drawbacks of the original implementation of CFF such as floating-point computation and memory allocation, in order to allow parallelism exploitation and perform algorithm optimizations. Experimental results show that our embedded face detection system can accurately locate faces with less computational load and memory cost. It runs on a 275 MHz Starcore DSP at 35 QCIF images/s with state-of-the-art detection rates and very low false alarm rates.

  19. Video-based face recognition via convolutional neural networks

    Science.gov (United States)

    Bao, Tianlong; Ding, Chunhui; Karmoshi, Saleem; Zhu, Ming

    2017-06-01

    Face recognition has been widely studied recently while video-based face recognition still remains a challenging task because of the low quality and large intra-class variation of video captured face images. In this paper, we focus on two scenarios of video-based face recognition: 1)Still-to-Video(S2V) face recognition, i.e., querying a still face image against a gallery of video sequences; 2)Video-to-Still(V2S) face recognition, in contrast to S2V scenario. A novel method was proposed in this paper to transfer still and video face images to an Euclidean space by a carefully designed convolutional neural network, then Euclidean metrics are used to measure the distance between still and video images. Identities of still and video images that group as pairs are used as supervision. In the training stage, a joint loss function that measures the Euclidean distance between the predicted features of training pairs and expanding vectors of still images is optimized to minimize the intra-class variation while the inter-class variation is guaranteed due to the large margin of still images. Transferred features are finally learned via the designed convolutional neural network. Experiments are performed on COX face dataset. Experimental results show that our method achieves reliable performance compared with other state-of-the-art methods.

  20. Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks.

    Science.gov (United States)

    Dosovitskiy, Alexey; Fischer, Philipp; Springenberg, Jost Tobias; Riedmiller, Martin; Brox, Thomas

    2016-09-01

    Deep convolutional networks have proven to be very successful in learning task specific features that allow for unprecedented performance on various computer vision tasks. Training of such networks follows mostly the supervised learning paradigm, where sufficiently many input-output pairs are required for training. Acquisition of large training sets is one of the key challenges, when approaching a new task. In this paper, we aim for generic feature learning and present an approach for training a convolutional network using only unlabeled data. To this end, we train the network to discriminate between a set of surrogate classes. Each surrogate class is formed by applying a variety of transformations to a randomly sampled 'seed' image patch. In contrast to supervised network training, the resulting feature representation is not class specific. It rather provides robustness to the transformations that have been applied during training. This generic feature representation allows for classification results that outperform the state of the art for unsupervised learning on several popular datasets (STL-10, CIFAR-10, Caltech-101, Caltech-256). While features learned with our approach cannot compete with class specific features from supervised training on a classification task, we show that they are advantageous on geometric matching problems, where they also outperform the SIFT descriptor.

  1. Real-Time Video Convolutional Face Finder on Embedded Platforms

    Directory of Open Access Journals (Sweden)

    Mamalet Franck

    2007-01-01

    Full Text Available A high-level optimization methodology is applied for implementing the well-known convolutional face finder (CFF algorithm for real-time applications on mobile phones, such as teleconferencing, advanced user interfaces, image indexing, and security access control. CFF is based on a feature extraction and classification technique which consists of a pipeline of convolutions and subsampling operations. The design of embedded systems requires a good trade-off between performance and code size due to the limited amount of available resources. The followed methodology copes with the main drawbacks of the original implementation of CFF such as floating-point computation and memory allocation, in order to allow parallelism exploitation and perform algorithm optimizations. Experimental results show that our embedded face detection system can accurately locate faces with less computational load and memory cost. It runs on a 275 MHz Starcore DSP at 35 QCIF images/s with state-of-the-art detection rates and very low false alarm rates.

  2. Classification of stroke disease using convolutional neural network

    Science.gov (United States)

    Marbun, J. T.; Seniman; Andayani, U.

    2018-03-01

    Stroke is a condition that occurs when the blood supply stop flowing to the brain because of a blockage or a broken blood vessel. A symptoms that happen when experiencing stroke, some of them is a dropped consciousness, disrupted vision and paralyzed body. The general examination is being done to get a picture of the brain part that have stroke using Computerized Tomography (CT) Scan. The image produced from CT will be manually checked and need a proper lighting by doctor to get a type of stroke. That is why it needs a method to classify stroke from CT image automatically. A method proposed in this research is Convolutional Neural Network. CT image of the brain is used as the input for image processing. The stage before classification are image processing (Grayscaling, Scaling, Contrast Limited Adaptive Histogram Equalization, then the image being classified with Convolutional Neural Network. The result then showed that the method significantly conducted was able to be used as a tool to classify stroke disease in order to distinguish the type of stroke from CT image.

  3. 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.

  4. Classifications of Multispectral Colorectal Cancer Tissues Using Convolution Neural Network.

    Science.gov (United States)

    Haj-Hassan, Hawraa; Chaddad, Ahmad; Harkouss, Youssef; Desrosiers, Christian; Toews, Matthew; Tanougast, Camel

    2017-01-01

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

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

    Directory of Open Access Journals (Sweden)

    Hawraa Haj-Hassan

    2017-01-01

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

  6. Thermalnet: a Deep Convolutional Network for Synthetic Thermal Image Generation

    Science.gov (United States)

    Kniaz, V. V.; Gorbatsevich, V. S.; Mizginov, V. A.

    2017-05-01

    Deep convolutional neural networks have dramatically changed the landscape of the modern computer vision. Nowadays methods based on deep neural networks show the best performance among image recognition and object detection algorithms. While polishing of network architectures received a lot of scholar attention, from the practical point of view the preparation of a large image dataset for a successful training of a neural network became one of major challenges. This challenge is particularly profound for image recognition in wavelengths lying outside the visible spectrum. For example no infrared or radar image datasets large enough for successful training of a deep neural network are available to date in public domain. Recent advances of deep neural networks prove that they are also capable to do arbitrary image transformations such as super-resolution image generation, grayscale image colorisation and imitation of style of a given artist. Thus a natural question arise: how could be deep neural networks used for augmentation of existing large image datasets? This paper is focused on the development of the Thermalnet deep convolutional neural network for augmentation of existing large visible image datasets with synthetic thermal images. The Thermalnet network architecture is inspired by colorisation deep neural networks.

  7. Coronary artery calcification (CAC) classification with deep convolutional neural networks

    Science.gov (United States)

    Liu, Xiuming; Wang, Shice; Deng, Yufeng; Chen, Kuan

    2017-03-01

    Coronary artery calcification (CAC) is a typical marker of the coronary artery disease, which is one of the biggest causes of mortality in the U.S. This study evaluates the feasibility of using a deep convolutional neural network (DCNN) to automatically detect CAC in X-ray images. 1768 posteroanterior (PA) view chest X-Ray images from Sichuan Province Peoples Hospital, China were collected retrospectively. Each image is associated with a corresponding diagnostic report written by a trained radiologist (907 normal, 861 diagnosed with CAC). Onequarter of the images were randomly selected as test samples; the rest were used as training samples. DCNN models consisting of 2,4,6 and 8 convolutional layers were designed using blocks of pre-designed CNN layers. Each block was implemented in Theano with Graphics Processing Units (GPU). Human-in-the-loop learning was also performed on a subset of 165 images with framed arteries by trained physicians. The results from the DCNN models were compared to the diagnostic reports. The average diagnostic accuracies for models with 2,4,6,8 layers were 0.85, 0.87, 0.88, and 0.89 respectively. The areas under the curve (AUC) were 0.92, 0.95, 0.95, and 0.96. As the model grows deeper, the AUC or diagnostic accuracies did not have statistically significant changes. The results of this study indicate that DCNN models have promising potential in the field of intelligent medical image diagnosis practice.

  8. Using convolutional decoding to improve time delay and phase estimation in digital communications

    Science.gov (United States)

    Ormesher, Richard C [Albuquerque, NM; Mason, John J [Albuquerque, NM

    2010-01-26

    The time delay and/or phase of a communication signal received by a digital communication receiver can be estimated based on a convolutional decoding operation that the communication receiver performs on the received communication signal. If the original transmitted communication signal has been spread according to a spreading operation, a corresponding despreading operation can be integrated into the convolutional decoding operation.

  9. An upper bound on the number of errors corrected by a convolutional code

    DEFF Research Database (Denmark)

    Justesen, Jørn

    2000-01-01

    The number of errors that a convolutional codes can correct in a segment of the encoded sequence is upper bounded by the number of distinct syndrome sequences of the relevant length.......The number of errors that a convolutional codes can correct in a segment of the encoded sequence is upper bounded by the number of distinct syndrome sequences of the relevant length....

  10. Linear diffusion-wave channel routing using a discrete Hayami convolution method

    Science.gov (United States)

    Li Wang; Joan Q. Wu; William J. Elliot; Fritz R. Feidler; Sergey. Lapin

    2014-01-01

    The convolution of an input with a response function has been widely used in hydrology as a means to solve various problems analytically. Due to the high computation demand in solving the functions using numerical integration, it is often advantageous to use the discrete convolution instead of the integration of the continuous functions. This approach greatly reduces...

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

    Science.gov (United States)

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

    2017-12-01

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

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

    Directory of Open Access Journals (Sweden)

    Ryan Cunningham

    2018-01-01

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

  13. Pulmonary nodule classification in lung cancer screening with three-dimensional convolutional neural networks.

    Science.gov (United States)

    Liu, Shuang; Xie, Yiting; Jirapatnakul, Artit; Reeves, Anthony P

    2017-10-01

    A three-dimensional (3-D) convolutional neural network (CNN) trained from scratch is presented for the classification of pulmonary nodule malignancy from low-dose chest CT scans. Recent approval of lung cancer screening in the United States provides motivation for determining the likelihood of malignancy of pulmonary nodules from the initial CT scan finding to minimize the number of follow-up actions. Classifier ensembles of different combinations of the 3-D CNN and traditional machine learning models based on handcrafted 3-D image features are also explored. The dataset consisting of 326 nodules is constructed with balanced size and class distribution with the malignancy status pathologically confirmed. The results show that both the 3-D CNN single model and the ensemble models with 3-D CNN outperform the respective counterparts constructed using only traditional models. Moreover, complementary information can be learned by the 3-D CNN and the conventional models, which together are combined to construct an ensemble model with statistically superior performance compared with the single traditional model. The performance of the 3-D CNN model demonstrates the potential for improving the lung cancer screening follow-up protocol, which currently mainly depends on the nodule size.

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

    Science.gov (United States)

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

    2017-06-01

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

  15. Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review.

    Science.gov (United States)

    Rawat, Waseem; Wang, Zenghui

    2017-09-01

    Convolutional neural networks (CNNs) have been applied to visual tasks since the late 1980s. However, despite a few scattered applications, they were dormant until the mid-2000s when developments in computing power and the advent of large amounts of labeled data, supplemented by improved algorithms, contributed to their advancement and brought them to the forefront of a neural network renaissance that has seen rapid progression since 2012. In this review, which focuses on the application of CNNs to image classification tasks, we cover their development, from their predecessors up to recent state-of-the-art deep learning systems. Along the way, we analyze (1) their early successes, (2) their role in the deep learning renaissance, (3) selected symbolic works that have contributed to their recent popularity, and (4) several improvement attempts by reviewing contributions and challenges of over 300 publications. We also introduce some of their current trends and remaining challenges.

  16. Convolutional Neural Networks for patient-specific ECG classification.

    Science.gov (United States)

    Kiranyaz, Serkan; Ince, Turker; Hamila, Ridha; Gabbouj, Moncef

    2015-01-01

    We propose a fast and accurate patient-specific electrocardiogram (ECG) classification and monitoring system using an adaptive implementation of 1D Convolutional Neural Networks (CNNs) that can fuse feature extraction and classification into a unified learner. In this way, a dedicated CNN will be trained for each patient by using relatively small common and patient-specific training data and thus it can also be used to classify long ECG records such as Holter registers in a fast and accurate manner. Alternatively, such a solution can conveniently be used for real-time ECG monitoring and early alert system on a light-weight wearable device. The experimental results demonstrate that the proposed system achieves a superior classification performance for the detection of ventricular ectopic beats (VEB) and supraventricular ectopic beats (SVEB).

  17. Towards Better Analysis of Deep Convolutional Neural Networks.

    Science.gov (United States)

    Liu, Mengchen; Shi, Jiaxin; Li, Zhen; Li, Chongxuan; Zhu, Jun; Liu, Shixia

    2017-01-01

    Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification. However, the development of high-quality deep models typically relies on a substantial amount of trial-and-error, as there is still no clear understanding of when and why a deep model works. In this paper, we present a visual analytics approach for better understanding, diagnosing, and refining deep CNNs. We formulate a deep CNN as a directed acyclic graph. Based on this formulation, a hybrid visualization is developed to disclose the multiple facets of each neuron and the interactions between them. In particular, we introduce a hierarchical rectangle packing algorithm and a matrix reordering algorithm to show the derived features of a neuron cluster. We also propose a biclustering-based edge bundling method to reduce visual clutter caused by a large number of connections between neurons. We evaluated our method on a set of CNNs and the results are generally favorable.

  18. 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.

  19. Multiview Convolutional Neural Networks for Multidocument Extractive Summarization.

    Science.gov (United States)

    Zhang, Yong; Er, Meng Joo; Zhao, Rui; Pratama, Mahardhika

    2017-10-01

    Multidocument summarization has gained popularity in many real world applications because vital information can be extracted within a short time. Extractive summarization aims to generate a summary of a document or a set of documents by ranking sentences and the ranking results rely heavily on the quality of sentence features. However, almost all previous algorithms require hand-crafted features for sentence representation. In this paper, we leverage on word embedding to represent sentences so as to avoid the intensive labor in feature engineering. An enhanced convolutional neural networks (CNNs) termed multiview CNNs is successfully developed to obtain the features of sentences and rank sentences jointly. Multiview learning is incorporated into the model to greatly enhance the learning capability of original CNN. We evaluate the generic summarization performance of our proposed method on five Document Understanding Conference datasets. The proposed system outperforms the state-of-the-art approaches and the improvement is statistically significant shown by paired t -test.

  20. Fully convolutional network with cluster for semantic segmentation

    Science.gov (United States)

    Ma, Xiao; Chen, Zhongbi; Zhang, Jianlin

    2018-04-01

    At present, image semantic segmentation technology has been an active research topic for scientists in the field of computer vision and artificial intelligence. Especially, the extensive research of deep neural network in image recognition greatly promotes the development of semantic segmentation. This paper puts forward a method based on fully convolutional network, by cluster algorithm k-means. The cluster algorithm using the image's low-level features and initializing the cluster centers by the super-pixel segmentation is proposed to correct the set of points with low reliability, which are mistakenly classified in great probability, by the set of points with high reliability in each clustering regions. This method refines the segmentation of the target contour and improves the accuracy of the image segmentation.

  1. Taxonomic Classification for Living Organisms Using Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Saed Khawaldeh

    2017-11-01

    Full Text Available Taxonomic classification has a wide-range of applications such as finding out more about evolutionary history. Compared to the estimated number of organisms that nature harbors, humanity does not have a thorough comprehension of to which specific classes they belong. The classification of living organisms can be done in many machine learning techniques. However, in this study, this is performed using convolutional neural networks. Moreover, a DNA encoding technique is incorporated in the algorithm to increase performance and avoid misclassifications. The algorithm proposed outperformed the state of the art algorithms in terms of accuracy and sensitivity, which illustrates a high potential for using it in many other applications in genome analysis.

  2. Plant species classification using deep convolutional neural network

    DEFF Research Database (Denmark)

    Dyrmann, Mads; Karstoft, Henrik; Midtiby, Henrik Skov

    2016-01-01

    Information on which weed species are present within agricultural fields is important for site specific weed management. This paper presents a method that is capable of recognising plant species in colour images by using a convolutional neural network. The network is built from scratch trained...... and tested on a total of 10,413 images containing 22 weed and crop species at early growth stages. These images originate from six different data sets, which have variations with respect to lighting, resolution, and soil type. This includes images taken under controlled conditions with regard to camera...... stabilisation and illumination, and images shot with hand-held mobile phones in fields with changing lighting conditions and different soil types. For these 22 species, the network is able to achieve a classification accuracy of 86.2%....

  3. Feature Fusion Based on Convolutional Neural Network for SAR ATR

    Directory of Open Access Journals (Sweden)

    Chen Shi-Qi

    2017-01-01

    Full Text Available Recent breakthroughs in algorithms related to deep convolutional neural networks (DCNN have stimulated the development of various of signal processing approaches, where the specific application of Automatic Target Recognition (ATR using Synthetic Aperture Radar (SAR data has spurred widely attention. Inspired by the more efficient distributed training such as inception architecture and residual network, a new feature fusion structure which jointly exploits all the merits of each version is proposed to reduce the data dimensions and the complexity of computation. The detailed procedure presented in this paper consists of the fused features, which make the representation of SAR images more distinguishable after the extraction of a set of features from DCNN, followed by a trainable classifier. In particular, the obtained results on the 10-class benchmark data set demonstrate that the presented architecture can achieve remarkable classification performance to the current state-of-the-art methods.

  4. A New Method for Face Recognition Using Convolutional Neural Network

    Directory of Open Access Journals (Sweden)

    Patrik Kamencay

    2017-01-01

    Full Text Available In this paper, the performance of the proposed Convolutional Neural Network (CNN with three well-known image recognition methods such as Principal Component Analysis (PCA, Local Binary Patterns Histograms (LBPH and K–Nearest Neighbour (KNN is tested. In our experiments, the overall recognition accuracy of the PCA, LBPH, KNN and proposed CNN is demonstrated. All the experiments were implemented on the ORL database and the obtained experimental results were shown and evaluated. This face database consists of 400 different subjects (40 classes/ 10 images for each class. The experimental result shows that the LBPH provide better results than PCA and KNN. These experimental results on the ORL database demonstrated the effectiveness of the proposed method for face recognition. For proposed CNN we have obtained a best recognition accuracy of 98.3 %. The proposed method based on CNN outperforms the state of the art methods.

  5. Convolution backprojection image reconstruction for spotlight mode synthetic aperture radar.

    Science.gov (United States)

    Desai, M D; Jenkins, W K

    1992-01-01

    Convolution backprojection (CBP) image reconstruction has been proposed as a means of producing high-resolution synthetic-aperture radar (SAR) images by processing data directly in the polar recording format which is the conventional recording format for spotlight mode SAR. The CBP algorithm filters each projection as it is recorded and then backprojects the ensemble of filtered projections to create the final image in a pixel-by-pixel format. CBP reconstruction produces high-quality images by handling the recorded data directly in polar format. The CBP algorithm requires only 1-D interpolation along the filtered projections to determine the precise values that must be contributed to the backprojection summation from each projection. The algorithm is thus able to produce higher quality images by eliminating the inaccuracies of 2-D interpolation, as well as using all the data recorded in the spectral domain annular sector more effectively. The computational complexity of the CBP algorithm is O(N (3)).

  6. Training strategy for convolutional neural networks in pedestrian gender classification

    Science.gov (United States)

    Ng, Choon-Boon; Tay, Yong-Haur; Goi, Bok-Min

    2017-06-01

    In this work, we studied a strategy for training a convolutional neural network in pedestrian gender classification with limited amount of labeled training data. Unsupervised learning by k-means clustering on pedestrian images was used to learn the filters to initialize the first layer of the network. As a form of pre-training, supervised learning for the related task of pedestrian classification was performed. Finally, the network was fine-tuned for gender classification. We found that this strategy improved the network's generalization ability in gender classification, achieving better test results when compared to random weights initialization and slightly more beneficial than merely initializing the first layer filters by unsupervised learning. This shows that unsupervised learning followed by pre-training with pedestrian images is an effective strategy to learn useful features for pedestrian gender classification.

  7. High Order Tensor Formulation for Convolutional Sparse Coding

    KAUST Repository

    Bibi, Adel Aamer

    2017-12-25

    Convolutional sparse coding (CSC) has gained attention for its successful role as a reconstruction and a classification tool in the computer vision and machine learning community. Current CSC methods can only reconstruct singlefeature 2D images independently. However, learning multidimensional dictionaries and sparse codes for the reconstruction of multi-dimensional data is very important, as it examines correlations among all the data jointly. This provides more capacity for the learned dictionaries to better reconstruct data. In this paper, we propose a generic and novel formulation for the CSC problem that can handle an arbitrary order tensor of data. Backed with experimental results, our proposed formulation can not only tackle applications that are not possible with standard CSC solvers, including colored video reconstruction (5D- tensors), but it also performs favorably in reconstruction with much fewer parameters as compared to naive extensions of standard CSC to multiple features/channels.

  8. XOR-FREE Implementation of Convolutional Encoder for Reconfigurable Hardware

    Directory of Open Access Journals (Sweden)

    Gaurav Purohit

    2016-01-01

    Full Text Available This paper presents a novel XOR-FREE algorithm to implement the convolutional encoder using reconfigurable hardware. The approach completely removes the XOR processing of a chosen nonsystematic, feedforward generator polynomial of larger constraint length. The hardware (HW implementation of new architecture uses Lookup Table (LUT for storing the parity bits. The design implements architectural reconfigurability by modifying the generator polynomial of the same constraint length and code rate to reduce the design complexity. The proposed architecture reduces the dynamic power up to 30% and improves the hardware cost and propagation delay up to 20% and 32%, respectively. The performance of the proposed architecture is validated in MATLAB Simulink and tested on Zynq-7 series FPGA.

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

    Science.gov (United States)

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

    2015-04-01

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

  10. 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%.

  11. Finger vein recognition based on convolutional neural network

    Directory of Open Access Journals (Sweden)

    Meng Gesi

    2017-01-01

    Full Text Available Biometric Authentication Technology has been widely used in this information age. As one of the most important technology of authentication, finger vein recognition attracts our attention because of its high security, reliable accuracy and excellent performance. However, the current finger vein recognition system is difficult to be applied widely because its complicated image pre-processing and not representative feature vectors. To solve this problem, a finger vein recognition method based on the convolution neural network (CNN is proposed in the paper. The image samples are directly input into the CNN model to extract its feature vector so that we can make authentication by comparing the Euclidean distance between these vectors. Finally, the Deep Learning Framework Caffe is adopted to verify this method. The result shows that there are great improvements in both speed and accuracy rate compared to the previous research. And the model has nice robustness in illumination and rotation.

  12. Classification of decays involving variable decay chains with convolutional architectures

    CERN Multimedia

    CERN. Geneva

    2018-01-01

    Vidyo contribution We present a technique to perform classification of decays that exhibit decay chains involving a variable number of particles, which include a broad class of $B$ meson decays sensitive to new physics. The utility of such decays as a probe of the Standard Model is dependent upon accurate determination of the decay rate, which is challenged by the combinatorial background arising in high-multiplicity decay modes. In our model, each particle in the decay event is represented as a fixed-dimensional vector of feature attributes, forming an $n \\times k$ representation of the event, where $n$ is the number of particles in the event and $k$ is the dimensionality of the feature vector. A convolutional architecture is used to capture dependencies between the embedded particle representations and perform the final classification. The proposed model performs outperforms standard machine learning approaches based on Monte Carlo studies across a range of variable final-state decays with the Belle II det...

  13. Network Intrusion Detection through Stacking Dilated Convolutional Autoencoders

    Directory of Open Access Journals (Sweden)

    Yang Yu

    2017-01-01

    Full Text Available Network intrusion detection is one of the most important parts for cyber security to protect computer systems against malicious attacks. With the emergence of numerous sophisticated and new attacks, however, network intrusion detection techniques are facing several significant challenges. The overall objective of this study is to learn useful feature representations automatically and efficiently from large amounts of unlabeled raw network traffic data by using deep learning approaches. We propose a novel network intrusion model by stacking dilated convolutional autoencoders and evaluate our method on two new intrusion detection datasets. Several experiments were carried out to check the effectiveness of our approach. The comparative experimental results demonstrate that the proposed model can achieve considerably high performance which meets the demand of high accuracy and adaptability of network intrusion detection systems (NIDSs. It is quite potential and promising to apply our model in the large-scale and real-world network environments.

  14. Deep learning with convolutional neural network in radiology.

    Science.gov (United States)

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

    2018-04-01

    Deep learning with a convolutional neural network (CNN) is gaining attention recently for its high performance in image recognition. Images themselves can be utilized in a learning process with this technique, and feature extraction in advance of the learning process is not required. Important features can be automatically learned. Thanks to the development of hardware and software in addition to techniques regarding deep learning, application of this technique to radiological images for predicting clinically useful information, such as the detection and the evaluation of lesions, etc., are beginning to be investigated. This article illustrates basic technical knowledge regarding deep learning with CNNs along the actual course (collecting data, implementing CNNs, and training and testing phases). Pitfalls regarding this technique and how to manage them are also illustrated. We also described some advanced topics of deep learning, results of recent clinical studies, and the future directions of clinical application of deep learning techniques.

  15. Automatic Recognition of fMRI-derived Functional Networks using 3D Convolutional Neural Networks.

    Science.gov (United States)

    Zhao, Yu; Dong, Qinglin; Zhang, Shu; Zhang, Wei; Chen, Hanbo; Jiang, Xi; Guo, Lei; Hu, Xintao; Han, Junwei; Liu, Tianming

    2017-06-15

    Current fMRI data modeling techniques such as Independent Component Analysis (ICA) and Sparse Coding methods can effectively reconstruct dozens or hundreds of concurrent interacting functional brain networks simultaneously from the whole brain fMRI signals. However, such reconstructed networks have no correspondences across different subjects. Thus, automatic, effective and accurate classification and recognition of these large numbers of fMRI-derived functional brain networks are very important for subsequent steps of functional brain analysis in cognitive and clinical neuroscience applications. However, this task is still a challenging and open problem due to the tremendous variability of various types of functional brain networks and the presence of various sources of noises. In recognition of the fact that convolutional neural networks (CNN) has superior capability of representing spatial patterns with huge variability and dealing with large noises, in this paper, we design, apply and evaluate a deep 3D CNN framework for automatic, effective and accurate classification and recognition of large number of functional brain networks reconstructed by sparse representation of whole-brain fMRI signals. Our extensive experimental results based on the Human Connectome Project (HCP) fMRI data showed that the proposed deep 3D CNN can effectively and robustly perform functional networks classification and recognition tasks, while maintaining a high tolerance for mistakenly labelled training instances. Our work provides a new deep learning approach for modeling functional connectomes based on fMRI data.

  16. 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.

  17. Very High Resolution Tree Cover Mapping for Continental United States using Deep Convolutional Neural Networks

    Science.gov (United States)

    Ganguly, S.; Kalia, S.; Li, S.; Michaelis, A.; Nemani, R. R.; Saatchi, S.

    2017-12-01

    Uncertainties in input land cover estimates contribute to a significant bias in modeled above gound biomass (AGB) and carbon estimates from satellite-derived data. The resolution of most currently used passive remote sensing products is not sufficient to capture tree canopy cover of less than ca. 10-20 percent, limiting their utility to estimate canopy cover and AGB for trees outside of forest land. In our study, we created a first of its kind Continental United States (CONUS) tree cover map at a spatial resolution of 1-m for the 2010-2012 epoch using the USDA NAIP imagery to address the present uncertainties in AGB estimates. The process involves different tasks including data acquisition/ingestion to pre-processing and running a state-of-art encoder-decoder based deep convolutional neural network (CNN) algorithm for automatically generating a tree/non-tree map for almost a quarter million scenes. The entire processing chain including generation of the largest open source existing aerial/satellite image training database was performed at the NEX supercomputing and storage facility. We believe the resulting forest cover product will substantially contribute to filling the gaps in ongoing carbon and ecological monitoring research and help quantifying the errors and uncertainties in derived products.

  18. A fully convolutional network for weed mapping of unmanned aerial vehicle (UAV) imagery.

    Science.gov (United States)

    Huang, Huasheng; Deng, Jizhong; Lan, Yubin; Yang, Aqing; Deng, Xiaoling; Zhang, Lei

    2018-01-01

    Appropriate Site Specific Weed Management (SSWM) is crucial to ensure the crop yields. Within SSWM of large-scale area, remote sensing is a key technology to provide accurate weed distribution information. Compared with satellite and piloted aircraft remote sensing, unmanned aerial vehicle (UAV) is capable of capturing high spatial resolution imagery, which will provide more detailed information for weed mapping. The objective of this paper is to generate an accurate weed cover map based on UAV imagery. The UAV RGB imagery was collected in 2017 October over the rice field located in South China. The Fully Convolutional Network (FCN) method was proposed for weed mapping of the collected imagery. Transfer learning was used to improve generalization capability, and skip architecture was applied to increase the prediction accuracy. After that, the performance of FCN architecture was compared with Patch_based CNN algorithm and Pixel_based CNN method. Experimental results showed that our FCN method outperformed others, both in terms of accuracy and efficiency. The overall accuracy of the FCN approach was up to 0.935 and the accuracy for weed recognition was 0.883, which means that this algorithm is capable of generating accurate weed cover maps for the evaluated UAV imagery.

  19. Small Field-of-view single-shot EPI-DWI of the prostate: Evaluation of spatially-tailored two-dimensional radiofrequency excitation pulses.

    Science.gov (United States)

    Attenberger, Ulrike I; Rathmann, Nils; Sertdemir, Metin; Riffel, Philipp; Weidner, Anja; Kannengiesser, Stefan; Morelli, John N; Schoenberg, Stefan O; Hausmann, Daniel

    2016-06-01

    Spatially-tailored (RF) excitation pulses in echo-planar imaging (EPI), combined with a decreased FOV in the phase-encoding direction, enable a reduction of k-space acquisition lines, which shortens the echo train length (ETL) and reduces susceptibility artifacts. The purpose of this study was to evaluate the image quality of a zoomed EPI (z-EPI) sequence in diffusion-weighted imaging (DWI) of the prostate in comparison to a conventional single-shot EPI using single-channel (c-EPI1) and multi-channel (c-EPI2) RF excitation, with and without use of an endorectal coil. 33 consecutive patients (mean age: 61 +/- 9 years; mean PSA: 8.67±6.23 ng/ml) with examinations between 10/2012 and 02/2014 were analyzed in this retrospective study. In 26 of 33 patients the initial multiparametric (mp)-MRI was performed on a whole-body 3T scanner (Magnetom Trio, Siemens, Erlangen, Germany) using an endorectal coil (c (conventional)-EPI1). Zoomed-EPI (Z-EPI) examinations of these patients and a complete mp-MRI protocol including c-EPI2 of 7 additional patients were carried out on another 3T wb MR scanner with two-channel dynamic parallel transmit capability (Magnetom Skyra with TimTX TrueShape, Siemens). For z-EPI, the one-dimensional spatially selective RF excitation pulse was replaced by a two-dimensional RF pulse. Degree of image blur and susceptibility artifacts (0=not present to 3= non-diagnostic), maximum image distortion (mm), apparent diffusion coefficient (ADC) values, as well as overall scan preference were evaluated. SNR maps were generated to compare c-EPI2 and z-EPI. Overall image quality of z-EPI was preferred by both readers in all examinations with a single exception. Susceptibility artifacts were rated significantly lower on z-EPI compared to both other methods (z-EPI vs c-EPI1: p<0.01; z-EPI vs c-EPI2: p<0.01) as well as image blur (z-EPI vs c-EPI1: p<0.01; z-EPI vs c-EPI2: p<0.01). Image distortion was not statistically significantly reduced with z-EPI (z-EPI vs c

  20. Radiation effects on histological changes in mouse submandibular glands. Computer analysis of acini, convoluted granular tubules, and granules

    Energy Technology Data Exchange (ETDEWEB)

    Yamada, Masaya; Nasu, Masanori [Nippon Dental Univ., Tokyo (Japan)

    1997-06-01

    A single X-ray dose of 10 Gy and 20 Gy was delivered to the submandibular gland in mice. The submandibular glands were compared 3, 14, 30, 90, 180, and 270 days after irradiation by obtaining the area ratio of both the acini and convoluted granular tubules and the ratio of granules to the acini and convoluted granular tubules by an imaging analyzer. The following results were obtained. An acinar atrophy was observed 14 days after irradiation in the 10 Gy-irradiated group and at both 3 and 14 days in the 20 Gy-irradiated group. The 10 Gy-irradiated group showed a significant decrease in the area ratio of the acini to the submandibular gland at 14 days, but thereafter the values increased to the extent of the non-irradiated control group over 30 days to 270 days. The 20 Gy-irradiated group showed a significant decrease in the area ratio of the acini to the submandibular gland at 3 days. Atrophy of the convoluted granular tubules in the submandibular gland was significantly higher at 14 days in the 10 Gy-irradiated group than in the non-irradiated group, but thereafter returned to the same value as in the non-irradiated group. In the 20 Gy-irradiated group, it was lower at both 3 and 14 days than in the non-irradiated group, but the differences were not significant. The ratio of granules in the 10 Gy irradiated group was the same as that in the non-irradiated group until 30 days after irradiation, but was significantly decreased at 14 days. The ratio of granules to the convoluted granular tubules was lower in the 10 Gy-irradiated group than in the non-irradiated group until 90 days after irradiation but was the same as in the non-irradiated group at 180 and 270 days. It was markedly decreased at both 3 and 14 days after irradiation in the 20 Gy-irradiated group. (author)

  1. Fovea detection in optical coherence tomography using convolutional neural networks

    Science.gov (United States)

    Liefers, Bart; Venhuizen, Freerk G.; Theelen, Thomas; Hoyng, Carel; van Ginneken, Bram; Sánchez, Clara I.

    2017-02-01

    The fovea is an important clinical landmark that is used as a reference for assessing various quantitative measures, such as central retinal thickness or drusen count. In this paper we propose a novel method for automatic detection of the foveal center in Optical Coherence Tomography (OCT) scans. Although the clinician will generally aim to center the OCT scan on the fovea, post-acquisition image processing will give a more accurate estimate of the true location of the foveal center. A Convolutional Neural Network (CNN) was trained on a set of 781 OCT scans that classifies each pixel in the OCT B-scan with a probability of belonging to the fovea. Dilated convolutions were used to obtain a large receptive field, while maintaining pixel-level accuracy. In order to train the network more effectively, negative patches were sampled selectively after each epoch. After CNN classification of the entire OCT volume, the predicted foveal center was chosen as the voxel with maximum output probability, after applying an optimized three-dimensional Gaussian blurring. We evaluate the performance of our method on a data set of 99 OCT scans presenting different stages of Age-related Macular Degeneration (AMD). The fovea was correctly detected in 96:9% of the cases, with a mean distance error of 73 μm(+/-112 μm). This result was comparable to the performance of a second human observer who obtained a mean distance error of 69 μm (+/-94 μm). Experiments showed that the proposed method is accurate and robust even in retinas heavily affected by pathology.

  2. Topology reduction in deep convolutional feature extraction networks

    Science.gov (United States)

    Wiatowski, Thomas; Grohs, Philipp; Bölcskei, Helmut

    2017-08-01

    Deep convolutional neural networks (CNNs) used in practice employ potentially hundreds of layers and 10,000s of nodes. Such network sizes entail significant computational complexity due to the large number of convolutions that need to be carried out; in addition, a large number of parameters needs to be learned and stored. Very deep and wide CNNs may therefore not be well suited to applications operating under severe resource constraints as is the case, e.g., in low-power embedded and mobile platforms. This paper aims at understanding the impact of CNN topology, specifically depth and width, on the network's feature extraction capabilities. We address this question for the class of scattering networks that employ either Weyl-Heisenberg filters or wavelets, the modulus non-linearity, and no pooling. The exponential feature map energy decay results in Wiatowski et al., 2017, are generalized to O(a-N), where an arbitrary decay factor a > 1 can be realized through suitable choice of the Weyl-Heisenberg prototype function or the mother wavelet. We then show how networks of fixed (possibly small) depth N can be designed to guarantee that ((1 - ɛ) · 100)% of the input signal's energy are contained in the feature vector. Based on the notion of operationally significant nodes, we characterize, partly rigorously and partly heuristically, the topology-reducing effects of (effectively) band-limited input signals, band-limited filters, and feature map symmetries. Finally, for networks based on Weyl-Heisenberg filters, we determine the prototype function bandwidth that minimizes - for fixed network depth N - the average number of operationally significant nodes per layer.

  3. Limitations of a convolution method for modeling geometric uncertainties in radiation therapy. I. The effect of shift invariance

    International Nuclear Information System (INIS)

    Craig, Tim; Battista, Jerry; Van Dyk, Jake

    2003-01-01

    Convolution methods have been used to model the effect of geometric uncertainties on dose delivery in radiation therapy. Convolution assumes shift invariance of the dose distribution. Internal inhomogeneities and surface curvature lead to violations of this assumption. The magnitude of the error resulting from violation of shift invariance is not well documented. This issue is addressed by comparing dose distributions calculated using the Convolution method with dose distributions obtained by Direct Simulation. A comparison of conventional Static dose distributions was also made with Direct Simulation. This analysis was performed for phantom geometries and several clinical tumor sites. A modification to the Convolution method to correct for some of the inherent errors is proposed and tested using example phantoms and patients. We refer to this modified method as the Corrected Convolution. The average maximum dose error in the calculated volume (averaged over different beam arrangements in the various phantom examples) was 21% with the Static dose calculation, 9% with Convolution, and reduced to 5% with the Corrected Convolution. The average maximum dose error in the calculated volume (averaged over four clinical examples) was 9% for the Static method, 13% for Convolution, and 3% for Corrected Convolution. While Convolution can provide a superior estimate of the dose delivered when geometric uncertainties are present, the violation of shift invariance can result in substantial errors near the surface of the patient. The proposed Corrected Convolution modification reduces errors near the surface to 3% or less

  4. Development and application of deep convolutional neural network in target detection

    Science.gov (United States)

    Jiang, Xiaowei; Wang, Chunping; Fu, Qiang

    2018-04-01

    With the development of big data and algorithms, deep convolution neural networks with more hidden layers have more powerful feature learning and feature expression ability than traditional machine learning methods, making artificial intelligence surpass human level in many fields. This paper first reviews the development and application of deep convolutional neural networks in the field of object detection in recent years, then briefly summarizes and ponders some existing problems in the current research, and the future development of deep convolutional neural network is prospected.

  5. Application of a Hybrid Model Based on a Convolutional Auto-Encoder and Convolutional Neural Network in Object-Oriented Remote Sensing Classification

    Directory of Open Access Journals (Sweden)

    Wei Cui

    2018-01-01

    Full Text Available Variation in the format and classification requirements for remote sensing data makes establishing a standard remote sensing sample dataset difficult. As a result, few remote sensing deep neural network models have been widely accepted. We propose a hybrid deep neural network model based on a convolutional auto-encoder and a complementary convolutional neural network to solve this problem. The convolutional auto-encoder supports feature extraction and data dimension reduction of remote sensing data. The extracted features are input into the convolutional neural network and subsequently classified. Experimental results show that in the proposed model, the classification accuracy increases from 0.916 to 0.944, compared to a traditional convolutional neural network model; furthermore, the number of training runs is reduced from 40,000 to 22,000, and the number of labelled samples can be reduced by more than half, all while ensuring a classification accuracy of no less than 0.9, which suggests the effectiveness and feasibility of the proposed model.

  6. Deep learning with convolutional neural networks for EEG decoding and visualization.

    Science.gov (United States)

    Schirrmeister, Robin Tibor; Springenberg, Jost Tobias; Fiederer, Lukas Dominique Josef; Glasstetter, Martin; Eggensperger, Katharina; Tangermann, Michael; Hutter, Frank; Burgard, Wolfram; Ball, Tonio

    2017-11-01

    Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end-to-end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end-to-end EEG analysis, but a better understanding of how to design and train ConvNets for end-to-end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task-related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG-based brain mapping. Hum Brain Mapp 38:5391-5420, 2017. © 2017 Wiley Periodicals, Inc. © 2017 The Authors Human Brain Mapping Published by Wiley Periodicals, Inc.

  7. A new convolution algorithm for loss probablity analysis in multiservice networks

    DEFF Research Database (Denmark)

    Huang, Qian; Ko, King-Tim; Iversen, Villy Bæk

    2011-01-01

    Performance analysis in multiservice loss systems generally focuses on accurate and efficient calculation methods for traffic loss probability. Convolution algorithm is one of the existing efficient numerical methods. Exact loss probabilities are obtainable from the convolution algorithm in systems...... where the bandwidth is fully shared by all traffic classes; but not available for systems with trunk reservation, i.e. part of the bandwidth is reserved for a special class of traffic. A proposal known as asymmetric convolution algorithm (ACA) has been made to overcome the deficiency of the convolution...... algorithm. It obtains an approximation of the channel occupancy distribution in multiservice systems with trunk reservation. However, the ACA approximation is only accurate with two traffic flows; increased approximation errors are observed for systems with three or more traffic flows. In this paper, we...

  8. Directional Radiometry and Radiative Transfer: the Convoluted Path From Centuries-old Phenomenology to Physical Optics

    Science.gov (United States)

    Mishchenko, Michael I.

    2014-01-01

    This Essay traces the centuries-long history of the phenomenological disciplines of directional radiometry and radiative transfer in turbid media, discusses their fundamental weaknesses, and outlines the convoluted process of their conversion into legitimate branches of physical optics.

  9. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks

    Science.gov (United States)

    Abdeljaber, Osama; Avci, Onur; Kiranyaz, Serkan; Gabbouj, Moncef; Inman, Daniel J.

    2017-02-01

    Structural health monitoring (SHM) and vibration-based structural damage detection have been a continuous interest for civil, mechanical and aerospace engineers over the decades. Early and meticulous damage detection has always been one of the principal objectives of SHM applications. The performance of a classical damage detection system predominantly depends on the choice of the features and the classifier. While the fixed and hand-crafted features may either be a sub-optimal choice for a particular structure or fail to achieve the same level of performance on another structure, they usually require a large computation power which may hinder their usage for real-time structural damage detection. This paper presents a novel, fast and accurate structural damage detection system using 1D Convolutional Neural Networks (CNNs) that has an inherent adaptive design to fuse both feature extraction and classification blocks into a single and compact learning body. The proposed method performs vibration-based damage detection and localization of the damage in real-time. The advantage of this approach is its ability to extract optimal damage-sensitive features automatically from the raw acceleration signals. Large-scale experiments conducted on a grandstand simulator revealed an outstanding performance and verified the computational efficiency of the proposed real-time damage detection method.

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

    Science.gov (United States)

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

    2017-03-01

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

  11. Convolutional neural networks for transient candidate vetting in large-scale surveys

    Science.gov (United States)

    Gieseke, Fabian; Bloemen, Steven; van den Bogaard, Cas; Heskes, Tom; Kindler, Jonas; Scalzo, Richard A.; Ribeiro, Valério A. R. M.; van Roestel, Jan; Groot, Paul J.; Yuan, Fang; Möller, Anais; Tucker, Brad E.

    2017-12-01

    Current synoptic sky surveys monitor large areas of the sky to find variable and transient astronomical sources. As the number of detections per night at a single telescope easily exceeds several thousand, current detection pipelines make intensive use of machine learning algorithms to classify the detected objects and to filter out the most interesting candidates. A number of upcoming surveys will produce up to three orders of magnitude more data, which renders high-precision classification systems essential to reduce the manual and, hence, expensive vetting by human experts. We present an approach based on convolutional neural networks to discriminate between true astrophysical sources and artefacts in reference-subtracted optical images. We show that relatively simple networks are already competitive with state-of-the-art systems and that their quality can further be improved via slightly deeper networks and additional pre-processing steps - eventually yielding models outperforming state-of-the-art systems. In particular, our best model correctly classifies about 97.3 per cent of all 'real' and 99.7 per cent of all 'bogus' instances on a test set containing 1942 'bogus' and 227 'real' instances in total. Furthermore, the networks considered in this work can also successfully classify these objects at hand without relying on difference images, which might pave the way for future detection pipelines not containing image subtraction steps at all.

  12. Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks.

    Science.gov (United States)

    Kiranyaz, Serkan; Ince, Turker; Gabbouj, Moncef

    2016-03-01

    This paper presents a fast and accurate patient-specific electrocardiogram (ECG) classification and monitoring system. An adaptive implementation of 1-D convolutional neural networks (CNNs) is inherently used to fuse the two major blocks of the ECG classification into a single learning body: feature extraction and classification. Therefore, for each patient, an individual and simple CNN will be trained by using relatively small common and patient-specific training data, and thus, such patient-specific feature extraction ability can further improve the classification performance. Since this also negates the necessity to extract hand-crafted manual features, once a dedicated CNN is trained for a particular patient, it can solely be used to classify possibly long ECG data stream in a fast and accurate manner or alternatively, such a solution can conveniently be used for real-time ECG monitoring and early alert system on a light-weight wearable device. The results over the MIT-BIH arrhythmia benchmark database demonstrate that the proposed solution achieves a superior classification performance than most of the state-of-the-art methods for the detection of ventricular ectopic beats and supraventricular ectopic beats. Besides the speed and computational efficiency achieved, once a dedicated CNN is trained for an individual patient, it can solely be used to classify his/her long ECG records such as Holter registers in a fast and accurate manner. Due to its simple and parameter invariant nature, the proposed system is highly generic, and, thus, applicable to any ECG dataset.

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

    Directory of Open Access Journals (Sweden)

    Evangelia I. Zacharaki

    2017-07-01

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

  14. Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images

    Directory of Open Access Journals (Sweden)

    Lingyan Ran

    2017-06-01

    Full Text Available Vision-based mobile robot navigation is a vibrant area of research with numerous algorithms having been developed, the vast majority of which either belong to the scene-oriented simultaneous localization and mapping (SLAM or fall into the category of robot-oriented lane-detection/trajectory tracking. These methods suffer from high computational cost and require stringent labelling and calibration efforts. To address these challenges, this paper proposes a lightweight robot navigation framework based purely on uncalibrated spherical images. To simplify the orientation estimation, path prediction and improve computational efficiency, the navigation problem is decomposed into a series of classification tasks. To mitigate the adverse effects of insufficient negative samples in the “navigation via classification” task, we introduce the spherical camera for scene capturing, which enables 360° fisheye panorama as training samples and generation of sufficient positive and negative heading directions. The classification is implemented as an end-to-end Convolutional Neural Network (CNN, trained on our proposed Spherical-Navi image dataset, whose category labels can be efficiently collected. This CNN is capable of predicting potential path directions with high confidence levels based on a single, uncalibrated spherical image. Experimental results demonstrate that the proposed framework outperforms competing ones in realistic applications.

  15. Contextual Multi-Scale Region Convolutional 3D Network for Activity Detection

    KAUST Repository

    Bai, Yancheng

    2018-01-28

    Activity detection is a fundamental problem in computer vision. Detecting activities of different temporal scales is particularly challenging. In this paper, we propose the contextual multi-scale region convolutional 3D network (CMS-RC3D) for activity detection. To deal with the inherent temporal scale variability of activity instances, the temporal feature pyramid is used to represent activities of different temporal scales. On each level of the temporal feature pyramid, an activity proposal detector and an activity classifier are learned to detect activities of specific temporal scales. Temporal contextual information is fused into activity classifiers for better recognition. More importantly, the entire model at all levels can be trained end-to-end. Our CMS-RC3D detector can deal with activities at all temporal scale ranges with only a single pass through the backbone network. We test our detector on two public activity detection benchmarks, THUMOS14 and ActivityNet. Extensive experiments show that the proposed CMS-RC3D detector outperforms state-of-the-art methods on THUMOS14 by a substantial margin and achieves comparable results on ActivityNet despite using a shallow feature extractor.

  16. Automated species-level identification and segmentation of planktonic foraminifera using convolutional neural networks

    Science.gov (United States)

    Marchitto, T. M., Jr.; Mitra, R.; Zhong, B.; Ge, Q.; Kanakiya, B.; Lobaton, E.

    2017-12-01

    Identification and picking of foraminifera from sediment samples is often a laborious and repetitive task. Previous attempts to automate this process have met with limited success, but we show that recent advances in machine learning can be brought to bear on the problem. As a `proof of concept' we have developed a system that is capable of recognizing six species of extant planktonic foraminifera that are commonly used in paleoceanographic studies. Our pipeline begins with digital photographs taken under 16 different illuminations using an LED ring, which are then fused into a single 3D image. Labeled image sets were used to train various types of image classification algorithms, and performance on unlabeled image sets was measured in terms of precision (whether IDs are correct) and recall (what fraction of the target species are found). We find that Convolutional Neural Network (CNN) approaches achieve precision and recall values between 80 and 90%, which is similar precision and better recall than human expert performance using the same type of photographs. We have also trained a CNN to segment the 3D images into individual chambers and apertures, which can not only improve identification performance but also automate the measurement of foraminifera for morphometric studies. Given that there are only 35 species of extant planktonic foraminifera larger than 150 μm, we suggest that a fully automated characterization of this assemblage is attainable. This is the first step toward the realization of a foram picking robot.

  17. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

    OpenAIRE

    Milletari, Fausto; Navab, Nassir; Ahmadi, Seyed-Ahmad

    2016-01-01

    Convolutional Neural Networks (CNNs) have been recently employed to solve problems from both the computer vision and medical image analysis fields. Despite their popularity, most approaches are only able to process 2D images while most medical data used in clinical practice consists of 3D volumes. In this work we propose an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network. Our CNN is trained end-to-end on MRI volumes depicting prostate, and learns t...

  18. Segmentation of Drosophila Heart in Optical Coherence Microscopy Images Using Convolutional Neural Networks

    OpenAIRE

    Duan, Lian; Qin, Xi; He, Yuanhao; Sang, Xialin; Pan, Jinda; Xu, Tao; Men, Jing; Tanzi, Rudolph E.; Li, Airong; Ma, Yutao; Zhou, Chao

    2018-01-01

    Convolutional neural networks are powerful tools for image segmentation and classification. Here, we use this method to identify and mark the heart region of Drosophila at different developmental stages in the cross-sectional images acquired by a custom optical coherence microscopy (OCM) system. With our well-trained convolutional neural network model, the heart regions through multiple heartbeat cycles can be marked with an intersection over union (IOU) of ~86%. Various morphological and dyn...

  19. A convolution method for predicting mean treatment dose including organ motion at imaging

    International Nuclear Information System (INIS)

    Booth, J.T.; Zavgorodni, S.F.; Royal Adelaide Hospital, SA

    2000-01-01

    Full text: The random treatment delivery errors (organ motion and set-up error) can be incorporated into the treatment planning software using a convolution method. Mean treatment dose is computed as the convolution of a static dose distribution with a variation kernel. Typically this variation kernel is Gaussian with variance equal to the sum of the organ motion and set-up error variances. We propose a novel variation kernel for the convolution technique that additionally considers the position of the mobile organ in the planning CT image. The systematic error of organ position in the planning CT image can be considered random for each patient over a population. Thus the variance of the variation kernel will equal the sum of treatment delivery variance and organ motion variance at planning for the population of treatments. The kernel is extended to deal with multiple pre-treatment CT scans to improve tumour localisation for planning. Mean treatment doses calculated with the convolution technique are compared to benchmark Monte Carlo (MC) computations. Calculations of mean treatment dose using the convolution technique agreed with MC results for all cases to better than ± 1 Gy in the planning treatment volume for a prescribed 60 Gy treatment. Convolution provides a quick method of incorporating random organ motion (captured in the planning CT image and during treatment delivery) and random set-up errors directly into the dose distribution. Copyright (2000) Australasian College of Physical Scientists and Engineers in Medicine

  20. Application of structured support vector machine backpropagation to a convolutional neural network for human pose estimation.

    Science.gov (United States)

    Witoonchart, Peerajak; Chongstitvatana, Prabhas

    2017-08-01

    In this study, for the first time, we show how to formulate a structured support vector machine (SSVM) as two layers in a convolutional neural network, where the top layer is a loss augmented inference layer and the bottom layer is the normal convolutional layer. We show that a deformable part model can be learned with the proposed structured SVM neural network by backpropagating the error of the deformable part model to the convolutional neural network. The forward propagation calculates the loss augmented inference and the backpropagation calculates the gradient from the loss augmented inference layer to the convolutional layer. Thus, we obtain a new type of convolutional neural network called an Structured SVM convolutional neural network, which we applied to the human pose estimation problem. This new neural network can be used as the final layers in deep learning. Our method jointly learns the structural model parameters and the appearance model parameters. We implemented our method as a new layer in the existing Caffe library. Copyright © 2017 Elsevier Ltd. All rights reserved.

  1. Innervation of the renal proximal convoluted tubule of the rat

    International Nuclear Information System (INIS)

    Barajas, L.; Powers, K.

    1989-01-01

    Experimental data suggest the proximal tubule as a major site of neurogenic influence on tubular function. The functional and anatomical axial heterogeneity of the proximal tubule prompted this study of the distribution of innervation sites along the early, mid, and late proximal convoluted tubule (PCT) of the rat. Serial section autoradiograms, with tritiated norepinephrine serving as a marker for monoaminergic nerves, were used in this study. Freehand clay models and graphic reconstructions of proximal tubules permitted a rough estimation of the location of the innervation sites along the PCT. In the subcapsular nephrons, the early PCT (first third) was devoid of innervation sites with most of the innervation occurring in the mid (middle third) and in the late (last third) PCT. Innervation sites were found in the early PCT in nephrons located deeper in the cortex. In juxtamedullary nephrons, innervation sites could be observed on the PCT as it left the glomerulus. This gradient of PCT innervation can be explained by the different tubulovascular relationships of nephrons at different levels of the cortex. The absence of innervation sites in the early PCT of subcapsular nephrons suggests that any influence of the renal nerves on the early PCT might be due to an effect of neurotransmitter released from renal nerves reaching the early PCT via the interstitium and/or capillaries

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

    Directory of Open Access Journals (Sweden)

    Seungsoo Nam

    2018-01-01

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

  3. Animal Recognition System Based on Convolutional Neural Network

    Directory of Open Access Journals (Sweden)

    Tibor Trnovszky

    2017-01-01

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

  4. Rank-based pooling for deep convolutional neural networks.

    Science.gov (United States)

    Shi, Zenglin; Ye, Yangdong; Wu, Yunpeng

    2016-11-01

    Pooling is a key mechanism in deep convolutional neural networks (CNNs) which helps to achieve translation invariance. Numerous studies, both empirically and theoretically, show that pooling consistently boosts the performance of the CNNs. The conventional pooling methods are operated on activation values. In this work, we alternatively propose rank-based pooling. It is derived from the observations that ranking list is invariant under changes of activation values in a pooling region, and thus rank-based pooling operation may achieve more robust performance. In addition, the reasonable usage of rank can avoid the scale problems encountered by value-based methods. The novel pooling mechanism can be regarded as an instance of weighted pooling where a weighted sum of activations is used to generate the pooling output. This pooling mechanism can also be realized as rank-based average pooling (RAP), rank-based weighted pooling (RWP) and rank-based stochastic pooling (RSP) according to different weighting strategies. As another major contribution, we present a novel criterion to analyze the discriminant ability of various pooling methods, which is heavily under-researched in machine learning and computer vision community. Experimental results on several image benchmarks show that rank-based pooling outperforms the existing pooling methods in classification performance. We further demonstrate better performance on CIFAR datasets by integrating RSP into Network-in-Network. Copyright © 2016 Elsevier Ltd. All rights reserved.

  5. Very Deep Convolutional Neural Networks for Morphologic Classification of Erythrocytes.

    Science.gov (United States)

    Durant, Thomas J S; Olson, Eben M; Schulz, Wade L; Torres, Richard

    2017-12-01

    Morphologic profiling of the erythrocyte population is a widely used and clinically valuable diagnostic modality, but one that relies on a slow manual process associated with significant labor cost and limited reproducibility. Automated profiling of erythrocytes from digital images by capable machine learning approaches would augment the throughput and value of morphologic analysis. To this end, we sought to evaluate the performance of leading implementation strategies for convolutional neural networks (CNNs) when applied to classification of erythrocytes based on morphology. Erythrocytes were manually classified into 1 of 10 classes using a custom-developed Web application. Using recent literature to guide architectural considerations for neural network design, we implemented a "very deep" CNN, consisting of >150 layers, with dense shortcut connections. The final database comprised 3737 labeled cells. Ensemble model predictions on unseen data demonstrated a harmonic mean of recall and precision metrics of 92.70% and 89.39%, respectively. Of the 748 cells in the test set, 23 misclassification errors were made, with a correct classification frequency of 90.60%, represented as a harmonic mean across the 10 morphologic classes. These findings indicate that erythrocyte morphology profiles could be measured with a high degree of accuracy with "very deep" CNNs. Further, these data support future efforts to expand classes and optimize practical performance in a clinical environment as a prelude to full implementation as a clinical tool. © 2017 American Association for Clinical Chemistry.

  6. Shape Synthesis from Sketches via Procedural Models and Convolutional Networks.

    Science.gov (United States)

    Huang, Haibin; Kalogerakis, Evangelos; Yumer, Ersin; Mech, Radomir

    2017-08-01

    Procedural modeling techniques can produce high quality visual content through complex rule sets. However, controlling the outputs of these techniques for design purposes is often notoriously difficult for users due to the large number of parameters involved in these rule sets and also their non-linear relationship to the resulting content. To circumvent this problem, we present a sketch-based approach to procedural modeling. Given an approximate and abstract hand-drawn 2D sketch provided by a user, our algorithm automatically computes a set of procedural model parameters, which in turn yield multiple, detailed output shapes that resemble the user's input sketch. The user can then select an output shape, or further modify the sketch to explore alternative ones. At the heart of our approach is a deep Convolutional Neural Network (CNN) that is trained to map sketches to procedural model parameters. The network is trained by large amounts of automatically generated synthetic line drawings. By using an intuitive medium, i.e., freehand sketching as input, users are set free from manually adjusting procedural model parameters, yet they are still able to create high quality content. We demonstrate the accuracy and efficacy of our method in a variety of procedural modeling scenarios including design of man-made and organic shapes.

  7. A quantum algorithm for Viterbi decoding of classical convolutional codes

    Science.gov (United States)

    Grice, Jon R.; Meyer, David A.

    2015-07-01

    We present a quantum Viterbi algorithm (QVA) with better than classical performance under certain conditions. In this paper, the proposed algorithm is applied to decoding classical convolutional codes, for instance, large constraint length and short decode frames . Other applications of the classical Viterbi algorithm where is large (e.g., speech processing) could experience significant speedup with the QVA. The QVA exploits the fact that the decoding trellis is similar to the butterfly diagram of the fast Fourier transform, with its corresponding fast quantum algorithm. The tensor-product structure of the butterfly diagram corresponds to a quantum superposition that we show can be efficiently prepared. The quantum speedup is possible because the performance of the QVA depends on the fanout (number of possible transitions from any given state in the hidden Markov model) which is in general much less than . The QVA constructs a superposition of states which correspond to all legal paths through the decoding lattice, with phase as a function of the probability of the path being taken given received data. A specialized amplitude amplification procedure is applied one or more times to recover a superposition where the most probable path has a high probability of being measured.

  8. Automatic detection and classification of leukocytes using convolutional neural networks.

    Science.gov (United States)

    Zhao, Jianwei; Zhang, Minshu; Zhou, Zhenghua; Chu, Jianjun; Cao, Feilong

    2017-08-01

    The detection and classification of white blood cells (WBCs, also known as Leukocytes) is a hot issue because of its important applications in disease diagnosis. Nowadays the morphological analysis of blood cells is operated manually by skilled operators, which results in some drawbacks such as slowness of the analysis, a non-standard accuracy, and the dependence on the operator's skills. Although there have been many papers studying the detection of WBCs or classification of WBCs independently, few papers consider them together. This paper proposes an automatic detection and classification system for WBCs from peripheral blood images. It firstly proposes an algorithm to detect WBCs from the microscope images based on the simple relation of colors R, B and morphological operation. Then a granularity feature (pairwise rotation invariant co-occurrence local binary pattern, PRICoLBP feature) and SVM are applied to classify eosinophil and basophil from other WBCs firstly. Lastly, convolution neural networks are used to extract features in high level from WBCs automatically, and a random forest is applied to these features to recognize the other three kinds of WBCs: neutrophil, monocyte and lymphocyte. Some detection experiments on Cellavison database and ALL-IDB database show that our proposed detection method has better effect almost than iterative threshold method with less cost time, and some classification experiments show that our proposed classification method has better accuracy almost than some other methods.

  9. HEp-2 Cell Image Classification With Deep Convolutional Neural Networks.

    Science.gov (United States)

    Gao, Zhimin; Wang, Lei; Zhou, Luping; Zhang, Jianjia

    2017-03-01

    Efficient Human Epithelial-2 cell image classification can facilitate the diagnosis of many autoimmune diseases. This paper proposes an automatic framework for this classification task, by utilizing the deep convolutional neural networks (CNNs) which have recently attracted intensive attention in visual recognition. In addition to describing the proposed classification framework, this paper elaborates several interesting observations and findings obtained by our investigation. They include the important factors that impact network design and training, the role of rotation-based data augmentation for cell images, the effectiveness of cell image masks for classification, and the adaptability of the CNN-based classification system across different datasets. Extensive experimental study is conducted to verify the above findings and compares the proposed framework with the well-established image classification models in the literature. The results on benchmark datasets demonstrate that 1) the proposed framework can effectively outperform existing models by properly applying data augmentation, 2) our CNN-based framework has excellent adaptability across different datasets, which is highly desirable for cell image classification under varying laboratory settings. Our system is ranked high in the cell image classification competition hosted by ICPR 2014.

  10. Deblurring adaptive optics retinal images using deep convolutional neural networks.

    Science.gov (United States)

    Fei, Xiao; Zhao, Junlei; Zhao, Haoxin; Yun, Dai; Zhang, Yudong

    2017-12-01

    The adaptive optics (AO) can be used to compensate for ocular aberrations to achieve near diffraction limited high-resolution retinal images. However, many factors such as the limited aberration measurement and correction accuracy with AO, intraocular scatter, imaging noise and so on will degrade the quality of retinal images. Image post processing is an indispensable and economical method to make up for the limitation of AO retinal imaging procedure. In this paper, we proposed a deep learning method to restore the degraded retinal images for the first time. The method directly learned an end-to-end mapping between the blurred and restored retinal images. The mapping was represented as a deep convolutional neural network that was trained to output high-quality images directly from blurry inputs without any preprocessing. This network was validated on synthetically generated retinal images as well as real AO retinal images. The assessment of the restored retinal images demonstrated that the image quality had been significantly improved.

  11. On the Relationship between Visual Attributes and Convolutional Networks

    KAUST Repository

    Castillo, Victor

    2015-06-02

    One of the cornerstone principles of deep models is their abstraction capacity, i.e. their ability to learn abstract concepts from ‘simpler’ ones. Through extensive experiments, we characterize the nature of the relationship between abstract concepts (specifically objects in images) learned by popular and high performing convolutional networks (conv-nets) and established mid-level representations used in computer vision (specifically semantic visual attributes). We focus on attributes due to their impact on several applications, such as object description, retrieval and mining, and active (and zero-shot) learning. Among the findings we uncover, we show empirical evidence of the existence of Attribute Centric Nodes (ACNs) within a conv-net, which is trained to recognize objects (not attributes) in images. These special conv-net nodes (1) collectively encode information pertinent to visual attribute representation and discrimination, (2) are unevenly and sparsely distribution across all layers of the conv-net, and (3) play an important role in conv-net based object recognition.

  12. Bone age detection via carpogram analysis using convolutional neural networks

    Science.gov (United States)

    Torres, Felipe; Bravo, María. Alejandra; Salinas, Emmanuel; Triana, Gustavo; Arbeláez, Pablo

    2017-11-01

    Bone age assessment is a critical factor for determining delayed development in children, which can be a sign of pathologies such as endocrine diseases, growth abnormalities, chromosomal, neurological and congenital disorders among others. In this paper we present BoneNet, a methodology to assess automatically the skeletal maturity state in pediatric patients based on Convolutional Neural Networks. We train and evaluate our algorithm on a database of X-Ray images provided by the hospital Fundacion Santa Fe de Bogot ´ a with around 1500 images of patients between the ages 1 to 18. ´ We compare two different architectures to classify the given data in order to explore the generality of our method. To accomplish this, we define multiple binary age assessment problems, dividing the data by bone age and differentiating the patients by their gender. Thus, exploring several parameters, we develop BoneNet. Our approach is holistic, efficient, and modular, since it is possible for the specialists to use all the networks combined to determine how is the skeletal maturity of a patient. BoneNet achieves over 90% accuracy for most of the critical age thresholds, when differentiating the images between over or under a given age.

  13. Transfer Learning with Convolutional Neural Networks for SAR Ship Recognition

    Science.gov (United States)

    Zhang, Di; Liu, Jia; Heng, Wang; Ren, Kaijun; Song, Junqiang

    2018-03-01

    Ship recognition is the backbone of marine surveillance systems. Recent deep learning methods, e.g. Convolutional Neural Networks (CNNs), have shown high performance for optical images. Learning CNNs, however, requires a number of annotated samples to estimate numerous model parameters, which prevents its application to Synthetic Aperture Radar (SAR) images due to the limited annotated training samples. Transfer learning has been a promising technique for applications with limited data. To this end, a novel SAR ship recognition method based on CNNs with transfer learning has been developed. In this work, we firstly start with a CNNs model that has been trained in advance on Moving and Stationary Target Acquisition and Recognition (MSTAR) database. Next, based on the knowledge gained from this image recognition task, we fine-tune the CNNs on a new task to recognize three types of ships in the OpenSARShip database. The experimental results show that our proposed approach can obviously increase the recognition rate comparing with the result of merely applying CNNs. In addition, compared to existing methods, the proposed method proves to be very competitive and can learn discriminative features directly from training data instead of requiring pre-specification or pre-selection manually.

  14. 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%.

  15. Classification of breast cancer cytological specimen using convolutional neural network

    Science.gov (United States)

    Żejmo, Michał; Kowal, Marek; Korbicz, Józef; Monczak, Roman

    2017-01-01

    The paper presents a deep learning approach for automatic classification of breast tumors based on fine needle cytology. The main aim of the system is to distinguish benign from malignant cases based on microscopic images. Experiment was carried out on cytological samples derived from 50 patients (25 benign cases + 25 malignant cases) diagnosed in Regional Hospital in Zielona Góra. To classify microscopic images, we used convolutional neural networks (CNN) of two types: GoogLeNet and AlexNet. Due to the very large size of images of cytological specimen (on average 200000 × 100000 pixels), they were divided into smaller patches of size 256 × 256 pixels. Breast cancer classification usually is based on morphometric features of nuclei. Therefore, training and validation patches were selected using Support Vector Machine (SVM) so that suitable amount of cell material was depicted. Neural classifiers were tuned using GPU accelerated implementation of gradient descent algorithm. Training error was defined as a cross-entropy classification loss. Classification accuracy was defined as the percentage ratio of successfully classified validation patches to the total number of validation patches. The best accuracy rate of 83% was obtained by GoogLeNet model. We observed that more misclassified patches belong to malignant cases.

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

    Science.gov (United States)

    Tian, Qianyu; Gao, Nan; Zhang, Zonghua

    2018-01-01

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

  17. A deep convolutional neural network for recognizing foods

    Science.gov (United States)

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

    2015-12-01

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

  18. 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.

  19. Semantic Segmentation of Indoor Point Clouds Using Convolutional Neural Network

    Science.gov (United States)

    Babacan, K.; Chen, L.; Sohn, G.

    2017-11-01

    As Building Information Modelling (BIM) thrives, geometry becomes no longer sufficient; an ever increasing variety of semantic information is needed to express an indoor model adequately. On the other hand, for the existing buildings, automatically generating semantically enriched BIM from point cloud data is in its infancy. The previous research to enhance the semantic content rely on frameworks in which some specific rules and/or features that are hand coded by specialists. These methods immanently lack generalization and easily break in different circumstances. On this account, a generalized framework is urgently needed to automatically and accurately generate semantic information. Therefore we propose to employ deep learning techniques for the semantic segmentation of point clouds into meaningful parts. More specifically, we build a volumetric data representation in order to efficiently generate the high number of training samples needed to initiate a convolutional neural network architecture. The feedforward propagation is used in such a way to perform the classification in voxel level for achieving semantic segmentation. The method is tested both for a mobile laser scanner point cloud, and a larger scale synthetically generated data. We also demonstrate a case study, in which our method can be effectively used to leverage the extraction of planar surfaces in challenging cluttered indoor environments.

  20. Building Extraction from Remote Sensing Data Using Fully Convolutional Networks

    Science.gov (United States)

    Bittner, K.; Cui, S.; Reinartz, P.

    2017-05-01

    Building detection and footprint extraction are highly demanded for many remote sensing applications. Though most previous works have shown promising results, the automatic extraction of building footprints still remains a nontrivial topic, especially in complex urban areas. Recently developed extensions of the CNN framework made it possible to perform dense pixel-wise classification of input images. Based on these abilities we propose a methodology, which automatically generates a full resolution binary building mask out of a Digital Surface Model (DSM) using a Fully Convolution Network (FCN) architecture. The advantage of using the depth information is that it provides geometrical silhouettes and allows a better separation of buildings from background as well as through its invariance to illumination and color variations. The proposed framework has mainly two steps. Firstly, the FCN is trained on a large set of patches consisting of normalized DSM (nDSM) as inputs and available ground truth building mask as target outputs. Secondly, the generated predictions from FCN are viewed as unary terms for a Fully connected Conditional Random Fields (FCRF), which enables us to create a final binary building mask. A series of experiments demonstrate that our methodology is able to extract accurate building footprints which are close to the buildings original shapes to a high degree. The quantitative and qualitative analysis show the significant improvements of the results in contrast to the multy-layer fully connected network from our previous work.

  1. BUILDING EXTRACTION FROM REMOTE SENSING DATA USING FULLY CONVOLUTIONAL NETWORKS

    Directory of Open Access Journals (Sweden)

    K. Bittner

    2017-05-01

    Full Text Available Building detection and footprint extraction are highly demanded for many remote sensing applications. Though most previous works have shown promising results, the automatic extraction of building footprints still remains a nontrivial topic, especially in complex urban areas. Recently developed extensions of the CNN framework made it possible to perform dense pixel-wise classification of input images. Based on these abilities we propose a methodology, which automatically generates a full resolution binary building mask out of a Digital Surface Model (DSM using a Fully Convolution Network (FCN architecture. The advantage of using the depth information is that it provides geometrical silhouettes and allows a better separation of buildings from background as well as through its invariance to illumination and color variations. The proposed framework has mainly two steps. Firstly, the FCN is trained on a large set of patches consisting of normalized DSM (nDSM as inputs and available ground truth building mask as target outputs. Secondly, the generated predictions from FCN are viewed as unary terms for a Fully connected Conditional Random Fields (FCRF, which enables us to create a final binary building mask. A series of experiments demonstrate that our methodology is able to extract accurate building footprints which are close to the buildings original shapes to a high degree. The quantitative and qualitative analysis show the significant improvements of the results in contrast to the multy-layer fully connected network from our previous work.

  2. Multi-resolution Convolution Methodology for ICP Waveform Morphology Analysis.

    Science.gov (United States)

    Shaw, Martin; Piper, Ian; Hawthorne, Christopher

    2016-01-01

    Intracranial pressure (ICP) monitoring is a key clinical tool in the assessment and treatment of patients in neurointensive care. ICP morphology analysis can be useful in the classification of waveform features.A methodology for the decomposition of an ICP signal into clinically relevant dimensions has been devised that allows the identification of important ICP waveform types. It has three main components. First, multi-resolution convolution analysis is used for the main signal decomposition. Then, an impulse function is created, with multiple parameters, that can represent any form in the signal under analysis. Finally, a simple, localised optimisation technique is used to find morphologies of interest in the decomposed data.A pilot application of this methodology using a simple signal has been performed. This has shown that the technique works with performance receiver operator characteristic area under the curve values for each of the waveform types: plateau wave, B wave and high and low compliance states of 0.936, 0.694, 0.676 and 0.698, respectively.This is a novel technique that showed some promise during the pilot analysis. However, it requires further optimisation to become a usable clinical tool for the automated analysis of ICP signals.

  3. Fully automated quantitative cephalometry using convolutional neural networks.

    Science.gov (United States)

    Arık, Sercan Ö; Ibragimov, Bulat; Xing, Lei

    2017-01-01

    Quantitative cephalometry plays an essential role in clinical diagnosis, treatment, and surgery. Development of fully automated techniques for these procedures is important to enable consistently accurate computerized analyses. We study the application of deep convolutional neural networks (CNNs) for fully automated quantitative cephalometry for the first time. The proposed framework utilizes CNNs for detection of landmarks that describe the anatomy of the depicted patient and yield quantitative estimation of pathologies in the jaws and skull base regions. We use a publicly available cephalometric x-ray image dataset to train CNNs for recognition of landmark appearance patterns. CNNs are trained to output probabilistic estimations of different landmark locations, which are combined using a shape-based model. We evaluate the overall framework on the test set and compare with other proposed techniques. We use the estimated landmark locations to assess anatomically relevant measurements and classify them into different anatomical types. Overall, our results demonstrate high anatomical landmark detection accuracy ([Formula: see text] to 2% higher success detection rate for a 2-mm range compared with the top benchmarks in the literature) and high anatomical type classification accuracy ([Formula: see text] average classification accuracy for test set). We demonstrate that CNNs, which merely input raw image patches, are promising for accurate quantitative cephalometry.

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

    Science.gov (United States)

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

    2015-03-19

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

  5. Image reconstruction in computerized tomography using the convolution method

    International Nuclear Information System (INIS)

    Oliveira Rebelo, A.M. de.

    1984-03-01

    In the present work an algoritin was derived, using the analytical convolution method (filtered back-projection) for two-dimensional or three-dimensional image reconstruction in computerized tomography applied to non-destructive testing and to the medical use. This mathematical model is based on the analytical Fourier transform method for image reconstruction. This model consists of a discontinuous system formed by an NxN array of cells (pixels). The attenuation in the object under study of a colimated gamma ray beam has been determined for various positions and incidence angles (projections) in terms of the interaction of the beam with the intercepted pixels. The contribution of each pixel to beam attenuation was determined using the weight function W ij which was used for simulated tests. Simulated tests using standard objects with attenuation coefficients in the range of 0,2 to 0,7 cm -1 were carried out using cell arrays of up to 25x25. One application was carried out in the medical area simulating image reconstruction of an arm phantom with attenuation coefficients in the range of 0,2 to 0,5 cm -1 using cell arrays of 41x41. The simulated results show that, in objects with a great number of interfaces and great variations of attenuation coefficients at these interfaces, a good reconstruction is obtained with the number of projections equal to the reconstruction matrix dimension. A good reconstruction is otherwise obtained with fewer projections. (author) [pt

  6. Image aesthetic quality evaluation using convolution neural network embedded learning

    Science.gov (United States)

    Li, Yu-xin; Pu, Yuan-yuan; Xu, Dan; Qian, Wen-hua; Wang, Li-peng

    2017-11-01

    A way of embedded learning convolution neural network (ELCNN) based on the image content is proposed to evaluate the image aesthetic quality in this paper. Our approach can not only solve the problem of small-scale data but also score the image aesthetic quality. First, we chose Alexnet and VGG_S to compare for confirming which is more suitable for this image aesthetic quality evaluation task. Second, to further boost the image aesthetic quality classification performance, we employ the image content to train aesthetic quality classification models. But the training samples become smaller and only using once fine-tuning cannot make full use of the small-scale data set. Third, to solve the problem in second step, a way of using twice fine-tuning continually based on the aesthetic quality label and content label respective is proposed, the classification probability of the trained CNN models is used to evaluate the image aesthetic quality. The experiments are carried on the small-scale data set of Photo Quality. The experiment results show that the classification accuracy rates of our approach are higher than the existing image aesthetic quality evaluation approaches.

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

    Directory of Open Access Journals (Sweden)

    Miki UENO

    2017-03-01

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

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

    Directory of Open Access Journals (Sweden)

    Martin Längkvist

    2016-04-01

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

  9. Classification of breast cancer histology images using Convolutional Neural Networks.

    Science.gov (United States)

    Araújo, Teresa; Aresta, Guilherme; Castro, Eduardo; Rouco, José; Aguiar, Paulo; Eloy, Catarina; Polónia, António; Campilho, Aurélio

    2017-01-01

    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%.

  10. Noisy Ocular Recognition Based on Three Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Min Beom Lee

    2017-12-01

    Full Text Available In recent years, the iris recognition system has been gaining increasing acceptance for applications such as access control and smartphone security. When the images of the iris are obtained under unconstrained conditions, an issue of undermined quality is caused by optical and motion blur, off-angle view (the user’s eyes looking somewhere else, not into the front of the camera, specular reflection (SR and other factors. Such noisy iris images increase intra-individual variations and, as a result, reduce the accuracy of iris recognition. A typical iris recognition system requires a near-infrared (NIR illuminator along with an NIR camera, which are larger and more expensive than fingerprint recognition equipment. Hence, many studies have proposed methods of using iris images captured by a visible light camera without the need for an additional illuminator. In this research, we propose a new recognition method for noisy iris and ocular images by using one iris and two periocular regions, based on three convolutional neural networks (CNNs. Experiments were conducted by using the noisy iris challenge evaluation-part II (NICE.II training dataset (selected from the university of Beira iris (UBIRIS.v2 database, mobile iris challenge evaluation (MICHE database, and institute of automation of Chinese academy of sciences (CASIA-Iris-Distance database. As a result, the method proposed by this study outperformed previous methods.

  11. A parametric texture model based on deep convolutional features closely matches texture appearance for humans.

    Science.gov (United States)

    Wallis, Thomas S A; Funke, Christina M; Ecker, Alexander S; Gatys, Leon A; Wichmann, Felix A; Bethge, Matthias

    2017-10-01

    Our visual environment is full of texture-"stuff" like cloth, bark, or gravel as distinct from "things" like dresses, trees, or paths-and humans are adept at perceiving subtle variations in material properties. To investigate image features important for texture perception, we psychophysically compare a recent parametric model of texture appearance (convolutional neural network [CNN] model) that uses the features encoded by a deep CNN (VGG-19) with two other models: the venerable Portilla and Simoncelli model and an extension of the CNN model in which the power spectrum is additionally matched. Observers discriminated model-generated textures from original natural textures in a spatial three-alternative oddity paradigm under two viewing conditions: when test patches were briefly presented to the near-periphery ("parafoveal") and when observers were able to make eye movements to all three patches ("inspection"). Under parafoveal viewing, observers were unable to discriminate 10 of 12 original images from CNN model images, and remarkably, the simpler Portilla and Simoncelli model performed slightly better than the CNN model (11 textures). Under foveal inspection, matching CNN features captured appearance substantially better than the Portilla and Simoncelli model (nine compared to four textures), and including the power spectrum improved appearance matching for two of the three remaining textures. None of the models we test here could produce indiscriminable images for one of the 12 textures under the inspection condition. While deep CNN (VGG-19) features can often be used to synthesize textures that humans cannot discriminate from natural textures, there is currently no uniformly best model for all textures and viewing conditions.

  12. Application of deep learning in determining IR precipitation occurrence: a Convolutional Neural Network model

    Science.gov (United States)

    Wang, C.; Hong, Y.

    2017-12-01

    Infrared (IR) information from Geostationary satellites can be used to retrieve precipitation at pretty high spatiotemporal resolutions. Traditional artificial intelligence (AI) methodologies, such as artificial neural networks (ANN), have been designed to build the relationship between near-surface precipitation and manually derived IR features in products including PERSIANN and PERSIANN-CCS. This study builds an automatic precipitation detection model based on IR data using Convolutional Neural Network (CNN) which is implemented by the newly developed deep learning framework, Caffe. The model judges whether there is rain or no rain at pixel level. Compared with traditional ANN methods, CNN can extract features inside the raw data automatically and thoroughly. In this study, IR data from GOES satellites and precipitation estimates from the next generation QPE (Q2) over the central United States are used as inputs and labels, respectively. The whole datasets during the study period (June to August in 2012) are randomly partitioned to three sub datasets (train, validation and test) to establish the model at the spatial resolution of 0.08°×0.08° and the temporal resolution of 1 hour. The experiments show great improvements of CNN in rain identification compared to the widely used IR-based precipitation product, i.e., PERSIANN-CCS. The overall gain in performance is about 30% for critical success index (CSI), 32% for probability of detection (POD) and 12% for false alarm ratio (FAR). Compared to other recent IR-based precipitation retrieval methods (e.g., PERSIANN-DL developed by University of California Irvine), our model is simpler with less parameters, but achieves equally or even better results. CNN has been applied in computer vision domain successfully, and our results prove the method is suitable for IR precipitation detection. Future studies can expand the application of CNN from precipitation occurrence decision to precipitation amount retrieval.

  13. Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation.

    Science.gov (United States)

    Wang, Shuo; Zhou, Mu; Liu, Zaiyi; Liu, Zhenyu; Gu, Dongsheng; Zang, Yali; Dong, Di; Gevaert, Olivier; Tian, Jie

    2017-08-01

    Accurate lung nodule segmentation from computed tomography (CT) images is of great importance for image-driven lung cancer analysis. However, the heterogeneity of lung nodules and the presence of similar visual characteristics between nodules and their surroundings make it difficult for robust nodule segmentation. In this study, we propose a data-driven model, termed the Central Focused Convolutional Neural Networks (CF-CNN), to segment lung nodules from heterogeneous CT images. Our approach combines two key insights: 1) the proposed model captures a diverse set of nodule-sensitive features from both 3-D and 2-D CT images simultaneously; 2) when classifying an image voxel, the effects of its neighbor voxels can vary according to their spatial locations. We describe this phenomenon by proposing a novel central pooling layer retaining much information on voxel patch center, followed by a multi-scale patch learning strategy. Moreover, we design a weighted sampling to facilitate the model training, where training samples are selected according to their degree of segmentation difficulty. The proposed method has been extensively evaluated on the public LIDC dataset including 893 nodules and an independent dataset with 74 nodules from Guangdong General Hospital (GDGH). We showed that CF-CNN achieved superior segmentation performance with average dice scores of 82.15% and 80.02% for the two datasets respectively. Moreover, we compared our results with the inter-radiologists consistency on LIDC dataset, showing a difference in average dice score of only 1.98%. Copyright © 2017. Published by Elsevier B.V.

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

    Science.gov (United States)

    Vang, Yeeleng S; Xie, Xiaohui

    2017-09-01

    Many biological processes are governed by protein-ligand interactions. One such example is the recognition of self and non-self cells by the immune system. This immune response process is regulated by the major histocompatibility complex (MHC) protein which is encoded by the human leukocyte antigen (HLA) complex. Understanding the binding potential between MHC and peptides can lead to the design of more potent, peptide-based vaccines and immunotherapies for infectious autoimmune diseases. We apply machine learning techniques from the natural language processing (NLP) domain to address the task of MHC-peptide binding prediction. More specifically, we introduce a new distributed representation of amino acids, name HLA-Vec, that can be used for a variety of downstream proteomic machine learning tasks. We then propose a deep convolutional neural network architecture, name HLA-CNN, for the task of HLA class I-peptide binding prediction. Experimental results show combining the new distributed representation with our HLA-CNN architecture achieves state-of-the-art results in the majority of the latest two Immune Epitope Database (IEDB) weekly automated benchmark datasets. We further apply our model to predict binding on the human genome and identify 15 genes with potential for self binding. Codes to generate the HLA-Vec and HLA-CNN are publicly available at: https://github.com/uci-cbcl/HLA-bind . xhx@ics.uci.edu. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com

  15. Convolutional neural networks for prostate cancer recurrence prediction

    Science.gov (United States)

    Kumar, Neeraj; Verma, Ruchika; Arora, Ashish; Kumar, Abhay; Gupta, Sanchit; Sethi, Amit; Gann, Peter H.

    2017-03-01

    Accurate prediction of the treatment outcome is important for cancer treatment planning. We present an approach to predict prostate cancer (PCa) recurrence after radical prostatectomy using tissue images. We used a cohort whose case vs. control (recurrent vs. non-recurrent) status had been determined using post-treatment follow up. Further, to aid the development of novel biomarkers of PCa recurrence, cases and controls were paired based on matching of other predictive clinical variables such as Gleason grade, stage, age, and race. For this cohort, tissue resection microarray with up to four cores per patient was available. The proposed approach is based on deep learning, and its novelty lies in the use of two separate convolutional neural networks (CNNs) - one to detect individual nuclei even in the crowded areas, and the other to classify them. To detect nuclear centers in an image, the first CNN predicts distance transform of the underlying (but unknown) multi-nuclear map from the input HE image. The second CNN classifies the patches centered at nuclear centers into those belonging to cases or controls. Voting across patches extracted from image(s) of a patient yields the probability of recurrence for the patient. The proposed approach gave 0.81 AUC for a sample of 30 recurrent cases and 30 non-recurrent controls, after being trained on an independent set of 80 case-controls pairs. If validated further, such an approach might help in choosing between a combination of treatment options such as active surveillance, radical prostatectomy, radiation, and hormone therapy. It can also generalize to the prediction of treatment outcomes in other cancers.

  16. Classifying Radio Galaxies with the Convolutional Neural Network

    Energy Technology Data Exchange (ETDEWEB)

    Aniyan, A. K.; Thorat, K. [Department of Physics and Electronics, Rhodes University, Grahamstown (South Africa)

    2017-06-01

    We present the application of a deep machine learning technique to classify radio images of extended sources on a morphological basis using convolutional neural networks (CNN). In this study, we have taken the case of the Fanaroff–Riley (FR) class of radio galaxies as well as radio galaxies with bent-tailed morphology. We have used archival data from the Very Large Array (VLA)—Faint Images of the Radio Sky at Twenty Centimeters survey and existing visually classified samples available in the literature to train a neural network for morphological classification of these categories of radio sources. Our training sample size for each of these categories is ∼200 sources, which has been augmented by rotated versions of the same. Our study shows that CNNs can classify images of the FRI and FRII and bent-tailed radio galaxies with high accuracy (maximum precision at 95%) using well-defined samples and a “fusion classifier,” which combines the results of binary classifications, while allowing for a mechanism to find sources with unusual morphologies. The individual precision is highest for bent-tailed radio galaxies at 95% and is 91% and 75% for the FRI and FRII classes, respectively, whereas the recall is highest for FRI and FRIIs at 91% each, while the bent-tailed class has a recall of 79%. These results show that our results are comparable to that of manual classification, while being much faster. Finally, we discuss the computational and data-related challenges associated with the morphological classification of radio galaxies with CNNs.

  17. Classifying Radio Galaxies with the Convolutional Neural Network

    Science.gov (United States)

    Aniyan, A. K.; Thorat, K.

    2017-06-01

    We present the application of a deep machine learning technique to classify radio images of extended sources on a morphological basis using convolutional neural networks (CNN). In this study, we have taken the case of the Fanaroff-Riley (FR) class of radio galaxies as well as radio galaxies with bent-tailed morphology. We have used archival data from the Very Large Array (VLA)—Faint Images of the Radio Sky at Twenty Centimeters survey and existing visually classified samples available in the literature to train a neural network for morphological classification of these categories of radio sources. Our training sample size for each of these categories is ˜200 sources, which has been augmented by rotated versions of the same. Our study shows that CNNs can classify images of the FRI and FRII and bent-tailed radio galaxies with high accuracy (maximum precision at 95%) using well-defined samples and a “fusion classifier,” which combines the results of binary classifications, while allowing for a mechanism to find sources with unusual morphologies. The individual precision is highest for bent-tailed radio galaxies at 95% and is 91% and 75% for the FRI and FRII classes, respectively, whereas the recall is highest for FRI and FRIIs at 91% each, while the bent-tailed class has a recall of 79%. These results show that our results are comparable to that of manual classification, while being much faster. Finally, we discuss the computational and data-related challenges associated with the morphological classification of radio galaxies with CNNs.

  18. Classifying Radio Galaxies with the Convolutional Neural Network

    International Nuclear Information System (INIS)

    Aniyan, A. K.; Thorat, K.

    2017-01-01

    We present the application of a deep machine learning technique to classify radio images of extended sources on a morphological basis using convolutional neural networks (CNN). In this study, we have taken the case of the Fanaroff–Riley (FR) class of radio galaxies as well as radio galaxies with bent-tailed morphology. We have used archival data from the Very Large Array (VLA)—Faint Images of the Radio Sky at Twenty Centimeters survey and existing visually classified samples available in the literature to train a neural network for morphological classification of these categories of radio sources. Our training sample size for each of these categories is ∼200 sources, which has been augmented by rotated versions of the same. Our study shows that CNNs can classify images of the FRI and FRII and bent-tailed radio galaxies with high accuracy (maximum precision at 95%) using well-defined samples and a “fusion classifier,” which combines the results of binary classifications, while allowing for a mechanism to find sources with unusual morphologies. The individual precision is highest for bent-tailed radio galaxies at 95% and is 91% and 75% for the FRI and FRII classes, respectively, whereas the recall is highest for FRI and FRIIs at 91% each, while the bent-tailed class has a recall of 79%. These results show that our results are comparable to that of manual classification, while being much faster. Finally, we discuss the computational and data-related challenges associated with the morphological classification of radio galaxies with CNNs.

  19. Automatic Seismic-Event Classification with Convolutional Neural Networks.

    Science.gov (United States)

    Bueno Rodriguez, A.; Titos Luzón, M.; Garcia Martinez, L.; Benitez, C.; Ibáñez, J. M.

    2017-12-01

    Active volcanoes exhibit a wide range of seismic signals, providing vast amounts of unlabelled volcano-seismic data that can be analyzed through the lens of artificial intelligence. However, obtaining high-quality labelled data is time-consuming and expensive. Deep neural networks can process data in their raw form, compute high-level features and provide a better representation of the input data distribution. These systems can be deployed to classify seismic data at scale, enhance current early-warning systems and build extensive seismic catalogs. In this research, we aim to classify spectrograms from seven different seismic events registered at "Volcán de Fuego" (Colima, Mexico), during four eruptive periods. Our approach is based on convolutional neural networks (CNNs), a sub-type of deep neural networks that can exploit grid structure from the data. Volcano-seismic signals can be mapped into a grid-like structure using the spectrogram: a representation of the temporal evolution in terms of time and frequency. Spectrograms were computed from the data using Hamming windows with 4 seconds length, 2.5 seconds overlapping and 128 points FFT resolution. Results are compared to deep neural networks, random forest and SVMs. Experiments show that CNNs can exploit temporal and frequency information, attaining a classification accuracy of 93%, similar to deep networks 91% but outperforming SVM and random forest. These results empirically show that CNNs are powerful models to classify a wide range of volcano-seismic signals, and achieve good generalization. Furthermore, volcano-seismic spectrograms contains useful discriminative information for the CNN, as higher layers of the network combine high-level features computed for each frequency band, helping to detect simultaneous events in time. Being at the intersection of deep learning and geophysics, this research enables future studies of how CNNs can be used in volcano monitoring to accurately determine the detection and

  20. Dermoscopic Image Segmentation via Multistage Fully Convolutional Networks.

    Science.gov (United States)

    Bi, Lei; Kim, Jinman; Ahn, Euijoon; Kumar, Ashnil; Fulham, Michael; Feng, Dagan

    2017-09-01

    Segmentation of skin lesions is an important step in the automated computer aided diagnosis of melanoma. However, existing segmentation methods have a tendency to over- or under-segment the lesions and perform poorly when the lesions have fuzzy boundaries, low contrast with the background, inhomogeneous textures, or contain artifacts. Furthermore, the performance of these methods are heavily reliant on the appropriate tuning of a large number of parameters as well as the use of effective preprocessing techniques, such as illumination correction and hair removal. We propose to leverage fully convolutional networks (FCNs) to automatically segment the skin lesions. FCNs are a neural network architecture that achieves object detection by hierarchically combining low-level appearance information with high-level semantic information. We address the issue of FCN producing coarse segmentation boundaries for challenging skin lesions (e.g., those with fuzzy boundaries and/or low difference in the textures between the foreground and the background) through a multistage segmentation approach in which multiple FCNs learn complementary visual characteristics of different skin lesions; early stage FCNs learn coarse appearance and localization information while late-stage FCNs learn the subtle characteristics of the lesion boundaries. We also introduce a new parallel integration method to combine the complementary information derived from individual segmentation stages to achieve a final segmentation result that has accurate localization and well-defined lesion boundaries, even for the most challenging skin lesions. We achieved an average Dice coefficient of 91.18% on the ISBI 2016 Skin Lesion Challenge dataset and 90.66% on the PH2 dataset. Our extensive experimental results on two well-established public benchmark datasets demonstrate that our method is more effective than other state-of-the-art methods for skin lesion segmentation.

  1. Convoluted laminations in waterlain sediments:three examples from Eastern Canada and their relevance to neotectonics

    International Nuclear Information System (INIS)

    Macdougall, D.A.; Broster, B.E.

    1995-10-01

    The catastrophic disturbance of unconsolidated sediment produces a wide variety of deformation structures, particularly if the sediment is water-saturated at the time of disturbance. Layers, originally deposited as sub-horizontal, can become stretched or distended resulting in convoluted laminations. Faulted beds, slumped units, or dewatering structures may also occur in association with the disturbance. Convolutions were studied in five examples of Pleistocene glaciomarine deltas, at three locations in eastern Canada. Results from this study indicate that similar structures were produced in each of the sediment deposits, but some are especially common in specific facies (e.g. bottomset, foreset, topset). However, the particular cause of the convolutions varied within each deposit, and the origin could be better assessed when studied in relationship to other structures. None of the convolutions found could be attributed, categorically, to a seismic origin. However, neither could a seismic origin be dismissed for structures associated with convolutions occurring in deposits at: St. George, New Brunswick; Economy Point, Nova Scotia; and Lanark, Ontario. Of these deposits, the deformed structures at Economy Point are apparently post-glacial. (author). 24 refs., 58 figs

  2. Rapid broad area search and detection of Chinese surface-to-air missile sites using deep convolutional neural networks

    Science.gov (United States)

    Marcum, Richard A.; Davis, Curt H.; Scott, Grant J.; Nivin, Tyler W.

    2017-10-01

    We evaluated how deep convolutional neural networks (DCNN) could assist in the labor-intensive process of human visual searches for objects of interest in high-resolution imagery over large areas of the Earth's surface. Various DCNN were trained and tested using fewer than 100 positive training examples (China only) from a worldwide surface-to-air-missile (SAM) site dataset. A ResNet-101 DCNN achieved a 98.2% average accuracy for the China SAM site data. The ResNet-101 DCNN was used to process ˜19.6 M image chips over a large study area in southeastern China. DCNN chip detections (˜9300) were postprocessed with a spatial clustering algorithm to produce a ranked list of ˜2100 candidate SAM site locations. The combination of DCNN processing and spatial clustering effectively reduced the search area by ˜660X (0.15% of the DCNN-processed land area). An efficient web interface was used to facilitate a rapid serial human review of the candidate SAM sites in the China study area. Four novice imagery analysts with no prior imagery analysis experience were able to complete a DCNN-assisted SAM site search in an average time of ˜42 min. This search was ˜81X faster than a traditional visual search over an equivalent land area of ˜88,640 km2 while achieving nearly identical statistical accuracy (˜90% F1).

  3. Automated Detection of Fronts using a Deep Learning Convolutional Neural Network

    Science.gov (United States)

    Biard, J. C.; Kunkel, K.; Racah, E.

    2017-12-01

    A deeper understanding of climate model simulations and the future effects of global warming on extreme weather can be attained through direct analyses of the phenomena that produce weather. Such analyses require these phenomena to be identified in automatic, unbiased, and comprehensive ways. Atmospheric fronts are centrally important weather phenomena because of the variety of significant weather events, such as thunderstorms, directly associated with them. In current operational meteorology, fronts are identified and drawn visually based on the approximate spatial coincidence of a number of quasi-linear localized features - a trough (relative minimum) in air pressure in combination with gradients in air temperature and/or humidity and a shift in wind, and are categorized as cold, warm, stationary, or occluded, with each type exhibiting somewhat different characteristics. Fronts are extended in space with one dimension much larger than the other (often represented by complex curved lines), which poses a significant challenge for automated approaches. We addressed this challenge by using a Deep Learning Convolutional Neural Network (CNN) to automatically identify and classify fronts. The CNN was trained using a "truth" dataset of front locations identified by National Weather Service meteorologists as part of operational 3-hourly surface analyses. The input to the CNN is a set of 5 gridded fields of surface atmospheric variables, including 2m temperature, 2m specific humidity, surface pressure, and the two components of the 10m horizontal wind velocity vector at 3-hr resolution. The output is a set of feature maps containing the per - grid cell probabilities for the presence of the 4 front types. The CNN was trained on a subset of the data and then used to produce front probabilities for each 3-hr time snapshot over a 14-year period covering the continental United States and some adjacent areas. The total frequencies of fronts derived from the CNN outputs matches

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

    Science.gov (United States)

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

    2018-01-15

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

  5. Efficient 3D Watermarked Video Communication with Chaotic Interleaving, Convolution Coding, and LMMSE Equalization

    Science.gov (United States)

    El-Shafai, W.; El-Bakary, E. M.; El-Rabaie, S.; Zahran, O.; El-Halawany, M.; Abd El-Samie, F. E.

    2017-06-01

    Three-Dimensional Multi-View Video (3D-MVV) transmission over wireless networks suffers from Macro-Blocks losses due to either packet dropping or fading-motivated bit errors. Thus, the robust performance of 3D-MVV transmission schemes over wireless channels becomes a recent considerable hot research issue due to the restricted resources and the presence of severe channel errors. The 3D-MVV is composed of multiple video streams shot by several cameras around a single object, simultaneously. Therefore, it is an urgent task to achieve high compression ratios to meet future bandwidth constraints. Unfortunately, the highly-compressed 3D-MVV data becomes more sensitive and vulnerable to packet losses, especially in the case of heavy channel faults. Thus, in this paper, we suggest the application of a chaotic Baker interleaving approach with equalization and convolution coding for efficient Singular Value Decomposition (SVD) watermarked 3D-MVV transmission over an Orthogonal Frequency Division Multiplexing wireless system. Rayleigh fading and Additive White Gaussian Noise are considered in the real scenario of 3D-MVV transmission. The SVD watermarked 3D-MVV frames are primarily converted to their luminance and chrominance components, which are then converted to binary data format. After that, chaotic interleaving is applied prior to the modulation process. It is used to reduce the channel effects on the transmitted bit streams and it also adds a degree of encryption to the transmitted 3D-MVV frames. To test the performance of the proposed framework; several simulation experiments on different SVD watermarked 3D-MVV frames have been executed. The experimental results show that the received SVD watermarked 3D-MVV frames still have high Peak Signal-to-Noise Ratios and watermark extraction is possible in the proposed framework.

  6. KIKI-net: cross-domain convolutional neural networks for reconstructing undersampled magnetic resonance images.

    Science.gov (United States)

    Eo, Taejoon; Jun, Yohan; Kim, Taeseong; Jang, Jinseong; Lee, Ho-Joon; Hwang, Dosik

    2018-04-06

    To demonstrate accurate MR image reconstruction from undersampled k-space data using cross-domain convolutional neural networks (CNNs) METHODS: Cross-domain CNNs consist of 3 components: (1) a deep CNN operating on the k-space (KCNN), (2) a deep CNN operating on an image domain (ICNN), and (3) an interleaved data consistency operations. These components are alternately applied, and each CNN is trained to minimize the loss between the reconstructed and corresponding fully sampled k-spaces. The final reconstructed image is obtained by forward-propagating the undersampled k-space data through the entire network. Performances of K-net (KCNN with inverse Fourier transform), I-net (ICNN with interleaved data consistency), and various combinations of the 2 different networks were tested. The test results indicated that K-net and I-net have different advantages/disadvantages in terms of tissue-structure restoration. Consequently, the combination of K-net and I-net is superior to single-domain CNNs. Three MR data sets, the T 2 fluid-attenuated inversion recovery (T 2 FLAIR) set from the Alzheimer's Disease Neuroimaging Initiative and 2 data sets acquired at our local institute (T 2 FLAIR and T 1 weighted), were used to evaluate the performance of 7 conventional reconstruction algorithms and the proposed cross-domain CNNs, which hereafter is referred to as KIKI-net. KIKI-net outperforms conventional algorithms with mean improvements of 2.29 dB in peak SNR and 0.031 in structure similarity. KIKI-net exhibits superior performance over state-of-the-art conventional algorithms in terms of restoring tissue structures and removing aliasing artifacts. The results demonstrate that KIKI-net is applicable up to a reduction factor of 3 to 4 based on variable-density Cartesian undersampling. © 2018 International Society for Magnetic Resonance in Medicine.

  7. 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

  8. Convolutional Neural Networks for Earthquake Detection and Location of Seismicity in Central Oklahoma

    Science.gov (United States)

    Perol, T.; Gharbi, M.; Denolle, M.

    2016-12-01

    Induced seismicity is characterized by localized activity of small-scale and moderate-magnitude earthquakes. Poor instrumental coverage limits the accuracy of traditional techniques for earthquake detection and localization. Currently, the most effective approach to detect new (and smaller) events is the so-called template matching method. It matches events' waveforms against previously-seen waveform templates. This restricts the search to events that are collocated with the cataloged events. We propose an alternative method, which we called ConvNetQuake, that leverages recent advances in convolutional neural networks for pattern recognition and classification. Once trained on a dataset of 3-component seismograms, ConvNetQuake learns a bank of finite impulse response filters that can discriminate seismic events against noise. First, we compare our algorithm to template matching on synthetic data. We generate synthetic waveforms by adding randomly scaled copies of a single 3-component template at random temporal offsets over a Gaussian noise floor. While the accuracy of ConvNetQuake is slightly lower than that of template matching, it has the advantage of a more compact non-linear representation that can detect new events that were not in the training set. Second, we cluster the Guthrie earthquakes using a Multivariate Gaussian Mixture Model (MGMM) based on the Oklahoma Geological Survey (OGS) catalog and sample a few events from each cluster. We proceed as before and construct synthetic seismograms with the additional information of the events' location. We now train our algorithm to discriminate events from the noise and, jointly, to estimate the probability than the event belongs to a particular cluster. Using the MGMM, we produce maps of the continuous probability distribution of event location. Finally, we apply ConvNetQuake to the Guthrie sequence by training it on data from February 15th, 2014 to August, 31th 2014 using the known cataloged seismicity provided

  9. Efficient organ localization using multi-label convolutional neural networks in thorax-abdomen CT scans

    Science.gov (United States)

    Efrain Humpire-Mamani, Gabriel; Arindra Adiyoso Setio, Arnaud; van Ginneken, Bram; Jacobs, Colin

    2018-04-01

    Automatic localization of organs and other structures in medical images is an important preprocessing step that can improve and speed up other algorithms such as organ segmentation, lesion detection, and registration. This work presents an efficient method for simultaneous localization of multiple structures in 3D thorax-abdomen CT scans. Our approach predicts the location of multiple structures using a single multi-label convolutional neural network for each orthogonal view. Each network takes extra slices around the current slice as input to provide extra context. A sigmoid layer is used to perform multi-label classification. The output of the three networks is subsequently combined to compute a 3D bounding box for each structure. We used our approach to locate 11 structures of interest. The neural network was trained and evaluated on a large set of 1884 thorax-abdomen CT scans from patients undergoing oncological workup. Reference bounding boxes were annotated by human observers. The performance of our method was evaluated by computing the wall distance to the reference bounding boxes. The bounding boxes annotated by the first human observer were used as the reference standard for the test set. Using the best configuration, we obtained an average wall distance of 3.20~+/-~7.33 mm in the test set. The second human observer achieved 1.23~+/-~3.39 mm. For all structures, the results were better than those reported in previously published studies. In conclusion, we proposed an efficient method for the accurate localization of multiple organs. Our method uses multiple slices as input to provide more context around the slice under analysis, and we have shown that this improves performance. This method can easily be adapted to handle more organs.

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

    Science.gov (United States)

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

    2017-06-01

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

  11. Convolutional Neural Network-Based Human Detection in Nighttime Images Using Visible Light Camera Sensors

    Directory of Open Access Journals (Sweden)

    Jong Hyun Kim

    2017-05-01

    Full Text Available Because intelligent surveillance systems have recently undergone rapid growth, research on accurately detecting humans in videos captured at a long distance is growing in importance. The existing research using visible light cameras has mainly focused on methods of human detection for daytime hours when there is outside light, but human detection during nighttime hours when there is no outside light is difficult. Thus, methods that employ additional near-infrared (NIR illuminators and NIR cameras or thermal cameras have been used. However, in the case of NIR illuminators, there are limitations in terms of the illumination angle and distance. There are also difficulties because the illuminator power must be adaptively adjusted depending on whether the object is close or far away. In the case of thermal cameras, their cost is still high, which makes it difficult to install and use them in a variety of places. Because of this, research has been conducted on nighttime human detection using visible light cameras, but this has focused on objects at a short distance in an indoor environment or the use of video-based methods to capture multiple images and process them, which causes problems related to the increase in the processing time. To resolve these problems, this paper presents a method that uses a single image captured at night on a visible light camera to detect humans in a variety of environments based on a convolutional neural network. Experimental results using a self-constructed Dongguk night-time human detection database (DNHD-DB1 and two open databases (Korea advanced institute of science and technology (KAIST and computer vision center (CVC databases, as well as high-accuracy human detection in a variety of environments, show that the method has excellent performance compared to existing methods.

  12. Space-Time Convolutional Codes over Finite Fields and Rings for Systems with Large Diversity Order

    Directory of Open Access Journals (Sweden)

    B. F. Uchôa-Filho

    2008-06-01

    Full Text Available We propose a convolutional encoder over the finite ring of integers modulo pk,ℤpk, where p is a prime number and k is any positive integer, to generate a space-time convolutional code (STCC. Under this structure, we prove three properties related to the generator matrix of the convolutional code that can be used to simplify the code search procedure for STCCs over ℤpk. Some STCCs of large diversity order (≥4 designed under the trace criterion for n=2,3, and 4 transmit antennas are presented for various PSK signal constellations.

  13. Fast Automatic Airport Detection in Remote Sensing Images Using Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Fen Chen

    2018-03-01

    Full Text Available Fast and automatic detection of airports from remote sensing images is useful for many military and civilian applications. In this paper, a fast automatic detection method is proposed to detect airports from remote sensing images based on convolutional neural networks using the Faster R-CNN algorithm. This method first applies a convolutional neural network to generate candidate airport regions. Based on the features extracted from these proposals, it then uses another convolutional neural network to perform airport detection. By taking the typical elongated linear geometric shape of airports into consideration, some specific improvements to the method are proposed. These approaches successfully improve the quality of positive samples and achieve a better accuracy in the final detection results. Experimental results on an airport dataset, Landsat 8 images, and a Gaofen-1 satellite scene demonstrate the effectiveness and efficiency of the proposed method.

  14. Design and Implementation of Behavior Recognition System Based on Convolutional Neural Network

    Directory of Open Access Journals (Sweden)

    Yu Bo

    2017-01-01

    Full Text Available We build a set of human behavior recognition system based on the convolution neural network constructed for the specific human behavior in public places. Firstly, video of human behavior data set will be segmented into images, then we process the images by the method of background subtraction to extract moving foreground characters of body. Secondly, the training data sets are trained into the designed convolution neural network, and the depth learning network is constructed by stochastic gradient descent. Finally, the various behaviors of samples are classified and identified with the obtained network model, and the recognition results are compared with the current mainstream methods. The result show that the convolution neural network can study human behavior model automatically and identify human’s behaviors without any manually annotated trainings.

  15. Fast vision through frameless event-based sensing and convolutional processing: application to texture recognition.

    Science.gov (United States)

    Perez-Carrasco, Jose Antonio; Acha, Begona; Serrano, Carmen; Camunas-Mesa, Luis; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabe

    2010-04-01

    Address-event representation (AER) is an emergent hardware technology which shows a high potential for providing in the near future a solid technological substrate for emulating brain-like processing structures. When used for vision, AER sensors and processors are not restricted to capturing and processing still image frames, as in commercial frame-based video technology, but sense and process visual information in a pixel-level event-based frameless manner. As a result, vision processing is practically simultaneous to vision sensing, since there is no need to wait for sensing full frames. Also, only meaningful information is sensed, communicated, and processed. Of special interest for brain-like vision processing are some already reported AER convolutional chips, which have revealed a very high computational throughput as well as the possibility of assembling large convolutional neural networks in a modular fashion. It is expected that in a near future we may witness the appearance of large scale convolutional neural networks with hundreds or thousands of individual modules. In the meantime, some research is needed to investigate how to assemble and configure such large scale convolutional networks for specific applications. In this paper, we analyze AER spiking convolutional neural networks for texture recognition hardware applications. Based on the performance figures of already available individual AER convolution chips, we emulate large scale networks using a custom made event-based behavioral simulator. We have developed a new event-based processing architecture that emulates with AER hardware Manjunath's frame-based feature recognition software algorithm, and have analyzed its performance using our behavioral simulator. Recognition rate performance is not degraded. However, regarding speed, we show that recognition can be achieved before an equivalent frame is fully sensed and transmitted.

  16. Multi-task transfer learning deep convolutional neural network: application to computer-aided diagnosis of breast cancer on mammograms

    Science.gov (United States)

    Samala, Ravi K.; Chan, Heang-Ping; Hadjiiski, Lubomir M.; Helvie, Mark A.; Cha, Kenny H.; Richter, Caleb D.

    2017-12-01

    Transfer learning in deep convolutional neural networks (DCNNs) is an important step in its application to medical imaging tasks. We propose a multi-task transfer learning DCNN with the aim of translating the ‘knowledge’ learned from non-medical images to medical diagnostic tasks through supervised training and increasing the generalization capabilities of DCNNs by simultaneously learning auxiliary tasks. We studied this approach in an important application: classification of malignant and benign breast masses. With Institutional Review Board (IRB) approval, digitized screen-film mammograms (SFMs) and digital mammograms (DMs) were collected from our patient files and additional SFMs were obtained from the Digital Database for Screening Mammography. The data set consisted of 2242 views with 2454 masses (1057 malignant, 1397 benign). In single-task transfer learning, the DCNN was trained and tested on SFMs. In multi-task transfer learning, SFMs and DMs were used to train the DCNN, which was then tested on SFMs. N-fold cross-validation with the training set was used for training and parameter optimization. On the independent test set, the multi-task transfer learning DCNN was found to have significantly (p  =  0.007) higher performance compared to the single-task transfer learning DCNN. This study demonstrates that multi-task transfer learning may be an effective approach for training DCNN in medical imaging applications when training samples from a single modality are limited.

  17. Meda Inequality for Rearrangements of the Convolution on the Heisenberg Group and Some Applications

    Directory of Open Access Journals (Sweden)

    V. S. Guliyev

    2009-01-01

    Full Text Available The Meda inequality for rearrangements of the convolution operator on the Heisenberg group ℍn is proved. By using the Meda inequality, an O'Neil-type inequality for the convolution is obtained. As applications of these results, some sufficient and necessary conditions for the boundedness of the fractional maximal operator MΩ,α and fractional integral operator IΩ,α with rough kernels in the spaces Lp(ℍn are found. Finally, we give some comments on the extension of our results to the case of homogeneous groups.

  18. Alternate symbol inversion for improved symbol synchronization in convolutionally coded systems

    Science.gov (United States)

    Simon, M. K.; Smith, J. G.

    1980-01-01

    Inverting alternate symbols of the encoder output of a convolutionally coded system provides sufficient density of symbol transitions to guarantee adequate symbol synchronizer performance, a guarantee otherwise lacking. Although alternate symbol inversion may increase or decrease the average transition density, depending on the data source model, it produces a maximum number of contiguous symbols without transition for a particular class of convolutional codes, independent of the data source model. Further, this maximum is sufficiently small to guarantee acceptable symbol synchronizer performance for typical applications. Subsequent inversion of alternate detected symbols permits proper decoding.

  19. Convolution theory of a phase transition between hadronic and quark matter and the characteristic multiplicity distributions

    Energy Technology Data Exchange (ETDEWEB)

    Nakamura, E.R. (Physics Department, Fukui Prefectural College, 97-Ohata, Fukui 910, Japan (JP)); Kudo, K. (Department of Applied Physics, Fukui University, Fukui 910, (Japan))

    1990-01-01

    A convolution form of the free energy density of the thermodynamic system of hadrons is given on the basis of the convolution formula which yields a general form of the statistical bootstrap equation. It is shown that in the thermodynamic limit this free energy density has a typical singular form, which presents a phase transition between hadronic and quark matter, in the same way as magnetic transitions and classical liquid-gas transitions. The characteristic multiplicity distribution is predicted as a signal of the disordered state.

  20. Investigation of dosimetric differences between the TMR 10 and convolution algorithm for Gamma Knife stereotactic radiosurgery.

    Science.gov (United States)

    Rojas-Villabona, Alvaro; Kitchen, Neil; Paddick, Ian

    2016-11-08

    Since its inception, doses applied using Gamma Knife Radiosurgery (GKR) have been calculated using a simple TMR algorithm, which assumes the patient's head is of even density, the same as water. This results in a significant approximation of the dose delivered by the Gamma Knife. We investigated how GKR dose cal-culations varied when using a new convolution algorithm clinically available for GKR planning that takes into account density variations in the head compared with the established calculation algorithm. Fifty-five patients undergoing GKR and harboring 85 lesions were voluntarily and prospectively enrolled into the study. Their clinical treatment plans were created and delivered using TMR 10, but were then recalculated using the density correction algorithm. Dosimetric differences between the planning algorithms were noted. Beam on time (BOT), which is directly proportional to dose, was the main value investigated. Changes of mean and maximum dose to organs at risk (OAR) were also assessed. Phantom studies were performed to investigate the effect of frame and pin materials on dose calculation using the convolution algorithm. Convolution yielded a mean increase in BOT of 7.4% (3.6%-11.6%). However, approximately 1.5% of this amount was due to the head contour being derived from the CT scans, as opposed to measurements using the Skull Scaling Instrument with TMR. Dose to the cochlea calculated with the convolution algorithm was approximately 7% lower than with the TMR 10 algorithm. No significant difference in relative dose distribution was noted and CT artifact typically caused by the stereotactic frame, glue embolization material or different fixation pin materials did not systematically affect convolu-tion isodoses. Nonetheless, substantial error was introduced to the convolution calculation in one target located exactly in the area of major CT artifact caused by a fixation pin. Inhomogeneity correction using the convolution algorithm results in a

  1. A Fast Numerical Method for Max-Convolution and the Application to Efficient Max-Product Inference in Bayesian Networks.

    Science.gov (United States)

    Serang, Oliver

    2015-08-01

    Observations depending on sums of random variables are common throughout many fields; however, no efficient solution is currently known for performing max-product inference on these sums of general discrete distributions (max-product inference can be used to obtain maximum a posteriori estimates). The limiting step to max-product inference is the max-convolution problem (sometimes presented in log-transformed form and denoted as "infimal convolution," "min-convolution," or "convolution on the tropical semiring"), for which no O(k log(k)) method is currently known. Presented here is an O(k log(k)) numerical method for estimating the max-convolution of two nonnegative vectors (e.g., two probability mass functions), where k is the length of the larger vector. This numerical max-convolution method is then demonstrated by performing fast max-product inference on a convolution tree, a data structure for performing fast inference given information on the sum of n discrete random variables in O(nk log(nk)log(n)) steps (where each random variable has an arbitrary prior distribution on k contiguous possible states). The numerical max-convolution method can be applied to specialized classes of hidden Markov models to reduce the runtime of computing the Viterbi path from nk(2) to nk log(k), and has potential application to the all-pairs shortest paths problem.

  2. Efficient document-image super-resolution using convolutional ...

    Indian Academy of Sciences (India)

    Experiments performed by us using optical character recognizers (OCRs) show that the character level accuracy of the OCR reduces significantly with decrease in the spatial resolution of document images. There are real life scenarios, where high-resolution (HR) images are not available, where it is desirable toenhance ...

  3. Two projects in theoretical neuroscience: A convolution-based metric for neural membrane potentials and a combinatorial connectionist semantic network method

    Science.gov (United States)

    Evans, Garrett Nolan

    In this work, I present two projects that both contribute to the aim of discovering how intelligence manifests in the brain. The first project is a method for analyzing recorded neural signals, which takes the form of a convolution-based metric on neural membrane potential recordings. Relying only on integral and algebraic operations, the metric compares the timing and number of spikes within recordings as well as the recordings' subthreshold features: summarizing differences in these with a single "distance" between the recordings. Like van Rossum's (2001) metric for spike trains, the metric is based on a convolution operation that it performs on the input data. The kernel used for the convolution is carefully chosen such that it produces a desirable frequency space response and, unlike van Rossum's kernel, causes the metric to be first order both in differences between nearby spike times and in differences between same-time membrane potential values: an important trait. The second project is a combinatorial syntax method for connectionist semantic network encoding. Combinatorial syntax has been a point on which those who support a symbol-processing view of intelligent processing and those who favor a connectionist view have had difficulty seeing eye-to-eye. Symbol-processing theorists have persuasively argued that combinatorial syntax is necessary for certain intelligent mental operations, such as reasoning by analogy. Connectionists have focused on the versatility and adaptability offered by self-organizing networks of simple processing units. With this project, I show that there is a way to reconcile the two perspectives and to ascribe a combinatorial syntax to a connectionist network. The critical principle is to interpret nodes, or units, in the connectionist network as bound integrations of the interpretations for nodes that they share links with. Nodes need not correspond exactly to neurons and may correspond instead to distributed sets, or assemblies, of

  4. Automated Detection of Cloud and Cloud Shadow in Single-Date Landsat Imagery Using Neural Networks and Spatial Post-Processing

    Directory of Open Access Journals (Sweden)

    M. Joseph Hughes

    2014-05-01

    Full Text Available The use of Landsat data to answer ecological questions is greatly increased by the effective removal of cloud and cloud shadow from satellite images. We develop a novel algorithm to identify and classify clouds and cloud shadow, SPARCS: Spatial Procedures for Automated Removal of Cloud and Shadow. The method uses a neural network approach to determine cloud, cloud shadow, water, snow/ice and clear sky classification memberships of each pixel in a Landsat scene. It then applies a series of spatial procedures to resolve pixels with ambiguous membership by using information, such as the membership values of neighboring pixels and an estimate of cloud shadow locations from cloud and solar geometry. In a comparison with FMask, a high-quality cloud and cloud shadow classification algorithm currently available, SPARCS performs favorably, with substantially lower omission errors for cloud shadow (8.0% and 3.2%, only slightly higher omission errors for clouds (0.9% and 1.3%, respectively and fewer errors of commission (2.6% and 0.3%. Additionally, SPARCS provides a measure of uncertainty in its classification that can be exploited by other algorithms that require clear sky pixels. To illustrate this, we present an application that constructs obstruction-free composites of images acquired on different dates in support of a method for vegetation change detection.

  5. Vasopressin induces phosphorylation of the thiazide-sensitive sodium chloride cotransporter in the distal convoluted tubule

    DEFF Research Database (Denmark)

    Pedersen, Nis Borbye; Hofmeister, Marlene Vind; Rosenbaek, Lena L

    2010-01-01

    (Thr53, Thr58 and Thr53/Thr58) to assess the role of arginine vasopressin (AVP) in regulating NCC in rodent kidney in vivo. Immunohistochemistry showed distinct staining of phosphorylated NCC (pNCC) at the apical plasma membrane domain of distal convoluted tubule (DCT) cells. Unlike total NCC, p...

  6. Inverse Problems for a Parabolic Integrodifferential Equation in a Convolutional Weak Form

    Directory of Open Access Journals (Sweden)

    Kairi Kasemets

    2013-01-01

    Full Text Available We deduce formulas for the Fréchet derivatives of cost functionals of several inverse problems for a parabolic integrodifferential equation in a weak formulation. The method consists in the application of an integrated convolutional form of the weak problem and all computations are implemented in regular Sobolev spaces.

  7. Resting State fMRI Functional Connectivity-Based Classification Using a Convolutional Neural Network Architecture

    Directory of Open Access Journals (Sweden)

    Regina J. Meszlényi

    2017-10-01

    Full Text Available Machine learning techniques have become increasingly popular in the field of resting state fMRI (functional magnetic resonance imaging network based classification. However, the application of convolutional networks has been proposed only very recently and has remained largely unexplored. In this paper we describe a convolutional neural network architecture for functional connectome classification called connectome-convolutional neural network (CCNN. Our results on simulated datasets and a publicly available dataset for amnestic mild cognitive impairment classification demonstrate that our CCNN model can efficiently distinguish between subject groups. We also show that the connectome-convolutional network is capable to combine information from diverse functional connectivity metrics and that models using a combination of different connectivity descriptors are able to outperform classifiers using only one metric. From this flexibility follows that our proposed CCNN model can be easily adapted to a wide range of connectome based classification or regression tasks, by varying which connectivity descriptor combinations are used to train the network.

  8. Convolutional auto-encoder for image denoising of ultra-low-dose CT

    Directory of Open Access Journals (Sweden)

    Mizuho Nishio

    2017-08-01

    Conclusion: Neural network with convolutional auto-encoder could be trained using pairs of standard-dose and ultra-low-dose CT image patches. According to the visual assessment by radiologists and technologists, the performance of our proposed method was superior to that of large-scale nonlocal mean and block-matching and 3D filtering.

  9. Improving airway segmentation in computed tomography using leak detection with convolutional networks

    NARCIS (Netherlands)

    Charbonnier, J.P.; Rikxoort, E.M. van; Setio, A.A.A.; Schaefer-Prokop, C.M.; Ginneken, B. van; Ciompi, F.

    2017-01-01

    We propose a novel method to improve airway segmentation in thoracic computed tomography (CT) by detecting and removing leaks. Leak detection is formulated as a classification problem, in which a convolutional network (ConvNet) is trained in a supervised fashion to perform the classification task.

  10. Resting State fMRI Functional Connectivity-Based Classification Using a Convolutional Neural Network Architecture

    Science.gov (United States)

    Meszlényi, Regina J.; Buza, Krisztian; Vidnyánszky, Zoltán

    2017-01-01

    Machine learning techniques have become increasingly popular in the field of resting state fMRI (functional magnetic resonance imaging) network based classification. However, the application of convolutional networks has been proposed only very recently and has remained largely unexplored. In this paper we describe a convolutional neural network architecture for functional connectome classification called connectome-convolutional neural network (CCNN). Our results on simulated datasets and a publicly available dataset for amnestic mild cognitive impairment classification demonstrate that our CCNN model can efficiently distinguish between subject groups. We also show that the connectome-convolutional network is capable to combine information from diverse functional connectivity metrics and that models using a combination of different connectivity descriptors are able to outperform classifiers using only one metric. From this flexibility follows that our proposed CCNN model can be easily adapted to a wide range of connectome based classification or regression tasks, by varying which connectivity descriptor combinations are used to train the network. PMID:29089883

  11. Fast 2D Convolutions and Cross-Correlations Using Scalable Architectures.

    Science.gov (United States)

    Carranza, Cesar; Llamocca, Daniel; Pattichis, Marios

    2017-05-01

    The manuscript describes fast and scalable architectures and associated algorithms for computing convolutions and cross-correlations. The basic idea is to map 2D convolutions and cross-correlations to a collection of 1D convolutions and cross-correlations in the transform domain. This is accomplished through the use of the discrete periodic radon transform for general kernels and the use of singular value decomposition -LU decompositions for low-rank kernels. The approach uses scalable architectures that can be fitted into modern FPGA and Zynq-SOC devices. Based on different types of available resources, for P×P blocks, 2D convolutions and cross-correlations can be computed in just O(P) clock cycles up to O(P 2 ) clock cycles. Thus, there is a trade-off between performance and required numbers and types of resources. We provide implementations of the proposed architectures using modern programmable devices (Virtex-7 and Zynq-SOC). Based on the amounts and types of required resources, we show that the proposed approaches significantly outperform current methods.

  12. Analisis Unjuk Kerja Convolutional Code pada Sistem MIMO MC-DSSS Melalui Kanal Rayleigh Fading

    Directory of Open Access Journals (Sweden)

    Kadek Agus Mahabojana Dwi Prayoga

    2017-08-01

    Full Text Available Kombinasi antara sistem MIMO (multiple input multiple output, OFDM (orthogonal frequency division multiplexing, dan spread spectrum serta adanya teknik pengkodean kanal mampu mengurangi efek fading dan error yang terjadi. Penelitian ini bertujuan untuk mengetahui perbandingan performansi dari sistem MIMO MC-DSSS (multi carrier-direct sequence spread spectrum Uncoded atau tanpa pengkodean kanal dan MIMO MC-DSSS Convolutional Code atau dengan pengkodean kanal Convolutional yang melalui kanal Rayleigh Fading, ditinjau dari nilai dan grafik BER (bit error rate berbanding Eb/No (energy per bit to noise power spectral density ratio. Penelitian ini menggunakan metode simulasi dengan menggunakan program Matlab R2015a. Hasil dari simulasi didapat unjuk kerja sistem MIMO MC-DSSS dengan Convolutional Code memiliki hasil yang lebih baik dari MIMO MC-DSSS. Pada kanal transmisi Rayleigh Fading untuk mencapi nilai BER sebesar 10-3 pada sistem MIMO MC-DSSS dengan Convolutional Code dibutuhkan Eb/No sebesar -7 dB. Sedangkan pada sistem MIMO MC-DSSS dibutuhkan Eb/No sebesar -3 dB.[turnitin 20%, 7-11-2016

  13. Further results on binary convolutional codes with an optimum distance profile

    DEFF Research Database (Denmark)

    Johannesson, Rolf; Paaske, Erik

    1978-01-01

    Fixed binary convolutional codes are considered which are simultaneously optimal or near-optimal according to three criteria: namely, distance profiled, free distanced_{ infty}, and minimum number of weightd_{infty}paths. It is shown how the optimum distance profile criterion can be used to limit...

  14. Upper bounds on the number of errors corrected by a convolutional code

    DEFF Research Database (Denmark)

    Justesen, Jørn

    2004-01-01

    We derive upper bounds on the weights of error patterns that can be corrected by a convolutional code with given parameters, or equivalently we give bounds on the code rate for a given set of error patterns. The bounds parallel the Hamming bound for block codes by relating the number of error...... patterns to the number of distinct syndromes....

  15. Synthetic bootstrapping of convolutional neural networks for semantic plant part segmentation

    NARCIS (Netherlands)

    Barth, R.; IJsselmuiden, J.; Hemming, J.; Henten, Van E.J.

    2017-01-01

    A current bottleneck of state-of-the-art machine learning methods for image segmentation in agriculture, e.g. convolutional neural networks (CNNs), is the requirement of large manually annotated datasets on a per-pixel level. In this paper, we investigated how related synthetic images can be used to

  16. Object recognition using deep convolutional neural networks with complete transfer and partial frozen layers

    NARCIS (Netherlands)

    Kruithof, M.C.; Bouma, H.; Fischer, N.M.; Schutte, K.

    2016-01-01

    Object recognition is important to understand the content of video and allow flexible querying in a large number of cameras, especially for security applications. Recent benchmarks show that deep convolutional neural networks are excellent approaches for object recognition. This paper describes an

  17. Deep Convolutional Generative Adversarial Network for Procedural 3D Landscape Generation Based on DEM

    DEFF Research Database (Denmark)

    Wulff-Jensen, Andreas; Rant, Niclas Nerup; Møller, Tobias Nordvig

    2018-01-01

    This paper proposes a novel framework for improving procedural generation of 3D landscapes using machine learning. We utilized a Deep Convolutional Generative Adversarial Network (DC-GAN) to generate heightmaps. The network was trained on a dataset consisting of Digital Elevation Maps (DEM...

  18. Radio Signal Augmentation for Improved Training of a Convolutional Neural Network

    Science.gov (United States)

    2016-09-01

    TECHNICAL REPORT 3055 September 2016 Radio Signal Augmentation for Improved Training of a Convolutional Neural Network Daniel...Security Branch Under authority of G. Settelmayer, Head Information Operations Division EXECUTIVE SUMMARY This technical report presents the...might recognize it across various mediums, even if brush strokes do not fundamentally resemble photographic pixels. 9 4. CONCLUSION The experiments

  19. New molecular players facilitating Mg(2+) reabsorption in the distal convoluted tubule.

    NARCIS (Netherlands)

    Glaudemans, Bob; Knoers, N.V.A.M.; Hoenderop, J.G.J.; Bindels, R.J.M.

    2010-01-01

    The renal distal convoluted tubule (DCT) has an essential role in maintaining systemic magnesium (Mg(2+)) concentration. The DCT is the final determinant of plasma Mg(2+) levels, as the more distal nephron segments are largely impermeable to Mg(2+). In the past decade, positional candidate

  20. A fully convolutional networks (FCN) based image segmentation algorithm in binocular imaging system

    Science.gov (United States)

    Long, Zourong; Wei, Biao; Feng, Peng; Yu, Pengwei; Liu, Yuanyuan

    2018-01-01

    This paper proposes an image segmentation algorithm with fully convolutional networks (FCN) in binocular imaging system under various circumstance. Image segmentation is perfectly solved by semantic segmentation. FCN classifies the pixels, so as to achieve the level of image semantic segmentation. Different from the classical convolutional neural networks (CNN), FCN uses convolution layers instead of the fully connected layers. So it can accept image of arbitrary size. In this paper, we combine the convolutional neural network and scale invariant feature matching to solve the problem of visual positioning under different scenarios. All high-resolution images are captured with our calibrated binocular imaging system and several groups of test data are collected to verify this method. The experimental results show that the binocular images are effectively segmented without over-segmentation. With these segmented images, feature matching via SURF method is implemented to obtain regional information for further image processing. The final positioning procedure shows that the results are acceptable in the range of 1.4 1.6 m, the distance error is less than 10mm.

  1. Three-dimensional reconstruction from radiographs and electron micrographs: application of convolutions instead of Fourier transforms.

    Science.gov (United States)

    Ramachandran, G N; Lakshminarayanan, A V

    1971-09-01

    A new technique is proposed for the mathematical process of reconstruction of a three-dimensional object from its transmission shadowgraphs; it uses convolutions with functions defined in the real space of the object, without using Fourier transforms. The object is rotated about an axis at right angles to the direction of a parallel beam of radiation, and sections of it normal to the axis are reconstructed from data obtained by scanning the corresponding linear strips in the shadowgraphs at different angular settings. Since the formulae in the convolution method involve only summations over one variable at a time, while a two-dimensional reconstruction with the Fourier transform technique requires double summations, the convolution method is much faster (typically by a factor of 30); the relative increase in speed is larger where greater resolution is required. Tests of the convolution method with computer-simulated shadowgraphs show that it is also more accurate than the Fourier transform method. It has good potentialities for application in electron microscopy and x-radiography. A new method of reconstructing helical structures by this technique is also suggested.

  2. Role of the distal convoluted tubule in renal Mg(2+) handling: molecular lessons from inherited hypomagnesemia

    NARCIS (Netherlands)

    Ferre, S.; Hoenderop, J.G.J.; Bindels, R.J.M.

    2011-01-01

    In healthy individuals, Mg(2+) homeostasis is tightly regulated by the concerted action of intestinal absorption, exchange with bone, and renal excretion. The kidney, more precisely the distal convoluted tubule (DCT), is the final determinant of plasma Mg(2+) concentrations. Positional cloning

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

    NARCIS (Netherlands)

    Sokooti, Hessam; de Vos, Bob; Berendsen, Floris; Lelieveldt, Boudewijn P.F.; Išgum, Ivana; Staring, Marius

    2017-01-01

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

  4. Comparing Local Descriptors and Bags of Visual Words to Deep Convolutional Neural Networks for Plant Recognition

    NARCIS (Netherlands)

    Pawara, Pornntiwa; Okafor, Emmanuel; Surinta, Olarik; Schomaker, Lambertus; Wiering, Marco

    2017-01-01

    The use of machine learning and computer vision methods for recognizing different plants from images has attracted lots of attention from the community. This paper aims at comparing local feature descriptors and bags of visual words with different classifiers to deep convolutional neural networks

  5. Convolutional Neural Network for Multi-Source Deep Learning Crop Classification in Ukraine

    Science.gov (United States)

    Lavreniuk, M. S.

    2016-12-01

    Land cover and crop type maps are one of the most essential inputs when dealing with environmental and agriculture monitoring tasks [1]. During long time neural network (NN) approach was one of the most efficient and popular approach for most applications, including crop classification using remote sensing data, with high an overall accuracy (OA) [2]. In the last years the most popular and efficient method for multi-sensor and multi-temporal land cover classification is convolution neural networks (CNNs). Taking into account presence clouds in optical data, self-organizing Kohonen maps (SOMs) are used to restore missing pixel values in a time series of optical imagery from Landsat-8 satellite. After missing data restoration, optical data from Landsat-8 was merged with Sentinel-1A radar data for better crop types discrimination [3]. An ensemble of CNNs is proposed for multi-temporal satellite images supervised classification. Each CNN in the corresponding ensemble is a 1-d CNN with 4 layers implemented using the Google's library TensorFlow. The efficiency of the proposed approach was tested on a time-series of Landsat-8 and Sentinel-1A images over the JECAM test site (Kyiv region) in Ukraine in 2015. Overall classification accuracy for ensemble of CNNs was 93.5% that outperformed an ensemble of multi-layer perceptrons (MLPs) by +0.8% and allowed us to better discriminate summer crops, in particular maize and soybeans. For 2016 we would like to validate this method using Sentinel-1 and Sentinel-2 data for Ukraine territory within ESA project on country level demonstration Sen2Agri. 1. A. Kolotii et al., "Comparison of biophysical and satellite predictors for wheat yield forecasting in Ukraine," The Int. Arch. of Photogram., Rem. Sens. and Spatial Inform. Scie., vol. 40, no. 7, pp. 39-44, 2015. 2. F. Waldner et al., "Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity," Int. Journal of Rem. Sens. vol. 37, no. 14, pp

  6. Semantic White Balance: Semantic Color Constancy Using Convolutional Neural Network

    OpenAIRE

    Afifi, Mahmoud

    2018-01-01

    The goal of the computational color constancy is to preserve the perceptive colors of objects under different lighting conditions by removing the effect of color casts occurred by the scene's illumination. With the rapid development of deep learning based techniques, significant progress has been made in image semantic segmentation. In this work, we exploit the semantic information together with the color and spatial information of the input image in order to remove color casts. We train a co...

  7. 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.

  8. Spatial evolution of Zn-Fe-Pb isotopes of sphalerite within a single ore body: A case study from the Dongshengmiao ore deposit, Inner Mongolia, China

    Science.gov (United States)

    Gao, Zhaofu; Zhu, Xiangkun; Sun, Jian; Luo, Zhaohua; Bao, Chuang; Tang, Chao; Ma, Jianxiong

    2018-01-01

    Analyses of sphalerite minerals from the characteristic brecciated Zn-Pb ores of the main ore body in the giant Dongshengmiao deposit have revealed variations in δ66Zn from 0.17 to 0.40‰ and in δ56Fe from -1.78 to -0.35‰. Further, the investigated pyrrhotite samples have iron that is isotopically similar to that of associated sphalerite minerals. The most distinctive pattern revealed by the zinc and iron isotope data is the lateral trend of increasing δ66Zn and δ56Fe values from southwest to northeast within the main ore body. The lead isotopic homogeneity of ore sulfides from the main ore body suggests that there is only one significant source for metal, thus precluding the mixing of multiple metal sources as the key factor controlling spatial variations of zinc and iron isotopes. The most likely control on spatial variations is Rayleigh fractionation during hydrothermal fluid flow, with lighter Zn and Fe isotopes preferentially incorporated into the earliest sulfides to precipitate from fluids. Precipitations of sphalerite and pyrrhotite have played vital roles in the Zn and Fe isotopic variations, respectively, of the ore-forming system. Accordingly, the larger isotopic variability for Fe than Zn within the same hydrothermal system perhaps resulted from a larger proportion of precipitation for pyrrhotite than for sphalerite. The lateral trend pattern revealed by the zinc and iron isotope data is consistent with the occurrence of a cystic-shaped breccia zone, which is characterized by marked elevation in Cu. The results further confirm that Zn and Fe isotopes can be used as a vectoring tool for mineral prospecting.

  9. A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation.

    Science.gov (United States)

    Zeng, Xiangrui; Leung, Miguel Ricardo; Zeev-Ben-Mordehai, Tzviya; Xu, Min

    2018-05-01

    Cellular electron cryo-tomography enables the 3D visualization of cellular organization in the near-native state and at submolecular resolution. However, the contents of cellular tomograms are often complex, making it difficult to automatically isolate different in situ cellular components. In this paper, we propose a convolutional autoencoder-based unsupervised approach to provide a coarse grouping of 3D small subvolumes extracted from tomograms. We demonstrate that the autoencoder can be used for efficient and coarse characterization of features of macromolecular complexes and surfaces, such as membranes. In addition, the autoencoder can be used to detect non-cellular features related to sample preparation and data collection, such as carbon edges from the grid and tomogram boundaries. The autoencoder is also able to detect patterns that may indicate spatial interactions between cellular components. Furthermore, we demonstrate that our autoencoder can be used for weakly supervised semantic segmentation of cellular components, requiring a very small amount of manual annotation. Copyright © 2017 Elsevier Inc. All rights reserved.

  10. Unsupervised 3D Local Feature Learning by Circle Convolutional Restricted Boltzmann Machine.

    Science.gov (United States)

    Han, Zhizhong; Liu, Zhenbao; Han, Junwei; Vong, Chi-Man; Bu, Shuhui; Li, Xuelong

    2016-09-02

    Extracting local features from 3D shapes is an important and challenging task that usually requires carefully designed 3D shape descriptors. However, these descriptors are hand-crafted and require intensive human intervention with prior knowledge. To tackle this issue, we propose a novel deep learning model, namely Circle Convolutional Restricted Boltzmann Machine (CCRBM), for unsupervised 3D local feature learning. CCRBM is specially designed to learn from raw 3D representations. It effectively overcomes obstacles such as irregular vertex topology, orientation ambiguity on the 3D surface, and rigid or slightly non-rigid transformation invariance in the hierarchical learning of 3D data that cannot be resolved by the existing deep learning models. Specifically, by introducing the novel circle convolution, CCRBM holds a novel ring-like multilayer structure to learn 3D local features in a structure preserving manner. Circle convolution convolves across 3D local regions via rotating a novel circular sector convolution window in a consistent circular direction. In the process of circle convolution, extra points are sampled in each 3D local region and projected onto the tangent plane of the center of the region. In this way, the projection distances in each sector window are employed to constitute a novel local raw 3D representation called Projection Distance Distribution (PDD). In addition, to eliminate the initial location ambiguity of a sector window, the Fourier Transform Modulus (FTM) is used to transform the PDD into the Fourier domain which is then conveyed to CCRBM. Experiments using the learned local features are conducted on three aspects: global shape retrieval, partial shape retrieval, and shape correspondence. The experimental results show that the learned local features outperform other state-of-the-art 3D shape descriptors.

  11. Classification of multispectral or hyperspectral satellite imagery using clustering of sparse approximations on sparse representations in learned dictionaries obtained using efficient convolutional sparse coding

    Energy Technology Data Exchange (ETDEWEB)

    Moody, Daniela; Wohlberg, Brendt

    2018-01-02

    An approach for land cover classification, seasonal and yearly change detection and monitoring, and identification of changes in man-made features may use a clustering of sparse approximations (CoSA) on sparse representations in learned dictionaries. The learned dictionaries may be derived using efficient convolutional sparse coding to build multispectral or hyperspectral, multiresolution dictionaries that are adapted to regional satellite image data. Sparse image representations of images over the learned dictionaries may be used to perform unsupervised k-means clustering into land cover categories. The clustering process behaves as a classifier in detecting real variability. This approach may combine spectral and spatial textural characteristics to detect geologic, vegetative, hydrologic, and man-made features, as well as changes in these features over time.

  12. Spatial Sense.

    Science.gov (United States)

    Del Grande, John

    1990-01-01

    Describes seven spatial abilities related to mathematics including eye-motor coordination, figure-ground perception, perceptual constancy, position-in-space perception, perception of spatial relationships, visual discrimination, and visual memory. Discusses the relationship of the spatial abilities to the study of geometry. Lists 19 references.…

  13. Semantic segmentation of bioimages using convolutional neural networks

    CSIR Research Space (South Africa)

    Wiehman, S

    2016-07-01

    Full Text Available image processing pipeline, which achieved a worm segmentation accuracy of 94%, was outperformed by all of the architectures considered, with the best being 97.3% achieved by a FCN with a single downsampling layer. These results demonstrate the promise...

  14. Video Salient Object Detection via Fully Convolutional Networks

    Science.gov (United States)

    Wang, Wenguan; Shen, Jianbing; Shao, Ling

    2018-01-01

    This paper proposes a deep learning model to efficiently detect salient regions in videos. It addresses two important issues: (1) deep video saliency model training with the absence of sufficiently large and pixel-wise annotated video data, and (2) fast video saliency training and detection. The proposed deep video saliency network consists of two modules, for capturing the spatial and temporal saliency information, respectively. The dynamic saliency model, explicitly incorporating saliency estimates from the static saliency model, directly produces spatiotemporal saliency inference without time-consuming optical flow computation. We further propose a novel data augmentation technique that simulates video training data from existing annotated image datasets, which enables our network to learn diverse saliency information and prevents overfitting with the limited number of training videos. Leveraging our synthetic video data (150K video sequences) and real videos, our deep video saliency model successfully learns both spatial and temporal saliency cues, thus producing accurate spatiotemporal saliency estimate. We advance the state-of-the-art on the DAVIS dataset (MAE of .06) and the FBMS dataset (MAE of .07), and do so with much improved speed (2fps with all steps).

  15. Discriminating between benign and malignant breast tumors using 3D convolutional neural network in dynamic contrast enhanced-MR images

    Science.gov (United States)

    Li, Jing; Fan, Ming; Zhang, Juan; Li, Lihua

    2017-03-01

    Convolutional neural networks (CNNs) are the state-of-the-art deep learning network architectures that can be used in a range of applications, including computer vision and medical image analysis. It exhibits a powerful representation learning mechanism with an automated design to learn features directly from the data. However, the common 2D CNNs only use the two dimension spatial information without evaluating the correlation between the adjoin slices. In this study, we established a method of 3D CNNs to discriminate between malignant and benign breast tumors. To this end, 143 patients were enrolled which include 66 benign and 77 malignant instances. The MRI images were pre-processed for noise reduction and breast tumor region segmentation. Data augmentation by spatial translating, rotating and vertical and horizontal flipping is applied to the cases to reduce possible over-fitting. A region-of-interest (ROI) and a volume-of-interest (VOI) were segmented in 2D and 3D DCE-MRI, respectively. The enhancement ratio for each MR series was calculated for the 2D and 3D images. The results for the enhancement ratio images in the two series are integrated for classification. The results of the area under the ROC curve(AUC) values are 0.739 and 0.801 for 2D and 3D methods, respectively. The results for 3D CNN which combined 5 slices for each enhancement ratio images achieved a high accuracy(Acc), sensitivity(Sens) and specificity(Spec) of 0.781, 0.744 and 0.823, respectively. This study indicates that 3D CNN deep learning methods can be a promising technology for breast tumor classification without manual feature extraction.

  16. CLASSIFICATION OF URBAN AERIAL DATA BASED ON PIXEL LABELLING WITH DEEP CONVOLUTIONAL NEURAL NETWORKS AND LOGISTIC REGRESSION

    Directory of Open Access Journals (Sweden)

    W. Yao

    2016-06-01

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

  17. 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

  18. Spatial Modulation in the Underwater Acoustic Communication Channel

    National Research Council Canada - National Science Library

    Kilfoyle, Daniel

    2000-01-01

    .... The technique, termed spatial modulation, seeks to control the spatial distribution of signal energy such that multiple parallel communication channels are supported by the single, physical ocean channel...

  19. Local dynamic range compensation for scanning electron microscope imaging system by sub-blocking multiple peak HE with convolution.

    Science.gov (United States)

    Sim, K S; Teh, V; Tey, Y C; Kho, T K

    2016-11-01

    This paper introduces new development technique to improve the Scanning Electron Microscope (SEM) image quality and we name it as sub-blocking multiple peak histogram equalization (SUB-B-MPHE) with convolution operator. By using this new proposed technique, it shows that the new modified MPHE performs better than original MPHE. In addition, the sub-blocking method consists of convolution operator which can help to remove the blocking effect for SEM images after applying this new developed technique. Hence, by using the convolution operator, it effectively removes the blocking effect by properly distributing the suitable pixel value for the whole image. Overall, the SUB-B-MPHE with convolution outperforms the rest of methods. SCANNING 38:492-501, 2016. © 2015 Wiley Periodicals, Inc. © Wiley Periodicals, Inc.

  20. Analysis by Monte Carlo simulations of the sensitivity to single event upset of SRAM memories under spatial proton or terrestrial neutron environment

    International Nuclear Information System (INIS)

    Lambert, D.

    2006-07-01

    Electronic systems in space and terrestrial environments are subjected to a flow of particles of natural origin, which can induce dysfunctions. These particles can cause Single Event Upsets (SEU) in SRAM memories. Although non-destructive, the SEU can have consequences on the equipment functioning in applications requiring a great reliability (airplane, satellite, launcher, medical, etc). Thus, an evaluation of the sensitivity of the component technology is necessary to predict the reliability of a system. In atmospheric environment, the SEU sensitivity is mainly caused by the secondary ions resulting from the nuclear reactions between the neutrons and the atoms of the component. In space environment, the protons with strong energies induce the same effects as the atmospheric neutrons. In our work, a new code of prediction of the rate of SEU has been developed (MC-DASIE) in order to quantify the sensitivity for a given environment and to explore the mechanisms of failures according to technology. This code makes it possible to study various technologies of memories SRAM (Bulk and SOI) in neutron and proton environment between 1 MeV and 1 GeV. Thus, MC-DASIE was used with experiment data to study the effect of integration on the sensitivity of the memories in terrestrial environment, a comparison between the neutron and proton irradiations and the influence of the modeling of the target component on the calculation of the rate of SEU. (author)

  1. Blumeria graminis interactions with barley conditioned by different single R genes demonstrate a temporal and spatial relationship between stomatal dysfunction and cell death.

    Science.gov (United States)

    Prats, Elena; Gay, Alan P; Roberts, Peter C; Thomas, Barry J; Sanderson, Ruth; Paveley, Neil; Lyngkjaer, Michael F; Carver, Tim L W; Mur, Luis A J

    2010-01-01

    Hypersensitive response (HR) against Blumeria graminis f. sp. hordei infection in barley (Hordeum vulgare) was associated with stomata "lock-up" leading to increased leaf water conductance (g(l)). Unique spatio-temporal patterns of HR formation occurred in barley with Mla1, Mla3, or MlLa R genes challenged with B. graminis f. sp. hordei. With Mla1, a rapid HR, limited to epidermal cells, arrested fungal growth before colonies initiated secondary attacks. With Mla3, mesophyll HR preceded that in epidermal cells whose initial survival supported secondary infections. With MlLa, mesophyll survived and not all attacked epidermal cells died immediately, allowing colony growth and secondary infection until arrested. Isolines with Mla1, Mla3, or MlLa genes inoculated with B. graminis f. sp. hordei ranging from 1 to 100 conidia mm(2) showed abnormally high g(l) during dark periods whose timing and extent correlated with those of each HR. Each isoline showed increased dark g(l) with the nonpathogen B. graminis f. sp. avenae which caused a single epidermal cell HR. Guard cell autofluorescence was seen only after drying of epidermal strips and closure of stomata suggesting that locked open stomata were viable. The data link stomatal lock-up to HR associated cell death and has implications for strategies for selecting disease resistant genotypes.

  2. Use of an iterative convolution approach for qualitative and quantitative peak analysis in low resolution gamma-ray spectra

    International Nuclear Information System (INIS)

    Gardner, Robin P.; Ai Xianyun; Peeples, Cody R.; Wang, Jiaxin; Lee, Kyoung; Peeples, Johanna L.; Calderon, Adan

    2011-01-01

    In many applications, low resolution gamma-ray spectrometers, such as sodium iodide scintillation detectors, are widely used primarily due to their relatively low cost and high detection efficiency. There is widespread interest in improved methods for analyzing spectral data acquired with such devices, using inverse analysis. Peak means and peak areas in gamma- and X-ray spectra are needed for both qualitative and quantitative analysis. This paper introduces the PEAKSI code package that was developed at the Center for Engineering Applications of Radioisotopes (CEAR). The basic approach described here is to use accurate forward models and iterative convolution instead of direct deconvolution. Rather than smoothing and differentiation a combination of linear regression and non-linear searching is used to minimize the reduced chi-square, since this approach retains the capability of establishing uncertainties in the estimated peak parameters. The PEAKSI package uses a Levenberg-Marquardt (LM) non-linear search method combined with multiple linear regression (MLR) to minimize the reduced chi-square value for fitting single or multiple overlapping peaks to determine peak parameters, including peak means, peak standard deviations or full width at half maximum (FWHM), net peak counts, and background counts of peaks in experimental gamma-ray spectra. This approach maintains the natural error structure so that parameter uncertainties can be estimated. The plan is to release this code to the public in the near future.

  3. An Adaptive Multi-Sensor Data Fusion Method Based on Deep Convolutional Neural Networks for Fault Diagnosis of Planetary Gearbox.

    Science.gov (United States)

    Jing, Luyang; Wang, Taiyong; Zhao, Ming; Wang, Peng

    2017-02-21

    A fault diagnosis approach based on multi-sensor data fusion is a promising tool to deal with complicated damage detection problems of mechanical systems. Nevertheless, this approach suffers from two challenges, which are (1) the feature extraction from various types of sensory data and (2) the selection of a suitable fusion level. It is usually difficult to choose an optimal feature or fusion level for a specific fault diagnosis task, and extensive domain expertise and human labor are also highly required during these selections. To address these two challenges, we propose an adaptive multi-sensor data fusion method based on deep convolutional neural networks (DCNN) for fault diagnosis. The proposed method can learn features from raw data and optimize a combination of different fusion levels adaptively to satisfy the requirements of any fault diagnosis task. The proposed method is tested through a planetary gearbox test rig. Handcraft features, manual-selected fusion levels, single sensory data, and two traditional intelligent models, back-propagation neural networks (BPNN) and a support vector machine (SVM), are used as comparisons in the experiment. The results demonstrate that the proposed method is able to detect the conditions of the planetary gearbox effectively with the best diagnosis accuracy among all comparative methods in the experiment.

  4. Effective Fusion of Multi-Modal Remote Sensing Data in a Fully Convolutional Network for Semantic Labeling

    Directory of Open Access Journals (Sweden)

    Wenkai Zhang

    2017-12-01

    Full Text Available In recent years, Fully Convolutional Networks (FCN have led to a great improvement of semantic labeling for various applications including multi-modal remote sensing data. Although different fusion strategies have been reported for multi-modal data, there is no in-depth study of the reasons of performance limits. For example, it is unclear, why an early fusion of multi-modal data in FCN does not lead to a satisfying result. In this paper, we investigate the contribution of individual layers inside FCN and propose an effective fusion strategy for the semantic labeling of color or infrared imagery together with elevation (e.g., Digital Surface Models. The sensitivity and contribution of layers concerning classes and multi-modal data are quantified by recall and descent rate of recall in a multi-resolution model. The contribution of different modalities to the pixel-wise prediction is analyzed explaining the reason of the poor performance caused by the plain concatenation of different modalities. Finally, based on the analysis an optimized scheme for the fusion of layers with image and elevation information into a single FCN model is derived. Experiments are performed on the ISPRS Vaihingen 2D Semantic Labeling dataset (infrared and RGB imagery as well as elevation and the Potsdam dataset (RGB imagery and elevation. Comprehensive evaluations demonstrate the potential of the proposed approach.

  5. An Adaptive Multi-Sensor Data Fusion Method Based on Deep Convolutional Neural Networks for Fault Diagnosis of Planetary Gearbox

    Directory of Open Access Journals (Sweden)

    Luyang Jing

    2017-02-01

    Full Text Available A fault diagnosis approach based on multi-sensor data fusion is a promising tool to deal with complicated damage detection problems of mechanical systems. Nevertheless, this approach suffers from two challenges, which are (1 the feature extraction from various types of sensory data and (2 the selection of a suitable fusion level. It is usually difficult to choose an optimal feature or fusion level for a specific fault diagnosis task, and extensive domain expertise and human labor are also highly required during these selections. To address these two challenges, we propose an adaptive multi-sensor data fusion method based on deep convolutional neural networks (DCNN for fault diagnosis. The proposed method can learn features from raw data and optimize a combination of different fusion levels adaptively to satisfy the requirements of any fault diagnosis task. The proposed method is tested through a planetary gearbox test rig. Handcraft features, manual-selected fusion levels, single sensory data, and two traditional intelligent models, back-propagation neural networks (BPNN and a support vector machine (SVM, are used as comparisons in the experiment. The results demonstrate that the proposed method is able to detect the conditions of the planetary gearbox effectively with the best diagnosis accuracy among all comparative methods in the experiment.

  6. Bearing Fault Diagnosis under Variable Speed Using Convolutional Neural Networks and the Stochastic Diagonal Levenberg-Marquardt Algorithm

    Directory of Open Access Journals (Sweden)

    Viet Tra

    2017-12-01

    Full Text Available This paper presents a novel method for diagnosing incipient bearing defects under variable operating speeds using convolutional neural networks (CNNs trained via the stochastic diagonal Levenberg-Marquardt (S-DLM algorithm. The CNNs utilize the spectral energy maps (SEMs of the acoustic emission (AE signals as inputs and automatically learn the optimal features, which yield the best discriminative models for diagnosing incipient bearing defects under variable operating speeds. The SEMs are two-dimensional maps that show the distribution of energy across different bands of the AE spectrum. It is hypothesized that the variation of a bearing’s speed would not alter the overall shape of the AE spectrum rather, it may only scale and translate it. Thus, at different speeds, the same defect would yield SEMs that are scaled and shifted versions of each other. This hypothesis is confirmed by the experimental results, where CNNs trained using the S-DLM algorithm yield significantly better diagnostic performance under variable operating speeds compared to existing methods. In this work, the performance of different training algorithms is also evaluated to select the best training algorithm for the CNNs. The proposed method is used to diagnose both single and compound defects at six different operating speeds.

  7. The Convolutional Visual Network for Identification and Reconstruction of NOvA Events

    Science.gov (United States)

    Psihas, Fernanda; NOvA Collaboration

    2017-10-01

    In 2016 the NOvA experiment released results for the observation of oscillations in the vμ and ve channels as well as ve cross section measurements using neutrinos from Fermilab’s NuMI beam. These and other measurements in progress rely on the accurate identification and reconstruction of the neutrino flavor and energy recorded by our detectors. This presentation describes the first application of convolutional neural network technology for event identification and reconstruction in particle detectors like NOvA. The Convolutional Visual Network (CVN) Algorithm was developed for identification, categorization, and reconstruction of NOvA events. It increased the selection efficiency of the ve appearance signal by 40% and studies show potential impact to the vμ disappearance analysis.

  8. CVN A Convolutional Visual Network for Identication and Reconstruction of NOvA Events

    Science.gov (United States)

    Psihas, Fernanda; NOvA Collaboration

    2017-09-01

    In the past year, the NOvA experiment released results for the observation of neutrino oscillations in the νμ and νe channels as well as νe cross section measurements using neutrinos from Fermilab’s NuMI beam. These and other measurements in progress rely on the accurate identication and reconstruction of the neutrino avor and energy recorded by our detectors. This presentation describes the rst application of convolutional neural network technology for event identication and reconstruction in particle detectors such as NOvA. The Convolutional Visual Network (CVN) Algorithm was developed for identication, categorization, and reconstruction of NOvA events. It increased the selection efficiency of the νe appearance signal by 40% and studies show potential impact to the νμ disappearance analysis.

  9. Pulmonary Nodule Classification with Deep Convolutional Neural Networks on Computed Tomography Images.

    Science.gov (United States)

    Li, Wei; Cao, Peng; Zhao, Dazhe; Wang, Junbo

    2016-01-01

    Computer aided detection (CAD) systems can assist radiologists by offering a second opinion on early diagnosis of lung cancer. Classification and feature representation play critical roles in false-positive reduction (FPR) in lung nodule CAD. We design a deep convolutional neural networks method for nodule classification, which has an advantage of autolearning representation and strong generalization ability. A specified network structure for nodule images is proposed to solve the recognition of three types of nodules, that is, solid, semisolid, and ground glass opacity (GGO). Deep convolutional neural networks are trained by 62,492 regions-of-interest (ROIs) samples including 40,772 nodules and 21,720 nonnodules from the Lung Image Database Consortium (LIDC) database. Experimental results demonstrate the effectiveness of the proposed method in terms of sensitivity and overall accuracy and that it consistently outperforms the competing methods.

  10. Applications of deep convolutional neural networks to digitized natural history collections

    Directory of Open Access Journals (Sweden)

    Eric Schuettpelz

    2017-11-01

    Full Text Available Natural history collections contain data that are critical for many scientific endeavors. Recent efforts in mass digitization are generating large datasets from these collections that can provide unprecedented insight. Here, we present examples of how deep convolutional neural networks can be applied in analyses of imaged herbarium specimens. We first demonstrate that a convolutional neural network can detect mercury-stained specimens across a collection with 90% accuracy. We then show that such a network can correctly distinguish two morphologically similar plant families 96% of the time. Discarding the most challenging specimen images increases accuracy to 94% and 99%, respectively. These results highlight the importance of mass digitization and deep learning approaches and reveal how they can together deliver powerful new investigative tools.

  11. Seismic signal auto-detecing from different features by using Convolutional Neural Network

    Science.gov (United States)

    Huang, Y.; Zhou, Y.; Yue, H.; Zhou, S.

    2017-12-01

    We try Convolutional Neural Network to detect some features of seismic data and compare their efficience. The features include whether a signal is seismic signal or noise and the arrival time of P and S phase and each feature correspond to a Convolutional Neural Network. We first use traditional STA/LTA to recongnize some events and then use templete matching to find more events as training set for the Neural Network. To make the training set more various, we add some noise to the seismic data and make some synthetic seismic data and noise. The 3-component raw signal and time-frequancy ananlyze are used as the input data for our neural network. Our Training is performed on GPUs to achieve efficient convergence. Our method improved the precision in comparison with STA/LTA and template matching. We will move to recurrent neural network to see if this kind network is better in detect P and S phase.

  12. Visual and Textual Sentiment Analysis of a Microblog Using Deep Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Yuhai Yu

    2016-06-01

    Full Text Available Sentiment analysis of online social media has attracted significant interest recently. Many studies have been performed, but most existing methods focus on either only textual content or only visual content. In this paper, we utilize deep learning models in a convolutional neural network (CNN to analyze the sentiment in Chinese microblogs from both textual and visual content. We first train a CNN on top of pre-trained word vectors for textual sentiment analysis and employ a deep convolutional neural network (DNN with generalized dropout for visual sentiment analysis. We then evaluate our sentiment prediction framework on a dataset collected from a famous Chinese social media network (Sina Weibo that includes text and related images and demonstrate state-of-the-art results on this Chinese sentiment analysis benchmark.

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

    Science.gov (United States)

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

    2017-03-01

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

  14. A New Missing Values Estimation Algorithm in Wireless Sensor Networks Based on Convolution

    Directory of Open Access Journals (Sweden)

    Feng Liu

    2013-04-01

    Full Text Available Nowadays, with the rapid development of Internet of Things (IoT applications, data missing phenomenon becomes very common in wireless sensor networks. This problem can greatly and directly threaten the stability and usability of the Internet of things applications which are constructed based on wireless sensor networks. How to estimate the missing value has attracted wide interest, and some solutions have been proposed. Different with the previous works, in this paper, we proposed a new convolution based missing value estimation algorithm. The convolution theory, which is usually used in the area of signal and image processing, can also be a practical and efficient way to estimate the missing sensor data. The results show that the proposed algorithm in this paper is practical and effective, and can estimate the missing value accurately.

  15. Discrete singular convolution method for the analysis of Mindlin plates on elastic foundations

    International Nuclear Information System (INIS)

    Civalek, Omer; Acar, Mustafa Hilmi

    2007-01-01

    The method of discrete singular convolution (DSC) is used for the bending analysis of Mindlin plates on two-parameter elastic foundations for the first time. Two different realizations of singular kernels, such as the regularized Shannon's delta (RSD) kernel and Lagrange delta sequence (LDS) kernel, are selected as singular convolution to illustrate the present algorithm. The methodology and procedures are presented and bending problems of thick plates on elastic foundations are studied for different boundary conditions. The influence of foundation parameters and shear deformation on the stress resultants and deflections of the plate have been investigated. Numerical studies are performed and the DSC results are compared well with other analytical solutions and some numerical results

  16. Adaptive Correlation Model for Visual Tracking Using Keypoints Matching and Deep Convolutional Feature

    Directory of Open Access Journals (Sweden)

    Yuankun Li

    2018-02-01

    Full Text Available Although correlation filter (CF-based visual tracking algorithms have achieved appealing results, there are still some problems to be solved. When the target object goes through long-term occlusions or scale variation, the correlation model used in existing CF-based algorithms will inevitably learn some non-target information or partial-target information. In order to avoid model contamination and enhance the adaptability of model updating, we introduce the keypoints matching strategy and adjust the model learning rate dynamically according to the matching score. Moreover, the proposed approach extracts convolutional features from a deep convolutional neural network (DCNN to accurately estimate the position and scale of the target. Experimental results demonstrate that the proposed tracker has achieved satisfactory performance in a wide range of challenging tracking scenarios.

  17. A Novel Image Tag Completion Method Based on Convolutional Neural Transformation

    KAUST Repository

    Geng, Yanyan

    2017-10-24

    In the problems of image retrieval and annotation, complete textual tag lists of images play critical roles. However, in real-world applications, the image tags are usually incomplete, thus it is important to learn the complete tags for images. In this paper, we study the problem of image tag complete and proposed a novel method for this problem based on a popular image representation method, convolutional neural network (CNN). The method estimates the complete tags from the convolutional filtering outputs of images based on a linear predictor. The CNN parameters, linear predictor, and the complete tags are learned jointly by our method. We build a minimization problem to encourage the consistency between the complete tags and the available incomplete tags, reduce the estimation error, and reduce the model complexity. An iterative algorithm is developed to solve the minimization problem. Experiments over benchmark image data sets show its effectiveness.

  18. The Convolutional Visual Network for Identification and Reconstruction of NOvA Events

    Energy Technology Data Exchange (ETDEWEB)

    Psihas, Fernanda [Indiana U.

    2017-11-22

    In 2016 the NOvA experiment released results for the observation of oscillations in the vμ and ve channels as well as ve cross section measurements using neutrinos from Fermilab’s NuMI beam. These and other measurements in progress rely on the accurate identification and reconstruction of the neutrino flavor and energy recorded by our detectors. This presentation describes the first application of convolutional neural network technology for event identification and reconstruction in particle detectors like NOvA. The Convolutional Visual Network (CVN) Algorithm was developed for identification, categorization, and reconstruction of NOvA events. It increased the selection efficiency of the ve appearance signal by 40% and studies show potential impact to the vμ disappearance analysis.

  19. 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.

  20. Investigations on the Potential of Convolutional Neural Networks for Vehicle Classification Based on RGB and LIDAR Data

    Science.gov (United States)

    Niessner, R.; Schilling, H.; Jutzi, B.

    2017-05-01

    In recent years, there has been a significant improvement in the detection, identification and classification of objects and images using Convolutional Neural Networks. To study the potential of the Convolutional Neural Network, in this paper three approaches are investigated to train classifiers based on Convolutional Neural Networks. These approaches allow Convolutional Neural Networks to be trained on datasets containing only a few hundred training samples, which results in a successful classification. Two of these approaches are based on the concept of transfer learning. In the first approach features, created by a pretrained Convolutional Neural Network, are used for a classification using a support vector machine. In the second approach a pretrained Convolutional Neural Network gets fine-tuned on a different data set. The third approach includes the design and training for flat Convolutional Neural Networks from the scratch. The evaluation of the proposed approaches is based on a data set provided by the IEEE Geoscience and Remote Sensing Society (GRSS) which contains RGB and LiDAR data of an urban area. In this work it is shown that these Convolutional Neural Networks lead to classification results with high accuracy both on RGB and LiDAR data. Features which are derived by RGB data transferred into LiDAR data by transfer learning lead to better results in classification in contrast to RGB data. Using a neural network which contains fewer layers than common neural networks leads to the best classification results. In this framework, it can furthermore be shown that the practical application of LiDAR images results in a better data basis for classification of vehicles than the use of RGB images.

  1. Time and Frequency Domain Optimization with Shift, Convolution and Smoothness in Factor Analysis Type Decompositions

    DEFF Research Database (Denmark)

    Madsen, Kristoffer Hougaard; Hansen, Lars Kai; Mørup, Morten

    2009-01-01

    representation we demonstrate how the class of objective functions that are separable in either time or frequency instances allow the gradient in the time or frequency domain to be converted to the opposing domain. We further demonstrate the usefulness of this framework for three different models; Shifted Non-negative...... Matrix Factorization, Convolutive Sparse Coding as well as Smooth and Sparse Matrix Factorization. Matlab implementation of the proposed algorithms are available for download at www.erpwavelab.org....

  2. REAL-TIME VIDEO SCALING BASED ON CONVOLUTION NEURAL NETWORK ARCHITECTURE

    OpenAIRE

    S Safinaz; A V Ravi Kumar

    2017-01-01

    In recent years, video super resolution techniques becomes mandatory requirements to get high resolution videos. Many super resolution techniques researched but still video super resolution or scaling is a vital challenge. In this paper, we have presented a real-time video scaling based on convolution neural network architecture to eliminate the blurriness in the images and video frames and to provide better reconstruction quality while scaling of large datasets from lower resolution frames t...

  3. Automatic Graphic Logo Detection via Fast Region-based Convolutional Networks

    OpenAIRE

    Oliveira, Gonçalo; Frazão, Xavier; Pimentel, André; Ribeiro, Bernardete

    2016-01-01

    Brand recognition is a very challenging topic with many useful applications in localization recognition, advertisement and marketing. In this paper we present an automatic graphic logo detection system that robustly handles unconstrained imaging conditions. Our approach is based on Fast Region-based Convolutional Networks (FRCN) proposed by Ross Girshick, which have shown state-of-the-art performance in several generic object recognition tasks (PASCAL Visual Object Classes challenges). In par...

  4. Fuzzy Logic Module of Convolutional Neural Network for Handwritten Digits Recognition

    Science.gov (United States)

    Popko, E. A.; Weinstein, I. A.

    2016-08-01

    Optical character recognition is one of the important issues in the field of pattern recognition. This paper presents a method for recognizing handwritten digits based on the modeling of convolutional neural network. The integrated fuzzy logic module based on a structural approach was developed. Used system architecture adjusted the output of the neural network to improve quality of symbol identification. It was shown that proposed algorithm was flexible and high recognition rate of 99.23% was achieved.

  5. Applicability of the Fourier convolution theorem to the analysis of late-type stellar spectra

    International Nuclear Information System (INIS)

    Bruning, D.H.

    1981-01-01

    Solar flux and intensity measurements were obtained at Sacramento Peak Observatory to test the validity of the Fourier convolution method as a means of analyzing the spectral line shapes of late-type stars. Analysis of six iron lines near 6200A shows that, in general, the convolution method is not a suitable approximation for the calculation of the flux profile. The convolution method does reasonably reproduce the line shape for some lines which appear not to vary across the disk of the sun, but does not properly calculate the central line depth of these lines. Even if a central depth correction could be found, it is difficult to predict, especially for stars other than the sun, which lines have nearly constant shapes and could be used with the convolution method. Therefore, explicit disk integrations are promoted as the only reliable method of spectral line analysis for late-type stars. Several methods of performing the disk integration are investigated. Although the Abt (1957) prescription appears suitable for the limited case studied, methods using annuli of equal area, equal flux, or equal width (Soberblom, 1980) are considered better models. The model that is the easiest to use and most efficient computationally is the equal area model. Model atmosphere calculations yield values for the microturbulence and macroturbulence similar to those derived by observers. Since the depth dependence of the microturbulence is ignored in the calculations, the intensity profiles at disk center and the limb do not match the observed intensity profiles with only one set of velocity parameters. Use of these incorrectly calculated intensity profiles in the integration procedure to obtain the flux profile leads to incorrect estimates of the solar macroturbulence

  6. Estimation of violin bowing features from Audio recordings with Convolutional Networks

    DEFF Research Database (Denmark)

    Perez-Carillo, Alfonso; Purwins, Hendrik

    and low-cost of the acquisition and its nonintrusive nature. The main challenge is designing robust detection algorithms to be as accurate as the direct approaches. In this paper, we present an indirect acquisition method to estimate violin bowing controls from audio signal analysis based on training...... Convolutional Neural Networks with a database of multimodal data (bowing controls and sound features) of violin performances....

  7. Analysis of a nuclear backscattering and reaction data by the method of convolution integrals

    International Nuclear Information System (INIS)

    Lewis, M.B.

    1979-02-01

    A quantitative description of nuclear backscattering and reaction processes is made. Various formulas pertinent to nuclear microanalysis are assembled in a manner useful for experimental application. Convolution integrals relating profiles of atoms in a metal substrate to the nuclear reaction spectra obtained in the laboratory are described and computed. Energy straggling and multiple scattering are explicitly included and shown to be important. Examples of the application of the method to simple backscattering, oxide films, and implanted gas are discussed. 7 figures, 1 table

  8. Using a Deep Convolutional Neural Network for Extracting Morphological Traits from Herbarium Images

    OpenAIRE

    Zhu,Yue; Durand,Thibaut; Chenin,Eric; Pignal,Marc; Galinari,Patrick; Vignes-Lebbe,Régine

    2017-01-01

    Natural history collection data are now accessible through databases and web portals. However, ecological or morphological traits describing specimens are rarely recorded while gathering data. This lack limits queries and analyses. Manual tagging of millions of specimens will be a huge task even with the help of citizen science projects such as "les herbonautes" (http://lesherbonautes.mnhn.fr). On the other hand, deep learning methods that use convolutional neural networks (CNN) demonstrate ...

  9. Optimized parallel convolutions for non-linear fluid models of tokamak ηi turbulence

    International Nuclear Information System (INIS)

    Milovich, J.L.; Tomaschke, G.; Kerbel, G.D.

    1993-01-01

    Non-linear computational fluid models of plasma turbulence based on spectral methods typically spend a large fraction of the total computing time evaluating convolutions. Usually these convolutions arise from an explicit or semi implicit treatment of the convective non-linearities in the problem. Often the principal convective velocity is perpendicular to magnetic field lines allowing a reduction of the convolution to two dimensions in an appropriate geometry, but beyond this, different models vary widely in the particulars of which mode amplitudes are selectively evolved to get the most efficient representation of the turbulence. As the number of modes in the problem, N, increases, the amount of computation required for this part of the evolution algorithm then scales as N 2 /timestep for a direct or analytic method and N ln N/timestep for a pseudospectral method. The constants of proportionality depend on the particulars of mode selection and determine the size problem for which the method will perform equally. For large enough N, the pseudospectral method performance is always superior, though some problems do not require correspondingly high resolution. Further, the Courant condition for numerical stability requires that the timestep size must decrease proportionately as N increases, thus accentuating the need to have fast methods for larger N problems. The authors have developed a package for the Cray system which performs these convolutions for a rather arbitrary mode selection scheme using either method. The package is highly optimized using a combination of macro and microtasking techniques, as well as vectorization and in some cases assembly coded routines. Parts of the package have also been developed and optimized for the CM200 and CM5 system. Performance comparisons with respect to problem size, parallelization, selection schemes and architecture are presented

  10. Cost-Sensitive Convolution based Neural Networks for Imbalanced Time-Series Classification

    OpenAIRE

    Geng, Yue; Luo, Xinyu

    2018-01-01

    Some deep convolutional neural networks were proposed for time-series classification and class imbalanced problems. However, those models performed degraded and even failed to recognize the minority class of an imbalanced temporal sequences dataset. Minority samples would bring troubles for temporal deep learning classifiers due to the equal treatments of majority and minority class. Until recently, there were few works applying deep learning on imbalanced time-series classification (ITSC) ta...

  11. Convolution-based estimation of organ dose in tube current modulated CT

    Science.gov (United States)

    Tian, Xiaoyu; Segars, W. P.; Dixon, R. L.; Samei, Ehsan

    2015-03-01

    Among the various metrics that quantify radiation dose in computed tomography (CT), organ dose is one of the most representative quantities reflecting patient-specific radiation burden.1 Accurate estimation of organ dose requires one to effectively model the patient anatomy and the irradiation field. As illustrated in previous studies, the patient anatomy factor can be modeled using a library of computational phantoms with representative body habitus.2 However, the modeling of irradiation field can be practically challenging, especially for CT exams performed with tube current modulation. The central challenge is to effectively quantify the scatter irradiation field created by the dynamic change of tube current. In this study, we present a convolution-based technique to effectively quantify the primary and scatter irradiation field for TCM examinations. The organ dose for a given clinical patient can then be rapidly determined using the convolution-based method, a patient-matching technique, and a library of computational phantoms. 58 adult patients were included in this study (age range: 18-70 y.o., weight range: 60-180 kg). One computational phantom was created based on the clinical images of each patient. Each patient was optimally matched against one of the remaining 57 computational phantoms using a leave-one-out strategy. For each computational phantom, the organ dose coefficients (CTDIvol-normalized organ dose) under fixed tube current were simulated using a validated Monte Carlo simulation program. Such organ dose coefficients were multiplied by a scaling factor, (CTDIvol )organ, convolution that quantifies the regional irradiation field. The convolution-based organ dose was compared with the organ dose simulated from Monte Carlo program with TCM profiles explicitly modeled on the original phantom created based on patient images. The estimation error was within 10% across all organs and modulation profiles for abdominopelvic examination. This strategy

  12. Accelerating Convolutional Neural Networks for Continuous Mobile Vision via Cache Reuse

    OpenAIRE

    Xu, Mengwei; Liu, Xuanzhe; Liu, Yunxin; Lin, Felix Xiaozhu

    2017-01-01

    Convolutional Neural Network (CNN) is the state-of-the-art algorithm of many mobile vision fields. It is also applied in many vision tasks such as face detection and augmented reality on mobile devices. Though benefited from the high accuracy achieved via deep CNN models, nowadays commercial mobile devices are often short in processing capacity and battery to continuously carry out such CNN-driven vision applications. In this paper, we propose a transparent caching mechanism, named CNNCache, ...

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

    OpenAIRE

    Lei Wang; Xin Xu; Hao Dong; Rong Gui; Fangling Pu

    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 us...

  14. An End-to-End Compression Framework Based on Convolutional Neural Networks

    OpenAIRE

    Jiang, Feng; Tao, Wen; Liu, Shaohui; Ren, Jie; Guo, Xun; Zhao, Debin

    2017-01-01

    Deep learning, e.g., convolutional neural networks (CNNs), has achieved great success in image processing and computer vision especially in high level vision applications such as recognition and understanding. However, it is rarely used to solve low-level vision problems such as image compression studied in this paper. Here, we move forward a step and propose a novel compression framework based on CNNs. To achieve high-quality image compression at low bit rates, two CNNs are seamlessly integr...

  15. Radio Model-free Noise Reduction of Radio Transmissions with Convolutional Autoencoders

    Science.gov (United States)

    2016-09-01

    Linux Journal 122(June):1–4. 5. Francois Chollet. 2015.“Keras: Deep Learning Library for TensorFlow and Theano.” Available online at https://github.com...Aaron C Courville, and Pascal Vincent. 2012. “Unsupervised Feature Learning and Deep Learning : A Review and New Perspectives.” Cornell University...Convolution Arithmetic for Deep Learning .” Cornell University Library. Computing Research Repository (CoRR). arXiv:1603.07285. 10. Ian Goodfellow, Jean

  16. Enhancing Spatial Resolution of Remotely Sensed Imagery Using Deep Learning

    Science.gov (United States)

    Beck, J. M.; Bridges, S.; Collins, C.; Rushing, J.; Graves, S. J.

    2017-12-01

    Researchers at the Information Technology and Systems Center at the University of Alabama in Huntsville are using Deep Learning with Convolutional Neural Networks (CNNs) to develop a method for enhancing the spatial resolutions of moderate resolution (10-60m) multispectral satellite imagery. This enhancement will effectively match the resolutions of imagery from multiple sensors to provide increased global temporal-spatial coverage for a variety of Earth science products. Our research is centered on using Deep Learning for automatically generating transformations for increasing the spatial resolution of remotely sensed images with different spatial, spectral, and temporal resolutions. One of the most important steps in using images from multiple sensors is to transform the different image layers into the same spatial resolution, preferably the highest spatial resolution, without compromising the spectral information. Recent advances in Deep Learning have shown that CNNs can be used to effectively and efficiently upscale or enhance the spatial resolution of multispectral images with the use of an auxiliary data source such as a high spatial resolution panchromatic image. In contrast, we are using both the spatial and spectral details inherent in low spatial resolution multispectral images for image enhancement without the use of a panchromatic image. This presentation will discuss how this technology will benefit many Earth Science applications that use remotely sensed images with moderate spatial resolutions.

  17. Response of the mitochondrial proteome of rat renal proximal convoluted tubules to chronic metabolic acidosis.

    Science.gov (United States)

    Freund, Dana M; Prenni, Jessica E; Curthoys, Norman P

    2013-01-15

    Metabolic acidosis is a common clinical condition that is caused by a decrease in blood pH and bicarbonate concentration. Increased extraction and mitochondrial catabolism of plasma glutamine within the renal proximal convoluted tubule generates ammonium and bicarbonate ions that facilitate the excretion of acid and partially restore acid-base balance. Previous studies identified only a few mitochondrial proteins, including two key enzymes of glutamine metabolism, which are increased during chronic acidosis. A workflow was developed to characterize the mitochondrial proteome of the proximal convoluted tubule. Based upon the increase in specific activity of cytochrome c oxidase, the isolated mitochondria were enriched eightfold. Two-dimensional liquid chromatography coupled with mass spectrometry was utilized to compare mitochondrial-enriched samples from control and chronic acidotic rats. Proteomic analysis identified 901 proteins in the control and acidotic samples. Further analysis identified 37 peptides that contain an N-ε-acetyl-lysine; of these, 22 are novel sites. Spectral counting analysis revealed 33 proteins that are significantly altered in abundance in response to chronic metabolic acidosis. Western blot analysis was performed to validate the calculated changes in abundance. Thus the current study represents the first comprehensive analysis of the mitochondrial proteome of the rat renal proximal convoluted tubule and its response to metabolic acidosis.

  18. REAL-TIME VIDEO SCALING BASED ON CONVOLUTION NEURAL NETWORK ARCHITECTURE

    Directory of Open Access Journals (Sweden)

    S Safinaz

    2017-08-01

    Full Text Available In recent years, video super resolution techniques becomes mandatory requirements to get high resolution videos. Many super resolution techniques researched but still video super resolution or scaling is a vital challenge. In this paper, we have presented a real-time video scaling based on convolution neural network architecture to eliminate the blurriness in the images and video frames and to provide better reconstruction quality while scaling of large datasets from lower resolution frames to high resolution frames. We compare our outcomes with multiple exiting algorithms. Our extensive results of proposed technique RemCNN (Reconstruction error minimization Convolution Neural Network shows that our model outperforms the existing technologies such as bicubic, bilinear, MCResNet and provide better reconstructed motioning images and video frames. The experimental results shows that our average PSNR result is 47.80474 considering upscale-2, 41.70209 for upscale-3 and 36.24503 for upscale-4 for Myanmar dataset which is very high in contrast to other existing techniques. This results proves our proposed model real-time video scaling based on convolution neural network architecture’s high efficiency and better performance.

  19. A Convolution-LSTM-Based Deep Neural Network for Cross-Domain MOOC Forum Post Classification

    Directory of Open Access Journals (Sweden)

    Xiaocong Wei

    2017-07-01

    Full Text Available Learners in a massive open online course often express feelings, exchange ideas and seek help by posting questions in discussion forums. Due to the very high learner-to-instructor ratios, it is unrealistic to expect instructors to adequately track the forums, find all of the issues that need resolution and understand their urgency and sentiment. In this paper, considering the biases among different courses, we propose a transfer learning framework based on a convolutional neural network and a long short-term memory model, called ConvL, to automatically identify whether a post expresses confusion, determine the urgency and classify the polarity of the sentiment. First, we learn the feature representation for each word by considering the local contextual feature via the convolution operation. Second, we learn the post representation from the features extracted through the convolution operation via the LSTM model, which considers the long-term temporal semantic relationships of features. Third, we investigate the possibility of transferring parameters from a model trained on one course to another course and the subsequent fine-tuning. Experiments on three real-world MOOC courses confirm the effectiveness of our framework. This work suggests that our model can potentially significantly increase the effectiveness of monitoring MOOC forums in real time.

  20. Design and Implementation of Convolutional Encoder and Viterbi Decoder Using FPGA.

    Directory of Open Access Journals (Sweden)

    Riham Ali Zbaid

    2018-01-01

    Full Text Available Keeping  the  fineness of data is the most significant thing in communication.There are many factors that affect the accuracy of the data when it is transmitted over the communication channel such as noise etc. to overcome these effects are encoding channels encryption.In this paper is used for one type of channel coding is convolutional codes. Convolution encoding is a Forward Error Correction (FEC method used in incessant one-way and real time communication links .It can offer a great development in the error bit rates so that small, low energy, and devices cheap transmission when used in applications such as satellites. In this paper highlight the design, simulation and implementation of convolution encoder and Viterbi decoder by using MATLAB- program (2011. SIMULINK HDL coder is used to convert MATLAB-SIMULINK models to VHDL using plates Altera Cyclone II code DE2-70. Simulation and evaluation of the implementation of the results coincided with the results of the design show the coinciding with the designed results.