Salient object detection based on multi-scale contrast.

PubMed

Wang, Hai; Dai, Lei; Cai, Yingfeng; Sun, Xiaoqiang; Chen, Long

2018-05-01

Due to the development of deep learning networks, a salient object detection based on deep learning networks, which are used to extract the features, has made a great breakthrough compared to the traditional methods. At present, the salient object detection mainly relies on very deep convolutional network, which is used to extract the features. In deep learning networks, an dramatic increase of network depth may cause more training errors instead. In this paper, we use the residual network to increase network depth and to mitigate the errors caused by depth increase simultaneously. Inspired by image simplification, we use color and texture features to obtain simplified image with multiple scales by means of region assimilation on the basis of super-pixels in order to reduce the complexity of images and to improve the accuracy of salient target detection. We refine the feature on pixel level by the multi-scale feature correction method to avoid the feature error when the image is simplified at the above-mentioned region level. The final full connection layer not only integrates features of multi-scale and multi-level but also works as classifier of salient targets. The experimental results show that proposed model achieves better results than other salient object detection models based on original deep learning networks. Copyright © 2018 Elsevier Ltd. All rights reserved.

Correction Approach for Delta Function Convolution Model Fitting of Fluorescence Decay Data in the Case of a Monoexponential Reference Fluorophore.

PubMed

Talbot, Clifford B; Lagarto, João; Warren, Sean; Neil, Mark A A; French, Paul M W; Dunsby, Chris

2015-09-01

A correction is proposed to the Delta function convolution method (DFCM) for fitting a multiexponential decay model to time-resolved fluorescence decay data using a monoexponential reference fluorophore. A theoretical analysis of the discretised DFCM multiexponential decay function shows the presence an extra exponential decay term with the same lifetime as the reference fluorophore that we denote as the residual reference component. This extra decay component arises as a result of the discretised convolution of one of the two terms in the modified model function required by the DFCM. The effect of the residual reference component becomes more pronounced when the fluorescence lifetime of the reference is longer than all of the individual components of the specimen under inspection and when the temporal sampling interval is not negligible compared to the quantity (τR (-1) - τ(-1))(-1), where τR and τ are the fluorescence lifetimes of the reference and the specimen respectively. It is shown that the unwanted residual reference component results in systematic errors when fitting simulated data and that these errors are not present when the proposed correction is applied. The correction is also verified using real data obtained from experiment.

Selection of neural network structure for system error correction of electro-optical tracker system with horizontal gimbal

NASA Astrophysics Data System (ADS)

Liu, Xing-fa; Cen, Ming

2007-12-01

Neural Network system error correction method is more precise than lest square system error correction method and spheric harmonics function system error correction method. The accuracy of neural network system error correction method is mainly related to the frame of Neural Network. Analysis and simulation prove that both BP neural network system error correction method and RBF neural network system error correction method have high correction accuracy; it is better to use RBF Network system error correction method than BP Network system error correction method for little studying stylebook considering training rate and neural network scale.

An investigation of error characteristics and coding performance

NASA Technical Reports Server (NTRS)

Ebel, William J.; Ingels, Frank M.

1993-01-01

The first year's effort on NASA Grant NAG5-2006 was an investigation to characterize typical errors resulting from the EOS dorn link. The analysis methods developed for this effort were used on test data from a March 1992 White Sands Terminal Test. The effectiveness of a concatenated coding scheme of a Reed Solomon outer code and a convolutional inner code versus a Reed Solomon only code scheme has been investigated as well as the effectiveness of a Periodic Convolutional Interleaver in dispersing errors of certain types. The work effort consisted of development of software that allows simulation studies with the appropriate coding schemes plus either simulated data with errors or actual data with errors. The software program is entitled Communication Link Error Analysis (CLEAN) and models downlink errors, forward error correcting schemes, and interleavers.

Fully Convolutional Networks for Ground Classification from LIDAR Point Clouds

NASA Astrophysics Data System (ADS)

Rizaldy, A.; Persello, C.; Gevaert, C. M.; Oude Elberink, S. J.

2018-05-01

Deep Learning has been massively used for image classification in recent years. The use of deep learning for ground classification from LIDAR point clouds has also been recently studied. However, point clouds need to be converted into an image in order to use Convolutional Neural Networks (CNNs). In state-of-the-art techniques, this conversion is slow because each point is converted into a separate image. This approach leads to highly redundant computation during conversion and classification. The goal of this study is to design a more efficient data conversion and ground classification. This goal is achieved by first converting the whole point cloud into a single image. The classification is then performed by a Fully Convolutional Network (FCN), a modified version of CNN designed for pixel-wise image classification. The proposed method is significantly faster than state-of-the-art techniques. On the ISPRS Filter Test dataset, it is 78 times faster for conversion and 16 times faster for classification. Our experimental analysis on the same dataset shows that the proposed method results in 5.22 % of total error, 4.10 % of type I error, and 15.07 % of type II error. Compared to the previous CNN-based technique and LAStools software, the proposed method reduces the total error and type I error (while type II error is slightly higher). The method was also tested on a very high point density LIDAR point clouds resulting in 4.02 % of total error, 2.15 % of type I error and 6.14 % of type II error.

VLSI single-chip (255,223) Reed-Solomon encoder with interleaver

NASA Technical Reports Server (NTRS)

Hsu, In-Shek (Inventor); Deutsch, Leslie J. (Inventor); Truong, Trieu-Kie (Inventor); Reed, Irving S. (Inventor)

1990-01-01

The invention relates to a concatenated Reed-Solomon/convolutional encoding system consisting of a Reed-Solomon outer code and a convolutional inner code for downlink telemetry in space missions, and more particularly to a Reed-Solomon encoder with programmable interleaving of the information symbols and code correction symbols to combat error bursts in the Viterbi decoder.

Segmentation of corneal endothelium images using a U-Net-based convolutional neural network.

PubMed

Fabijańska, Anna

2018-04-18

Diagnostic information regarding the health status of the corneal endothelium may be obtained by analyzing the size and the shape of the endothelial cells in specular microscopy images. Prior to the analysis, the endothelial cells need to be extracted from the image. Up to today, this has been performed manually or semi-automatically. Several approaches to automatic segmentation of endothelial cells exist; however, none of them is perfect. Therefore this paper proposes to perform cell segmentation using a U-Net-based convolutional neural network. Particularly, the network is trained to discriminate pixels located at the borders between cells. The edge probability map outputted by the network is next binarized and skeletonized in order to obtain one-pixel wide edges. The proposed solution was tested on a dataset consisting of 30 corneal endothelial images presenting cells of different sizes, achieving an AUROC level of 0.92. The resulting DICE is on average equal to 0.86, which is a good result, regarding the thickness of the compared edges. The corresponding mean absolute percentage error of cell number is at the level of 4.5% which confirms the high accuracy of the proposed approach. The resulting cell edges are well aligned to the ground truths and require a limited number of manual corrections. This also results in accurate values of the cell morphometric parameters. The corresponding errors range from 5.2% for endothelial cell density, through 6.2% for cell hexagonality to 11.93% for the coefficient of variation of the cell size. Copyright © 2018 Elsevier B.V. All rights reserved.

A fully convolutional networks (FCN) based image segmentation algorithm in binocular imaging system

NASA Astrophysics Data System (ADS)

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.

Applications of deep convolutional neural networks to digitized natural history collections.

PubMed

Schuettpelz, Eric; Frandsen, Paul B; Dikow, Rebecca B; Brown, Abel; Orli, Sylvia; Peters, Melinda; Metallo, Adam; Funk, Vicki A; Dorr, Laurence J

2017-01-01

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.

Vision-based mobile robot navigation through deep convolutional neural networks and end-to-end learning

NASA Astrophysics Data System (ADS)

Zhang, Yachu; Zhao, Yuejin; Liu, Ming; Dong, Liquan; Kong, Lingqin; Liu, Lingling

2017-09-01

In contrast to humans, who use only visual information for navigation, many mobile robots use laser scanners and ultrasonic sensors along with vision cameras to navigate. This work proposes a vision-based robot control algorithm based on deep convolutional neural networks. We create a large 15-layer convolutional neural network learning system and achieve the advanced recognition performance. Our system is trained from end to end to map raw input images to direction in supervised mode. The images of data sets are collected in a wide variety of weather conditions and lighting conditions. Besides, the data sets are augmented by adding Gaussian noise and Salt-and-pepper noise to avoid overfitting. The algorithm is verified by two experiments, which are line tracking and obstacle avoidance. The line tracking experiment is proceeded in order to track the desired path which is composed of straight and curved lines. The goal of obstacle avoidance experiment is to avoid the obstacles indoor. Finally, we get 3.29% error rate on the training set and 5.1% error rate on the test set in the line tracking experiment, 1.8% error rate on the training set and less than 5% error rate on the test set in the obstacle avoidance experiment. During the actual test, the robot can follow the runway centerline outdoor and avoid the obstacle in the room accurately. The result confirms the effectiveness of the algorithm and our improvement in the network structure and train parameters

Performance of MIMO-OFDM using convolution codes with QAM modulation

NASA Astrophysics Data System (ADS)

Astawa, I. Gede Puja; Moegiharto, Yoedy; Zainudin, Ahmad; Salim, Imam Dui Agus; Anggraeni, Nur Annisa

2014-04-01

Performance of Orthogonal Frequency Division Multiplexing (OFDM) system can be improved by adding channel coding (error correction code) to detect and correct errors that occur during data transmission. One can use the convolution code. This paper present performance of OFDM using Space Time Block Codes (STBC) diversity technique use QAM modulation with code rate ½. The evaluation is done by analyzing the value of Bit Error Rate (BER) vs Energy per Bit to Noise Power Spectral Density Ratio (Eb/No). This scheme is conducted 256 subcarrier which transmits Rayleigh multipath fading channel in OFDM system. To achieve a BER of 10-3 is required 10dB SNR in SISO-OFDM scheme. For 2×2 MIMO-OFDM scheme requires 10 dB to achieve a BER of 10-3. For 4×4 MIMO-OFDM scheme requires 5 dB while adding convolution in a 4x4 MIMO-OFDM can improve performance up to 0 dB to achieve the same BER. This proves the existence of saving power by 3 dB of 4×4 MIMO-OFDM system without coding, power saving 7 dB of 2×2 MIMO-OFDM and significant power savings from SISO-OFDM system.

Rock images classification by using deep convolution neural network

NASA Astrophysics Data System (ADS)

Cheng, Guojian; Guo, Wenhui

2017-08-01

Granularity analysis is one of the most essential issues in authenticate under microscope. To improve the efficiency and accuracy of traditional manual work, an convolutional neural network based method is proposed for granularity analysis from thin section image, which chooses and extracts features from image samples while build classifier to recognize granularity of input image samples. 4800 samples from Ordos basin are used for experiments under colour spaces of HSV, YCbCr and RGB respectively. On the test dataset, the correct rate in RGB colour space is 98.5%, and it is believable in HSV and YCbCr colour space. The results show that the convolution neural network can classify the rock images with high reliability.

Attenuation correction for brain PET imaging using deep neural network based on dixon and ZTE MR images.

PubMed

Gong, Kuang; Yang, Jaewon; Kim, Kyungsang; El Fakhri, Georges; Seo, Youngho; Li, Quanzheng

2018-05-23

Positron Emission Tomography (PET) is a functional imaging modality widely used in neuroscience studies. To obtain meaningful quantitative results from PET images, attenuation correction is necessary during image reconstruction. For PET/MR hybrid systems, PET attenuation is challenging as Magnetic Resonance (MR) images do not reflect attenuation coefficients directly. To address this issue, we present deep neural network methods to derive the continuous attenuation coefficients for brain PET imaging from MR images. With only Dixon MR images as the network input, the existing U-net structure was adopted and analysis using forty patient data sets shows it is superior than other Dixon based methods. When both Dixon and zero echo time (ZTE) images are available, we have proposed a modified U-net structure, named GroupU-net, to efficiently make use of both Dixon and ZTE information through group convolution modules when the network goes deeper. Quantitative analysis based on fourteen real patient data sets demonstrates that both network approaches can perform better than the standard methods, and the proposed network structure can further reduce the PET quantification error compared to the U-net structure. © 2018 Institute of Physics and Engineering in Medicine.

Applications of deep convolutional neural networks to digitized natural history collections

PubMed Central

Frandsen, Paul B.; Dikow, Rebecca B.; Brown, Abel; Orli, Sylvia; Peters, Melinda; Metallo, Adam; Funk, Vicki A.; Dorr, Laurence J.

2017-01-01

Abstract 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. PMID:29200929

New coding advances for deep space communications

NASA Technical Reports Server (NTRS)

Yuen, Joseph H.

1987-01-01

Advances made in error-correction coding for deep space communications are described. The code believed to be the best is a (15, 1/6) convolutional code, with maximum likelihood decoding; when it is concatenated with a 10-bit Reed-Solomon code, it achieves a bit error rate of 10 to the -6th, at a bit SNR of 0.42 dB. This code outperforms the Voyager code by 2.11 dB. The use of source statics in decoding convolutionally encoded Voyager images from the Uranus encounter is investigated, and it is found that a 2 dB decoding gain can be achieved.

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

PubMed Central

Kang, Guixia; Hou, Beibei; Zhang, Ningbo

2017-01-01

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

Development of an LSI maximum-likelihood convolutional decoder for advanced forward error correction capability on the NASA 30/20 GHz program

NASA Technical Reports Server (NTRS)

Clark, R. T.; Mccallister, R. D.

1982-01-01

The particular coding option identified as providing the best level of coding gain performance in an LSI-efficient implementation was the optimal constraint length five, rate one-half convolutional code. To determine the specific set of design parameters which optimally matches this decoder to the LSI constraints, a breadboard MCD (maximum-likelihood convolutional decoder) was fabricated and used to generate detailed performance trade-off data. The extensive performance testing data gathered during this design tradeoff study are summarized, and the functional and physical MCD chip characteristics are presented.

The Application of Social Characteristic and L1 Optimization in the Error Correction for Network Coding in Wireless Sensor Networks

PubMed Central

Zhang, Guangzhi; Cai, Shaobin; Xiong, Naixue

2018-01-01

One of the remarkable challenges about Wireless Sensor Networks (WSN) is how to transfer the collected data efficiently due to energy limitation of sensor nodes. Network coding will increase network throughput of WSN dramatically due to the broadcast nature of WSN. However, the network coding usually propagates a single original error over the whole network. Due to the special property of error propagation in network coding, most of error correction methods cannot correct more than C/2 corrupted errors where C is the max flow min cut of the network. To maximize the effectiveness of network coding applied in WSN, a new error-correcting mechanism to confront the propagated error is urgently needed. Based on the social network characteristic inherent in WSN and L1 optimization, we propose a novel scheme which successfully corrects more than C/2 corrupted errors. What is more, even if the error occurs on all the links of the network, our scheme also can correct errors successfully. With introducing a secret channel and a specially designed matrix which can trap some errors, we improve John and Yi’s model so that it can correct the propagated errors in network coding which usually pollute exactly 100% of the received messages. Taking advantage of the social characteristic inherent in WSN, we propose a new distributed approach that establishes reputation-based trust among sensor nodes in order to identify the informative upstream sensor nodes. With referred theory of social networks, the informative relay nodes are selected and marked with high trust value. The two methods of L1 optimization and utilizing social characteristic coordinate with each other, and can correct the propagated error whose fraction is even exactly 100% in WSN where network coding is performed. The effectiveness of the error correction scheme is validated through simulation experiments. PMID:29401668

The Application of Social Characteristic and L1 Optimization in the Error Correction for Network Coding in Wireless Sensor Networks.

PubMed

Zhang, Guangzhi; Cai, Shaobin; Xiong, Naixue

2018-02-03

One of the remarkable challenges about Wireless Sensor Networks (WSN) is how to transfer the collected data efficiently due to energy limitation of sensor nodes. Network coding will increase network throughput of WSN dramatically due to the broadcast nature of WSN. However, the network coding usually propagates a single original error over the whole network. Due to the special property of error propagation in network coding, most of error correction methods cannot correct more than C /2 corrupted errors where C is the max flow min cut of the network. To maximize the effectiveness of network coding applied in WSN, a new error-correcting mechanism to confront the propagated error is urgently needed. Based on the social network characteristic inherent in WSN and L1 optimization, we propose a novel scheme which successfully corrects more than C /2 corrupted errors. What is more, even if the error occurs on all the links of the network, our scheme also can correct errors successfully. With introducing a secret channel and a specially designed matrix which can trap some errors, we improve John and Yi's model so that it can correct the propagated errors in network coding which usually pollute exactly 100% of the received messages. Taking advantage of the social characteristic inherent in WSN, we propose a new distributed approach that establishes reputation-based trust among sensor nodes in order to identify the informative upstream sensor nodes. With referred theory of social networks, the informative relay nodes are selected and marked with high trust value. The two methods of L1 optimization and utilizing social characteristic coordinate with each other, and can correct the propagated error whose fraction is even exactly 100% in WSN where network coding is performed. The effectiveness of the error correction scheme is validated through simulation experiments.

Throughput and Energy Efficiency of a Cooperative Hybrid ARQ Protocol for Underwater Acoustic Sensor Networks

PubMed Central

Ghosh, Arindam; Lee, Jae-Won; Cho, Ho-Shin

2013-01-01

Due to its efficiency, reliability and better channel and resource utilization, cooperative transmission technologies have been attractive options in underwater as well as terrestrial sensor networks. Their performance can be further improved if merged with forward error correction (FEC) techniques. In this paper, we propose and analyze a retransmission protocol named Cooperative-Hybrid Automatic Repeat reQuest (C-HARQ) for underwater acoustic sensor networks, which exploits both the reliability of cooperative ARQ (CARQ) and the efficiency of incremental redundancy-hybrid ARQ (IR-HARQ) using rate-compatible punctured convolution (RCPC) codes. Extensive Monte Carlo simulations are performed to investigate the performance of the protocol, in terms of both throughput and energy efficiency. The results clearly reveal the enhancement in performance achieved by the C-HARQ protocol, which outperforms both CARQ and conventional stop and wait ARQ (S&W ARQ). Further, using computer simulations, optimum values of various network parameters are estimated so as to extract the best performance out of the C-HARQ protocol. PMID:24217359

A low-power, high-throughput maximum-likelihood convolutional decoder chip for NASA's 30/20 GHz program

NASA Technical Reports Server (NTRS)

Mccallister, R. D.; Crawford, J. J.

1981-01-01

It is pointed out that the NASA 30/20 GHz program will place in geosynchronous orbit a technically advanced communication satellite which can process time-division multiple access (TDMA) information bursts with a data throughput in excess of 4 GBPS. To guarantee acceptable data quality during periods of signal attenuation it will be necessary to provide a significant forward error correction (FEC) capability. Convolutional decoding (utilizing the maximum-likelihood techniques) was identified as the most attractive FEC strategy. Design trade-offs regarding a maximum-likelihood convolutional decoder (MCD) in a single-chip CMOS implementation are discussed.

An experimental comparison of ETM+ image geometric correction methods in the mountainous areas of Yunnan Province, China

NASA Astrophysics Data System (ADS)

Wang, Jinliang; Wu, Xuejiao

2010-11-01

Geometric correction of imagery is a basic application of remote sensing technology. Its precision will impact directly on the accuracy and reliability of applications. The accuracy of geometric correction depends on many factors, including the used model for correction and the accuracy of the reference map, the number of ground control points (GCP) and its spatial distribution, resampling methods. The ETM+ image of Kunming Dianchi Lake Basin and 1:50000 geographical maps had been used to compare different correction methods. The results showed that: (1) The correction errors were more than one pixel and some of them were several pixels when the polynomial model was used. The correction accuracy was not stable when the Delaunay model was used. The correction errors were less than one pixel when the collinearity equation was used. (2) 6, 9, 25 and 35 GCP were selected randomly for geometric correction using the polynomial correction model respectively, the best result was obtained when 25 GCPs were used. (3) The contrast ratio of image corrected by using nearest neighbor and the best resampling rate was compared to that of using the cubic convolution and bilinear model. But the continuity of pixel gravy value was not very good. The contrast of image corrected was the worst and the computation time was the longest by using the cubic convolution method. According to the above results, the result was the best by using bilinear to resample.

a Novel Deep Convolutional Neural Network for Spectral-Spatial Classification of Hyperspectral Data

NASA Astrophysics Data System (ADS)

Li, N.; Wang, C.; Zhao, H.; Gong, X.; Wang, D.

2018-04-01

Spatial and spectral information are obtained simultaneously by hyperspectral remote sensing. Joint extraction of these information of hyperspectral image is one of most import methods for hyperspectral image classification. In this paper, a novel deep convolutional neural network (CNN) is proposed, which extracts spectral-spatial information of hyperspectral images correctly. The proposed model not only learns sufficient knowledge from the limited number of samples, but also has powerful generalization ability. The proposed framework based on three-dimensional convolution can extract spectral-spatial features of labeled samples effectively. Though CNN has shown its robustness to distortion, it cannot extract features of different scales through the traditional pooling layer that only have one size of pooling window. Hence, spatial pyramid pooling (SPP) is introduced into three-dimensional local convolutional filters for hyperspectral classification. Experimental results with a widely used hyperspectral remote sensing dataset show that the proposed model provides competitive performance.

Very Deep Convolutional Neural Networks for Morphologic Classification of Erythrocytes.

PubMed

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.

Applying Gradient Descent in Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Cui, Nan

2018-04-01

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

Use of FEC coding to improve statistical multiplexing performance for video transport over ATM networks

NASA Astrophysics Data System (ADS)

Kurceren, Ragip; Modestino, James W.

1998-12-01

The use of forward error-control (FEC) coding, possibly in conjunction with ARQ techniques, has emerged as a promising approach for video transport over ATM networks for cell-loss recovery and/or bit error correction, such as might be required for wireless links. Although FEC provides cell-loss recovery capabilities it also introduces transmission overhead which can possibly cause additional cell losses. A methodology is described to maximize the number of video sources multiplexed at a given quality of service (QoS), measured in terms of decoded cell loss probability, using interlaced FEC codes. The transport channel is modelled as a block interference channel (BIC) and the multiplexer as single server, deterministic service, finite buffer supporting N users. Based upon an information-theoretic characterization of the BIC and large deviation bounds on the buffer overflow probability, the described methodology provides theoretically achievable upper limits on the number of sources multiplexed. Performance of specific coding techniques using interlaced nonbinary Reed-Solomon (RS) codes and binary rate-compatible punctured convolutional (RCPC) codes is illustrated.

ID card number detection algorithm based on convolutional neural network

NASA Astrophysics Data System (ADS)

Zhu, Jian; Ma, Hanjie; Feng, Jie; Dai, Leiyan

2018-04-01

In this paper, a new detection algorithm based on Convolutional Neural Network is presented in order to realize the fast and convenient ID information extraction in multiple scenarios. The algorithm uses the mobile device equipped with Android operating system to locate and extract the ID number; Use the special color distribution of the ID card, select the appropriate channel component; Use the image threshold segmentation, noise processing and morphological processing to take the binary processing for image; At the same time, the image rotation and projection method are used for horizontal correction when image was tilting; Finally, the single character is extracted by the projection method, and recognized by using Convolutional Neural Network. Through test shows that, A single ID number image from the extraction to the identification time is about 80ms, the accuracy rate is about 99%, It can be applied to the actual production and living environment.

Transfer Learning with Convolutional Neural Networks for Classification of Abdominal Ultrasound Images.

PubMed

Cheng, Phillip M; Malhi, Harshawn S

2017-04-01

The purpose of this study is to evaluate transfer learning with deep convolutional neural networks for the classification of abdominal ultrasound images. Grayscale images from 185 consecutive clinical abdominal ultrasound studies were categorized into 11 categories based on the text annotation specified by the technologist for the image. Cropped images were rescaled to 256 × 256 resolution and randomized, with 4094 images from 136 studies constituting the training set, and 1423 images from 49 studies constituting the test set. The fully connected layers of two convolutional neural networks based on CaffeNet and VGGNet, previously trained on the 2012 Large Scale Visual Recognition Challenge data set, were retrained on the training set. Weights in the convolutional layers of each network were frozen to serve as fixed feature extractors. Accuracy on the test set was evaluated for each network. A radiologist experienced in abdominal ultrasound also independently classified the images in the test set into the same 11 categories. The CaffeNet network classified 77.3% of the test set images accurately (1100/1423 images), with a top-2 accuracy of 90.4% (1287/1423 images). The larger VGGNet network classified 77.9% of the test set accurately (1109/1423 images), with a top-2 accuracy of VGGNet was 89.7% (1276/1423 images). The radiologist classified 71.7% of the test set images correctly (1020/1423 images). The differences in classification accuracies between both neural networks and the radiologist were statistically significant (p < 0.001). The results demonstrate that transfer learning with convolutional neural networks may be used to construct effective classifiers for abdominal ultrasound images.

Convolution neural networks for real-time needle detection and localization in 2D ultrasound.

PubMed

Mwikirize, Cosmas; Nosher, John L; Hacihaliloglu, Ilker

2018-05-01

We propose a framework for automatic and accurate detection of steeply inserted needles in 2D ultrasound data using convolution neural networks. We demonstrate its application in needle trajectory estimation and tip localization. Our approach consists of a unified network, comprising a fully convolutional network (FCN) and a fast region-based convolutional neural network (R-CNN). The FCN proposes candidate regions, which are then fed to a fast R-CNN for finer needle detection. We leverage a transfer learning paradigm, where the network weights are initialized by training with non-medical images, and fine-tuned with ex vivo ultrasound scans collected during insertion of a 17G epidural needle into freshly excised porcine and bovine tissue at depth settings up to 9 cm and [Formula: see text]-[Formula: see text] insertion angles. Needle detection results are used to accurately estimate needle trajectory from intensity invariant needle features and perform needle tip localization from an intensity search along the needle trajectory. Our needle detection model was trained and validated on 2500 ex vivo ultrasound scans. The detection system has a frame rate of 25 fps on a GPU and achieves 99.6% precision, 99.78% recall rate and an [Formula: see text] score of 0.99. Validation for needle localization was performed on 400 scans collected using a different imaging platform, over a bovine/porcine lumbosacral spine phantom. Shaft localization error of [Formula: see text], tip localization error of [Formula: see text] mm, and a total processing time of 0.58 s were achieved. The proposed method is fully automatic and provides robust needle localization results in challenging scanning conditions. The accurate and robust results coupled with real-time detection and sub-second total processing make the proposed method promising in applications for needle detection and localization during challenging minimally invasive ultrasound-guided procedures.

Modulation/demodulation techniques for satellite communications. Part 1: Background

NASA Technical Reports Server (NTRS)

Omura, J. K.; Simon, M. K.

1981-01-01

Basic characteristics of digital data transmission systems described include the physical communication links, the notion of bandwidth, FCC regulations, and performance measurements such as bit rates, bit error probabilities, throughputs, and delays. The error probability performance and spectral characteristics of various modulation/demodulation techniques commonly used or proposed for use in radio and satellite communication links are summarized. Forward error correction with block or convolutional codes is also discussed along with the important coding parameter, channel cutoff rate.

Kinetic Energy of Hydrocarbons as a Function of Electron Density and Convolutional Neural Networks.

PubMed

Yao, Kun; Parkhill, John

2016-03-08

We demonstrate a convolutional neural network trained to reproduce the Kohn-Sham kinetic energy of hydrocarbons from an input electron density. The output of the network is used as a nonlocal correction to conventional local and semilocal kinetic functionals. We show that this approximation qualitatively reproduces Kohn-Sham potential energy surfaces when used with conventional exchange correlation functionals. The density which minimizes the total energy given by the functional is examined in detail. We identify several avenues to improve on this exploratory work, by reducing numerical noise and changing the structure of our functional. Finally we examine the features in the density learned by the neural network to anticipate the prospects of generalizing these models.

Error control techniques for satellite and space communications

NASA Technical Reports Server (NTRS)

Costello, Daniel J., Jr.

1994-01-01

The unequal error protection capabilities of convolutional and trellis codes are studied. In certain environments, a discrepancy in the amount of error protection placed on different information bits is desirable. Examples of environments which have data of varying importance are a number of speech coding algorithms, packet switched networks, multi-user systems, embedded coding systems, and high definition television. Encoders which provide more than one level of error protection to information bits are called unequal error protection (UEP) codes. In this work, the effective free distance vector, d, is defined as an alternative to the free distance as a primary performance parameter for UEP convolutional and trellis encoders. For a given (n, k), convolutional encoder, G, the effective free distance vector is defined as the k-dimensional vector d = (d(sub 0), d(sub 1), ..., d(sub k-1)), where d(sub j), the j(exp th) effective free distance, is the lowest Hamming weight among all code sequences that are generated by input sequences with at least one '1' in the j(exp th) position. It is shown that, although the free distance for a code is unique to the code and independent of the encoder realization, the effective distance vector is dependent on the encoder realization.

Fully convolutional network with cluster for semantic segmentation

NASA Astrophysics Data System (ADS)

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.

Convolutional coding at 50 Mbps for the Shuttle Ku-band return link

NASA Technical Reports Server (NTRS)

Batson, B. H.; Huth, G. K.

1976-01-01

Error correcting coding is required for 50 Mbps data link from the Shuttle Orbiter through the Tracking and Data Relay Satellite System (TDRSS) to the ground because of severe power limitations. Convolutional coding has been chosen because the decoding algorithms (sequential and Viterbi) provide significant coding gains at the required bit error probability of one in 10 to the sixth power and can be implemented at 50 Mbps with moderate hardware. While a 50 Mbps sequential decoder has been built, the highest data rate achieved for a Viterbi decoder is 10 Mbps. Thus, five multiplexed 10 Mbps Viterbi decoders must be used to provide a 50 Mbps data rate. This paper discusses the tradeoffs which were considered when selecting the multiplexed Viterbi decoder approach for this application.

Accurate lithography simulation model based on convolutional neural networks

NASA Astrophysics Data System (ADS)

Watanabe, Yuki; Kimura, Taiki; Matsunawa, Tetsuaki; Nojima, Shigeki

2017-07-01

Lithography simulation is an essential technique for today's semiconductor manufacturing process. In order to calculate an entire chip in realistic time, compact resist model is commonly used. The model is established for faster calculation. To have accurate compact resist model, it is necessary to fix a complicated non-linear model function. However, it is difficult to decide an appropriate function manually because there are many options. This paper proposes a new compact resist model using CNN (Convolutional Neural Networks) which is one of deep learning techniques. CNN model makes it possible to determine an appropriate model function and achieve accurate simulation. Experimental results show CNN model can reduce CD prediction errors by 70% compared with the conventional model.

Recent advances in coding theory for near error-free communications

NASA Technical Reports Server (NTRS)

Cheung, K.-M.; Deutsch, L. J.; Dolinar, S. J.; Mceliece, R. J.; Pollara, F.; Shahshahani, M.; Swanson, L.

1991-01-01

Channel and source coding theories are discussed. The following subject areas are covered: large constraint length convolutional codes (the Galileo code); decoder design (the big Viterbi decoder); Voyager's and Galileo's data compression scheme; current research in data compression for images; neural networks for soft decoding; neural networks for source decoding; finite-state codes; and fractals for data compression.

Achieving unequal error protection with convolutional codes

NASA Technical Reports Server (NTRS)

Mills, D. G.; Costello, D. J., Jr.; Palazzo, R., Jr.

1994-01-01

This paper examines the unequal error protection capabilities of convolutional codes. Both time-invariant and periodically time-varying convolutional encoders are examined. The effective free distance vector is defined and is shown to be useful in determining the unequal error protection (UEP) capabilities of convolutional codes. A modified transfer function is used to determine an upper bound on the bit error probabilities for individual input bit positions in a convolutional encoder. The bound is heavily dependent on the individual effective free distance of the input bit position. A bound relating two individual effective free distances is presented. The bound is a useful tool in determining the maximum possible disparity in individual effective free distances of encoders of specified rate and memory distribution. The unequal error protection capabilities of convolutional encoders of several rates and memory distributions are determined and discussed.

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

DOE Office of Scientific and Technical Information (OSTI.GOV)

Raj, Sunny; Jha, Sumit Kumar; Pullum, Laura L.

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

Tweaked residual convolutional network for face alignment

NASA Astrophysics Data System (ADS)

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

2017-08-01

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

Quantum Error Correction

NASA Astrophysics Data System (ADS)

Lidar, Daniel A.; Brun, Todd A.

2013-09-01

Prologue; Preface; Part I. Background: 1. Introduction to decoherence and noise in open quantum systems Daniel Lidar and Todd Brun; 2. Introduction to quantum error correction Dave Bacon; 3. Introduction to decoherence-free subspaces and noiseless subsystems Daniel Lidar; 4. Introduction to quantum dynamical decoupling Lorenza Viola; 5. Introduction to quantum fault tolerance Panos Aliferis; Part II. Generalized Approaches to Quantum Error Correction: 6. Operator quantum error correction David Kribs and David Poulin; 7. Entanglement-assisted quantum error-correcting codes Todd Brun and Min-Hsiu Hsieh; 8. Continuous-time quantum error correction Ognyan Oreshkov; Part III. Advanced Quantum Codes: 9. Quantum convolutional codes Mark Wilde; 10. Non-additive quantum codes Markus Grassl and Martin Rötteler; 11. Iterative quantum coding systems David Poulin; 12. Algebraic quantum coding theory Andreas Klappenecker; 13. Optimization-based quantum error correction Andrew Fletcher; Part IV. Advanced Dynamical Decoupling: 14. High order dynamical decoupling Zhen-Yu Wang and Ren-Bao Liu; 15. Combinatorial approaches to dynamical decoupling Martin Rötteler and Pawel Wocjan; Part V. Alternative Quantum Computation Approaches: 16. Holonomic quantum computation Paolo Zanardi; 17. Fault tolerance for holonomic quantum computation Ognyan Oreshkov, Todd Brun and Daniel Lidar; 18. Fault tolerant measurement-based quantum computing Debbie Leung; Part VI. Topological Methods: 19. Topological codes Héctor Bombín; 20. Fault tolerant topological cluster state quantum computing Austin Fowler and Kovid Goyal; Part VII. Applications and Implementations: 21. Experimental quantum error correction Dave Bacon; 22. Experimental dynamical decoupling Lorenza Viola; 23. Architectures Jacob Taylor; 24. Error correction in quantum communication Mark Wilde; Part VIII. Critical Evaluation of Fault Tolerance: 25. Hamiltonian methods in QEC and fault tolerance Eduardo Novais, Eduardo Mucciolo and Harold Baranger; 26. Critique of fault-tolerant quantum information processing Robert Alicki; References; Index.

Peeling Away Timing Error in NetFlow Data

NASA Astrophysics Data System (ADS)

Trammell, Brian; Tellenbach, Bernhard; Schatzmann, Dominik; Burkhart, Martin

In this paper, we characterize, quantify, and correct timing errors introduced into network flow data by collection and export via Cisco NetFlow version 9. We find that while some of these sources of error (clock skew, export delay) are generally implementation-dependent and known in the literature, there is an additional cyclic error of up to one second that is inherent to the design of the export protocol. We present a method for correcting this cyclic error in the presence of clock skew and export delay. In an evaluation using traffic with known timing collected from a national-scale network, we show that this method can successfully correct the cyclic error. However, there can also be other implementation-specific errors for which insufficient information remains for correction. On the routers we have deployed in our network, this limits the accuracy to about 70ms, reinforcing the point that implementation matters when conducting research on network measurement data.

Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm

PubMed Central

McDonnell, Mark D.; Tissera, Migel D.; Vladusich, Tony; van Schaik, André; Tapson, Jonathan

2015-01-01

Recent advances in training deep (multi-layer) architectures have inspired a renaissance in neural network use. For example, deep convolutional networks are becoming the default option for difficult tasks on large datasets, such as image and speech recognition. However, here we show that error rates below 1% on the MNIST handwritten digit benchmark can be replicated with shallow non-convolutional neural networks. This is achieved by training such networks using the ‘Extreme Learning Machine’ (ELM) approach, which also enables a very rapid training time (∼ 10 minutes). Adding distortions, as is common practise for MNIST, reduces error rates even further. Our methods are also shown to be capable of achieving less than 5.5% error rates on the NORB image database. To achieve these results, we introduce several enhancements to the standard ELM algorithm, which individually and in combination can significantly improve performance. The main innovation is to ensure each hidden-unit operates only on a randomly sized and positioned patch of each image. This form of random ‘receptive field’ sampling of the input ensures the input weight matrix is sparse, with about 90% of weights equal to zero. Furthermore, combining our methods with a small number of iterations of a single-batch backpropagation method can significantly reduce the number of hidden-units required to achieve a particular performance. Our close to state-of-the-art results for MNIST and NORB suggest that the ease of use and accuracy of the ELM algorithm for designing a single-hidden-layer neural network classifier should cause it to be given greater consideration either as a standalone method for simpler problems, or as the final classification stage in deep neural networks applied to more difficult problems. PMID:26262687

Parameter estimation for the exponential-normal convolution model for background correction of affymetrix GeneChip data.

PubMed

McGee, Monnie; Chen, Zhongxue

2006-01-01

There are many methods of correcting microarray data for non-biological sources of error. Authors routinely supply software or code so that interested analysts can implement their methods. Even with a thorough reading of associated references, it is not always clear how requisite parts of the method are calculated in the software packages. However, it is important to have an understanding of such details, as this understanding is necessary for proper use of the output, or for implementing extensions to the model. In this paper, the calculation of parameter estimates used in Robust Multichip Average (RMA), a popular preprocessing algorithm for Affymetrix GeneChip brand microarrays, is elucidated. The background correction method for RMA assumes that the perfect match (PM) intensities observed result from a convolution of the true signal, assumed to be exponentially distributed, and a background noise component, assumed to have a normal distribution. A conditional expectation is calculated to estimate signal. Estimates of the mean and variance of the normal distribution and the rate parameter of the exponential distribution are needed to calculate this expectation. Simulation studies show that the current estimates are flawed; therefore, new ones are suggested. We examine the performance of preprocessing under the exponential-normal convolution model using several different methods to estimate the parameters.

Deep Learning: A Primer for Radiologists.

PubMed

Chartrand, Gabriel; Cheng, Phillip M; Vorontsov, Eugene; Drozdzal, Michal; Turcotte, Simon; Pal, Christopher J; Kadoury, Samuel; Tang, An

2017-01-01

Deep learning is a class of machine learning methods that are gaining success and attracting interest in many domains, including computer vision, speech recognition, natural language processing, and playing games. Deep learning methods produce a mapping from raw inputs to desired outputs (eg, image classes). Unlike traditional machine learning methods, which require hand-engineered feature extraction from inputs, deep learning methods learn these features directly from data. With the advent of large datasets and increased computing power, these methods can produce models with exceptional performance. These models are multilayer artificial neural networks, loosely inspired by biologic neural systems. Weighted connections between nodes (neurons) in the network are iteratively adjusted based on example pairs of inputs and target outputs by back-propagating a corrective error signal through the network. For computer vision tasks, convolutional neural networks (CNNs) have proven to be effective. Recently, several clinical applications of CNNs have been proposed and studied in radiology for classification, detection, and segmentation tasks. This article reviews the key concepts of deep learning for clinical radiologists, discusses technical requirements, describes emerging applications in clinical radiology, and outlines limitations and future directions in this field. Radiologists should become familiar with the principles and potential applications of deep learning in medical imaging. © RSNA, 2017.

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

PubMed

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 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.

Deep learning methods to guide CT image reconstruction and reduce metal artifacts

NASA Astrophysics Data System (ADS)

Gjesteby, Lars; Yang, Qingsong; Xi, Yan; Zhou, Ye; Zhang, Junping; Wang, Ge

2017-03-01

The rapidly-rising field of machine learning, including deep learning, has inspired applications across many disciplines. In medical imaging, deep learning has been primarily used for image processing and analysis. In this paper, we integrate a convolutional neural network (CNN) into the computed tomography (CT) image reconstruction process. Our first task is to monitor the quality of CT images during iterative reconstruction and decide when to stop the process according to an intelligent numerical observer instead of using a traditional stopping rule, such as a fixed error threshold or a maximum number of iterations. After training on ground truth images, the CNN was successful in guiding an iterative reconstruction process to yield high-quality images. Our second task is to improve a sinogram to correct for artifacts caused by metal objects. A large number of interpolation and normalization-based schemes were introduced for metal artifact reduction (MAR) over the past four decades. The NMAR algorithm is considered a state-of-the-art method, although residual errors often remain in the reconstructed images, especially in cases of multiple metal objects. Here we merge NMAR with deep learning in the projection domain to achieve additional correction in critical image regions. Our results indicate that deep learning can be a viable tool to address CT reconstruction challenges.

Technical Note: Deep learning based MRAC using rapid ultra-short echo time imaging.

PubMed

Jang, Hyungseok; Liu, Fang; Zhao, Gengyan; Bradshaw, Tyler; McMillan, Alan B

2018-05-15

In this study, we explore the feasibility of a novel framework for MR-based attenuation correction for PET/MR imaging based on deep learning via convolutional neural networks, which enables fully automated and robust estimation of a pseudo CT image based on ultrashort echo time (UTE), fat, and water images obtained by a rapid MR acquisition. MR images for MRAC are acquired using dual echo ramped hybrid encoding (dRHE), where both UTE and out-of-phase echo images are obtained within a short single acquisition (35 sec). Tissue labeling of air, soft tissue, and bone in the UTE image is accomplished via a deep learning network that was pre-trained with T1-weighted MR images. UTE images are used as input to the network, which was trained using labels derived from co-registered CT images. The tissue labels estimated by deep learning are refined by a conditional random field based correction. The soft tissue labels are further separated into fat and water components using the two-point Dixon method. The estimated bone, air, fat, and water images are then assigned appropriate Hounsfield units, resulting in a pseudo CT image for PET attenuation correction. To evaluate the proposed MRAC method, PET/MR imaging of the head was performed on 8 human subjects, where Dice similarity coefficients of the estimated tissue labels and relative PET errors were evaluated through comparison to a registered CT image. Dice coefficients for air (within the head), soft tissue, and bone labels were 0.76±0.03, 0.96±0.006, and 0.88±0.01. In PET quantification, the proposed MRAC method produced relative PET errors less than 1% within most brain regions. The proposed MRAC method utilizing deep learning with transfer learning and an efficient dRHE acquisition enables reliable PET quantification with accurate and rapid pseudo CT generation. This article is protected by copyright. All rights reserved. This article is protected by copyright. All rights reserved.

Training Deep Spiking Neural Networks Using Backpropagation.

PubMed

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

2016-01-01

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

Automatic Gleason grading of H and E stained microscopic prostate images using deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Gummeson, Anna; Arvidsson, Ida; Ohlsson, Mattias; Overgaard, Niels C.; Krzyzanowska, Agnieszka; Heyden, Anders; Bjartell, Anders; Aström, Kalle

2017-03-01

Prostate cancer is the most diagnosed cancer in men. The diagnosis is confirmed by pathologists based on ocular inspection of prostate biopsies in order to classify them according to Gleason score. The main goal of this paper is to automate the classification using convolutional neural networks (CNNs). The introduction of CNNs has broadened the field of pattern recognition. It replaces the classical way of designing and extracting hand-made features used for classification with the substantially different strategy of letting the computer itself decide which features are of importance. For automated prostate cancer classification into the classes: Benign, Gleason grade 3, 4 and 5 we propose a CNN with small convolutional filters that has been trained from scratch using stochastic gradient descent with momentum. The input consists of microscopic images of haematoxylin and eosin stained tissue, the output is a coarse segmentation into regions of the four different classes. The dataset used consists of 213 images, each considered to be of one class only. Using four-fold cross-validation we obtained an error rate of 7.3%, which is significantly better than previous state of the art using the same dataset. Although the dataset was rather small, good results were obtained. From this we conclude that CNN is a promising method for this problem. Future work includes obtaining a larger dataset, which potentially could diminish the error margin.

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

NASA Astrophysics Data System (ADS)

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%.

Research on image retrieval using deep convolutional neural network combining L1 regularization and PRelu activation function

NASA Astrophysics Data System (ADS)

QingJie, Wei; WenBin, Wang

2017-06-01

In this paper, the image retrieval using deep convolutional neural network combined with regularization and PRelu activation function is studied, and improves image retrieval accuracy. Deep convolutional neural network can not only simulate the process of human brain to receive and transmit information, but also contains a convolution operation, which is very suitable for processing images. Using deep convolutional neural network is better than direct extraction of image visual features for image retrieval. However, the structure of deep convolutional neural network is complex, and it is easy to over-fitting and reduces the accuracy of image retrieval. In this paper, we combine L1 regularization and PRelu activation function to construct a deep convolutional neural network to prevent over-fitting of the network and improve the accuracy of image retrieval

Convolutional neural network with transfer learning for rice type classification

NASA Astrophysics Data System (ADS)

Patel, Vaibhav Amit; Joshi, Manjunath V.

2018-04-01

Presently, rice type is identified manually by humans, which is time consuming and error prone. Therefore, there is a need to do this by machine which makes it faster with greater accuracy. This paper proposes a deep learning based method for classification of rice types. We propose two methods to classify the rice types. In the first method, we train a deep convolutional neural network (CNN) using the given segmented rice images. In the second method, we train a combination of a pretrained VGG16 network and the proposed method, while using transfer learning in which the weights of a pretrained network are used to achieve better accuracy. Our approach can also be used for classification of rice grain as broken or fine. We train a 5-class model for classifying rice types using 4000 training images and another 2- class model for the classification of broken and normal rice using 1600 training images. We observe that despite having distinct rice images, our architecture, pretrained on ImageNet data boosts classification accuracy significantly.

Rate-compatible punctured convolutional codes (RCPC codes) and their applications

NASA Astrophysics Data System (ADS)

Hagenauer, Joachim

1988-04-01

The concept of punctured convolutional codes is extended by punctuating a low-rate 1/N code periodically with period P to obtain a family of codes with rate P/(P + l), where l can be varied between 1 and (N - 1)P. A rate-compatibility restriction on the puncturing tables ensures that all code bits of high rate codes are used by the lower-rate codes. This allows transmission of incremental redundancy in ARQ/FEC (automatic repeat request/forward error correction) schemes and continuous rate variation to change from low to high error protection within a data frame. Families of RCPC codes with rates between 8/9 and 1/4 are given for memories M from 3 to 6 (8 to 64 trellis states) together with the relevant distance spectra. These codes are almost as good as the best known general convolutional codes of the respective rates. It is shown that the same Viterbi decoder can be used for all RCPC codes of the same M. The application of RCPC codes to hybrid ARQ/FEC schemes is discussed for Gaussian and Rayleigh fading channels using channel-state information to optimize throughput.

Performance of Serially Concatenated Convolutional Codes with Binary Modulation in AWGN and Noise Jamming over Rayleigh Fading Channels

DTIC Science & Technology

2001-09-01

Rate - compatible punctured convolutional codes (RCPC codes ) and their applications,” IEEE...ABSTRACT In this dissertation, the bit error rates for serially concatenated convolutional codes (SCCC) for both BPSK and DPSK modulation with...INTENTIONALLY LEFT BLANK i EXECUTIVE SUMMARY In this dissertation, the bit error rates of serially concatenated convolutional codes

ELHnet: a convolutional neural network for classifying cochlear endolymphatic hydrops imaged with optical coherence tomography.

PubMed

Liu, George S; Zhu, Michael H; Kim, Jinkyung; Raphael, Patrick; Applegate, Brian E; Oghalai, John S

2017-10-01

Detection of endolymphatic hydrops is important for diagnosing Meniere's disease, and can be performed non-invasively using optical coherence tomography (OCT) in animal models as well as potentially in the clinic. Here, we developed ELHnet, a convolutional neural network to classify endolymphatic hydrops in a mouse model using learned features from OCT images of mice cochleae. We trained ELHnet on 2159 training and validation images from 17 mice, using only the image pixels and observer-determined labels of endolymphatic hydrops as the inputs. We tested ELHnet on 37 images from 37 mice that were previously not used, and found that the neural network correctly classified 34 of the 37 mice. This demonstrates an improvement in performance from previous work on computer-aided classification of endolymphatic hydrops. To the best of our knowledge, this is the first deep CNN designed for endolymphatic hydrops classification.

ELHnet: a convolutional neural network for classifying cochlear endolymphatic hydrops imaged with optical coherence tomography

PubMed Central

Liu, George S.; Zhu, Michael H.; Kim, Jinkyung; Raphael, Patrick; Applegate, Brian E.; Oghalai, John S.

2017-01-01

Detection of endolymphatic hydrops is important for diagnosing Meniere’s disease, and can be performed non-invasively using optical coherence tomography (OCT) in animal models as well as potentially in the clinic. Here, we developed ELHnet, a convolutional neural network to classify endolymphatic hydrops in a mouse model using learned features from OCT images of mice cochleae. We trained ELHnet on 2159 training and validation images from 17 mice, using only the image pixels and observer-determined labels of endolymphatic hydrops as the inputs. We tested ELHnet on 37 images from 37 mice that were previously not used, and found that the neural network correctly classified 34 of the 37 mice. This demonstrates an improvement in performance from previous work on computer-aided classification of endolymphatic hydrops. To the best of our knowledge, this is the first deep CNN designed for endolymphatic hydrops classification. PMID:29082086

Semantic segmentation of mFISH images using convolutional networks.

PubMed

Pardo, Esteban; Morgado, José Mário T; Malpica, Norberto

2018-04-30

Multicolor in situ hybridization (mFISH) is a karyotyping technique used to detect major chromosomal alterations using fluorescent probes and imaging techniques. Manual interpretation of mFISH images is a time consuming step that can be automated using machine learning; in previous works, pixel or patch wise classification was employed, overlooking spatial information which can help identify chromosomes. In this work, we propose a fully convolutional semantic segmentation network for the interpretation of mFISH images, which uses both spatial and spectral information to classify each pixel in an end-to-end fashion. The semantic segmentation network developed was tested on samples extracted from a public dataset using cross validation. Despite having no labeling information of the image it was tested on, our algorithm yielded an average correct classification ratio (CCR) of 87.41%. Previously, this level of accuracy was only achieved with state of the art algorithms when classifying pixels from the same image in which the classifier has been trained. These results provide evidence that fully convolutional semantic segmentation networks may be employed in the computer aided diagnosis of genetic diseases with improved performance over the current image analysis methods. © 2018 International Society for Advancement of Cytometry. © 2018 International Society for Advancement of Cytometry.

Error-correcting codes on scale-free networks

NASA Astrophysics Data System (ADS)

Kim, Jung-Hoon; Ko, Young-Jo

2004-06-01

We investigate the potential of scale-free networks as error-correcting codes. We find that irregular low-density parity-check codes with the highest performance known to date have degree distributions well fitted by a power-law function p (k) ˜ k-γ with γ close to 2, which suggests that codes built on scale-free networks with appropriate power exponents can be good error-correcting codes, with a performance possibly approaching the Shannon limit. We demonstrate for an erasure channel that codes with a power-law degree distribution of the form p (k) = C (k+α)-γ , with k⩾2 and suitable selection of the parameters α and γ , indeed have very good error-correction capabilities.

Deep learning in breast cancer risk assessment: evaluation of convolutional neural networks on a clinical dataset of full-field digital mammograms.

PubMed

Li, Hui; Giger, Maryellen L; Huynh, Benjamin Q; Antropova, Natalia O

2017-10-01

To evaluate deep learning in the assessment of breast cancer risk in which convolutional neural networks (CNNs) with transfer learning are used to extract parenchymal characteristics directly from full-field digital mammographic (FFDM) images instead of using computerized radiographic texture analysis (RTA), 456 clinical FFDM cases were included: a "high-risk" BRCA1/2 gene-mutation carriers dataset (53 cases), a "high-risk" unilateral cancer patients dataset (75 cases), and a "low-risk dataset" (328 cases). Deep learning was compared to the use of features from RTA, as well as to a combination of both in the task of distinguishing between high- and low-risk subjects. Similar classification performances were obtained using CNN [area under the curve [Formula: see text]; standard error [Formula: see text

Characterizing the velocity of a wandering black hole and properties of the surrounding medium using convolutional neural networks

NASA Astrophysics Data System (ADS)

González, J. A.; Guzmán, F. S.

2018-03-01

We present a method for estimating the velocity of a wandering black hole and the equation of state for the gas around it based on a catalog of numerical simulations. The method uses machine-learning methods based on convolutional neural networks applied to the classification of images resulting from numerical simulations. Specifically we focus on the supersonic velocity regime and choose the direction of the black hole to be parallel to its spin. We build a catalog of 900 simulations by numerically solving Euler's equations onto the fixed space-time background of a black hole, for two parameters: the adiabatic index Γ with values in the range [1.1, 5 /3 ], and the asymptotic relative velocity of the black hole with respect to the surroundings v∞, with values within [0.2 ,0.8 ]c . For each simulation we produce a 2D image of the gas density once the process of accretion has approached a stationary regime. The results obtained show that the implemented convolutional neural networks are able to correctly classify the adiabatic index 87.78% of the time within an uncertainty of ±0.0284 , while the prediction of the velocity is correct 96.67% of the time within an uncertainty of ±0.03 c . We expect that this combination of a massive number of numerical simulations and machine-learning methods will help us analyze more complicated scenarios related to future high-resolution observations of black holes, like those from the Event Horizon Telescope.

Accounting for optical errors in microtensiometry.

PubMed

Hinton, Zachary R; Alvarez, Nicolas J

2018-09-15

Drop shape analysis (DSA) techniques measure interfacial tension subject to error in image analysis and the optical system. While considerable efforts have been made to minimize image analysis errors, very little work has treated optical errors. There are two main sources of error when considering the optical system: the angle of misalignment and the choice of focal plane. Due to the convoluted nature of these sources, small angles of misalignment can lead to large errors in measured curvature. We demonstrate using microtensiometry the contributions of these sources to measured errors in radius, and, more importantly, deconvolute the effects of misalignment and focal plane. Our findings are expected to have broad implications on all optical techniques measuring interfacial curvature. A geometric model is developed to analytically determine the contributions of misalignment angle and choice of focal plane on measurement error for spherical cap interfaces. This work utilizes a microtensiometer to validate the geometric model and to quantify the effect of both sources of error. For the case of a microtensiometer, an empirical calibration is demonstrated that corrects for optical errors and drastically simplifies implementation. The combination of geometric modeling and experimental results reveal a convoluted relationship between the true and measured interfacial radius as a function of the misalignment angle and choice of focal plane. The validated geometric model produces a full operating window that is strongly dependent on the capillary radius and spherical cap height. In all cases, the contribution of optical errors is minimized when the height of the spherical cap is equivalent to the capillary radius, i.e. a hemispherical interface. The understanding of these errors allow for correct measure of interfacial curvature and interfacial tension regardless of experimental setup. For the case of microtensiometry, this greatly decreases the time for experimental setup and increases experiential accuracy. In a broad sense, this work outlines the importance of optical errors in all DSA techniques. More specifically, these results have important implications for all microscale and microfluidic measurements of interface curvature. Copyright © 2018 Elsevier Inc. All rights reserved.

Neurometaplasticity: Glucoallostasis control of plasticity of the neural networks of error commission, detection, and correction modulates neuroplasticity to influence task precision

NASA Astrophysics Data System (ADS)

Welcome, Menizibeya O.; Dane, Şenol; Mastorakis, Nikos E.; Pereverzev, Vladimir A.

2017-12-01

The term "metaplasticity" is a recent one, which means plasticity of synaptic plasticity. Correspondingly, neurometaplasticity simply means plasticity of neuroplasticity, indicating that a previous plastic event determines the current plasticity of neurons. Emerging studies suggest that neurometaplasticity underlie many neural activities and neurobehavioral disorders. In our previous work, we indicated that glucoallostasis is essential for the control of plasticity of the neural network that control error commission, detection and correction. Here we review recent works, which suggest that task precision depends on the modulatory effects of neuroplasticity on the neural networks of error commission, detection, and correction. Furthermore, we discuss neurometaplasticity and its role in error commission, detection, and correction.

Information Theory, Inference and Learning Algorithms

NASA Astrophysics Data System (ADS)

Mackay, David J. C.

2003-10-01

Information theory and inference, often taught separately, are here united in one entertaining textbook. These topics lie at the heart of many exciting areas of contemporary science and engineering - communication, signal processing, data mining, machine learning, pattern recognition, computational neuroscience, bioinformatics, and cryptography. This textbook introduces theory in tandem with applications. Information theory is taught alongside practical communication systems, such as arithmetic coding for data compression and sparse-graph codes for error-correction. A toolbox of inference techniques, including message-passing algorithms, Monte Carlo methods, and variational approximations, are developed alongside applications of these tools to clustering, convolutional codes, independent component analysis, and neural networks. The final part of the book describes the state of the art in error-correcting codes, including low-density parity-check codes, turbo codes, and digital fountain codes -- the twenty-first century standards for satellite communications, disk drives, and data broadcast. Richly illustrated, filled with worked examples and over 400 exercises, some with detailed solutions, David MacKay's groundbreaking book is ideal for self-learning and for undergraduate or graduate courses. Interludes on crosswords, evolution, and sex provide entertainment along the way. In sum, this is a textbook on information, communication, and coding for a new generation of students, and an unparalleled entry point into these subjects for professionals in areas as diverse as computational biology, financial engineering, and machine learning.

Automatic classification of ovarian cancer types from cytological images using deep convolutional neural networks.

PubMed

Wu, Miao; Yan, Chuanbo; Liu, Huiqiang; Liu, Qian

2018-06-29

Ovarian cancer is one of the most common gynecologic malignancies. Accurate classification of ovarian cancer types (serous carcinoma, mucous carcinoma, endometrioid carcinoma, transparent cell carcinoma) is an essential part in the different diagnosis. Computer-aided diagnosis (CADx) can provide useful advice for pathologists to determine the diagnosis correctly. In our study, we employed a Deep Convolutional Neural Networks (DCNN) based on AlexNet to automatically classify the different types of ovarian cancers from cytological images. The DCNN consists of five convolutional layers, three max pooling layers, and two full reconnect layers. Then we trained the model by two group input data separately, one was original image data and the other one was augmented image data including image enhancement and image rotation. The testing results are obtained by the method of 10-fold cross-validation, showing that the accuracy of classification models has been improved from 72.76 to 78.20% by using augmented images as training data. The developed scheme was useful for classifying ovarian cancers from cytological images. © 2018 The Author(s).

Minimal-memory realization of pearl-necklace encoders of general quantum convolutional codes

DOE Office of Scientific and Technical Information (OSTI.GOV)

Houshmand, Monireh; Hosseini-Khayat, Saied

2011-02-15

Quantum convolutional codes, like their classical counterparts, promise to offer higher error correction performance than block codes of equivalent encoding complexity, and are expected to find important applications in reliable quantum communication where a continuous stream of qubits is transmitted. Grassl and Roetteler devised an algorithm to encode a quantum convolutional code with a ''pearl-necklace'' encoder. Despite their algorithm's theoretical significance as a neat way of representing quantum convolutional codes, it is not well suited to practical realization. In fact, there is no straightforward way to implement any given pearl-necklace structure. This paper closes the gap between theoretical representation andmore » practical implementation. In our previous work, we presented an efficient algorithm to find a minimal-memory realization of a pearl-necklace encoder for Calderbank-Shor-Steane (CSS) convolutional codes. This work is an extension of our previous work and presents an algorithm for turning a pearl-necklace encoder for a general (non-CSS) quantum convolutional code into a realizable quantum convolutional encoder. We show that a minimal-memory realization depends on the commutativity relations between the gate strings in the pearl-necklace encoder. We find a realization by means of a weighted graph which details the noncommutative paths through the pearl necklace. The weight of the longest path in this graph is equal to the minimal amount of memory needed to implement the encoder. The algorithm has a polynomial-time complexity in the number of gate strings in the pearl-necklace encoder.« less

Keypoint Density-Based Region Proposal for Fine-Grained Object Detection and Classification Using Regions with Convolutional Neural Network Features

DTIC Science & Technology

2015-12-15

Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network ... Convolutional Neural Networks (CNNs) enable them to outperform conventional techniques on standard object detection and classification tasks, their...detection accuracy and speed on the fine-grained Caltech UCSD bird dataset (Wah et al., 2011). Recently, Convolutional Neural Networks (CNNs), a deep

Neural network error correction for solving coupled ordinary differential equations

NASA Technical Reports Server (NTRS)

Shelton, R. O.; Darsey, J. A.; Sumpter, B. G.; Noid, D. W.

1992-01-01

A neural network is presented to learn errors generated by a numerical algorithm for solving coupled nonlinear differential equations. The method is based on using a neural network to correctly learn the error generated by, for example, Runge-Kutta on a model molecular dynamics (MD) problem. The neural network programs used in this study were developed by NASA. Comparisons are made for training the neural network using backpropagation and a new method which was found to converge with fewer iterations. The neural net programs, the MD model and the calculations are discussed.

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

PubMed

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 fine granularities, based on fMRI data. Copyright © 2017 Elsevier B.V. All rights reserved.

Deep multi-scale convolutional neural network for hyperspectral image classification

NASA Astrophysics Data System (ADS)

Zhang, Feng-zhe; Yang, Xia

2018-04-01

In this paper, we proposed a multi-scale convolutional neural network for hyperspectral image classification task. Firstly, compared with conventional convolution, we utilize multi-scale convolutions, which possess larger respective fields, to extract spectral features of hyperspectral image. We design a deep neural network with a multi-scale convolution layer which contains 3 different convolution kernel sizes. Secondly, to avoid overfitting of deep neural network, dropout is utilized, which randomly sleeps neurons, contributing to improve the classification accuracy a bit. In addition, new skills like ReLU in deep learning is utilized in this paper. We conduct experiments on University of Pavia and Salinas datasets, and obtained better classification accuracy compared with other methods.

Some partial-unit-memory convolutional codes

NASA Technical Reports Server (NTRS)

Abdel-Ghaffar, K.; Mceliece, R. J.; Solomon, G.

1991-01-01

The results of a study on a class of error correcting codes called partial unit memory (PUM) codes are presented. This class of codes, though not entirely new, has until now remained relatively unexplored. The possibility of using the well developed theory of block codes to construct a large family of promising PUM codes is shown. The performance of several specific PUM codes are compared with that of the Voyager standard (2, 1, 6) convolutional code. It was found that these codes can outperform the Voyager code with little or no increase in decoder complexity. This suggests that there may very well be PUM codes that can be used for deep space telemetry that offer both increased performance and decreased implementational complexity over current coding systems.

Reduction of metal artifacts in x-ray CT images using a convolutional neural network

NASA Astrophysics Data System (ADS)

Zhang, Yanbo; Chu, Ying; Yu, Hengyong

2017-09-01

Patients usually contain various metallic implants (e.g. dental fillings, prostheses), causing severe artifacts in the x-ray CT images. Although a large number of metal artifact reduction (MAR) methods have been proposed in the past four decades, MAR is still one of the major problems in clinical x-ray CT. In this work, we develop a convolutional neural network (CNN) based MAR framework, which combines the information from the original and corrected images to suppress artifacts. Before the MAR, we generate a group of data and train a CNN. First, we numerically simulate various metal artifacts cases and build a dataset, which includes metal-free images (used as references), metal-inserted images and various MAR methods corrected images. Then, ten thousands patches are extracted from the databased to train the metal artifact reduction CNN. In the MAR stage, the original image and two corrected images are stacked as a three-channel input image for CNN, and a CNN image is generated with less artifacts. The water equivalent regions in the CNN image are set to a uniform value to yield a CNN prior, whose forward projections are used to replace the metal affected projections, followed by the FBP reconstruction. Experimental results demonstrate the superior metal artifact reduction capability of the proposed method to its competitors.

Linear-regression convolutional neural network for fully automated coronary lumen segmentation in intravascular optical coherence tomography

NASA Astrophysics Data System (ADS)

Yong, Yan Ling; Tan, Li Kuo; McLaughlin, Robert A.; Chee, Kok Han; Liew, Yih Miin

2017-12-01

Intravascular optical coherence tomography (OCT) is an optical imaging modality commonly used in the assessment of coronary artery diseases during percutaneous coronary intervention. Manual segmentation to assess luminal stenosis from OCT pullback scans is challenging and time consuming. We propose a linear-regression convolutional neural network to automatically perform vessel lumen segmentation, parameterized in terms of radial distances from the catheter centroid in polar space. Benchmarked against gold-standard manual segmentation, our proposed algorithm achieves average locational accuracy of the vessel wall of 22 microns, and 0.985 and 0.970 in Dice coefficient and Jaccard similarity index, respectively. The average absolute error of luminal area estimation is 1.38%. The processing rate is 40.6 ms per image, suggesting the potential to be incorporated into a clinical workflow and to provide quantitative assessment of vessel lumen in an intraoperative time frame.

Study on the influence of stochastic properties of correction terms on the reliability of instantaneous network RTK

NASA Astrophysics Data System (ADS)

Próchniewicz, Dominik

2014-03-01

The reliability of precision GNSS positioning primarily depends on correct carrier-phase ambiguity resolution. An optimal estimation and correct validation of ambiguities necessitates a proper definition of mathematical positioning model. Of particular importance in the model definition is the taking into account of the atmospheric errors (ionospheric and tropospheric refraction) as well as orbital errors. The use of the network of reference stations in kinematic positioning, known as Network-based Real-Time Kinematic (Network RTK) solution, facilitates the modeling of such errors and their incorporation, in the form of correction terms, into the functional description of positioning model. Lowered accuracy of corrections, especially during atmospheric disturbances, results in the occurrence of unaccounted biases, the so-called residual errors. The taking into account of such errors in Network RTK positioning model is possible by incorporating the accuracy characteristics of the correction terms into the stochastic model of observations. In this paper we investigate the impact of the expansion of the stochastic model to include correction term variances on the reliability of the model solution. In particular the results of instantaneous solution that only utilizes a single epoch of GPS observations, is analyzed. Such a solution mode due to the low number of degrees of freedom is very sensitive to an inappropriate mathematical model definition. Thus the high level of the solution reliability is very difficult to achieve. Numerical tests performed for a test network located in mountain area during ionospheric disturbances allows to verify the described method for the poor measurement conditions. The results of the ambiguity resolution as well as the rover positioning accuracy shows that the proposed method of stochastic modeling can increase the reliability of instantaneous Network RTK performance.

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

NASA Astrophysics Data System (ADS)

Allman, Derek; Reiter, Austin; Bell, Muyinatu

2018-02-01

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

Convolutional neural networks for vibrational spectroscopic data analysis.

PubMed

Acquarelli, Jacopo; van Laarhoven, Twan; Gerretzen, Jan; Tran, Thanh N; Buydens, Lutgarde M C; Marchiori, Elena

2017-02-15

In this work we show that convolutional neural networks (CNNs) can be efficiently used to classify vibrational spectroscopic data and identify important spectral regions. CNNs are the current state-of-the-art in image classification and speech recognition and can learn interpretable representations of the data. These characteristics make CNNs a good candidate for reducing the need for preprocessing and for highlighting important spectral regions, both of which are crucial steps in the analysis of vibrational spectroscopic data. Chemometric analysis of vibrational spectroscopic data often relies on preprocessing methods involving baseline correction, scatter correction and noise removal, which are applied to the spectra prior to model building. Preprocessing is a critical step because even in simple problems using 'reasonable' preprocessing methods may decrease the performance of the final model. We develop a new CNN based method and provide an accompanying publicly available software. It is based on a simple CNN architecture with a single convolutional layer (a so-called shallow CNN). Our method outperforms standard classification algorithms used in chemometrics (e.g. PLS) in terms of accuracy when applied to non-preprocessed test data (86% average accuracy compared to the 62% achieved by PLS), and it achieves better performance even on preprocessed test data (96% average accuracy compared to the 89% achieved by PLS). For interpretability purposes, our method includes a procedure for finding important spectral regions, thereby facilitating qualitative interpretation of results. Copyright © 2016 Elsevier B.V. All rights reserved.

Deblurring adaptive optics retinal images using deep convolutional neural networks.

PubMed

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.

Deblurring adaptive optics retinal images using deep convolutional neural networks

PubMed Central

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

2017-01-01

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. PMID:29296496

Channel coding for underwater acoustic single-carrier CDMA communication system

NASA Astrophysics Data System (ADS)

Liu, Lanjun; Zhang, Yonglei; Zhang, Pengcheng; Zhou, Lin; Niu, Jiong

2017-01-01

CDMA is an effective multiple access protocol for underwater acoustic networks, and channel coding can effectively reduce the bit error rate (BER) of the underwater acoustic communication system. For the requirements of underwater acoustic mobile networks based on CDMA, an underwater acoustic single-carrier CDMA communication system (UWA/SCCDMA) based on the direct-sequence spread spectrum is proposed, and its channel coding scheme is studied based on convolution, RA, Turbo and LDPC coding respectively. The implementation steps of the Viterbi algorithm of convolutional coding, BP and minimum sum algorithms of RA coding, Log-MAP and SOVA algorithms of Turbo coding, and sum-product algorithm of LDPC coding are given. An UWA/SCCDMA simulation system based on Matlab is designed. Simulation results show that the UWA/SCCDMA based on RA, Turbo and LDPC coding have good performance such that the communication BER is all less than 10-6 in the underwater acoustic channel with low signal to noise ratio (SNR) from -12 dB to -10dB, which is about 2 orders of magnitude lower than that of the convolutional coding. The system based on Turbo coding with Log-MAP algorithm has the best performance.

Development and application of deep convolutional neural network in target detection

NASA Astrophysics Data System (ADS)

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.

Passive quantum error correction of linear optics networks through error averaging

NASA Astrophysics Data System (ADS)

Marshman, Ryan J.; Lund, Austin P.; Rohde, Peter P.; Ralph, Timothy C.

2018-02-01

We propose and investigate a method of error detection and noise correction for bosonic linear networks using a method of unitary averaging. The proposed error averaging does not rely on ancillary photons or control and feedforward correction circuits, remaining entirely passive in its operation. We construct a general mathematical framework for this technique and then give a series of proof of principle examples including numerical analysis. Two methods for the construction of averaging are then compared to determine the most effective manner of implementation and probe the related error thresholds. Finally we discuss some of the potential uses of this scheme.

Feasibility study of multi-pixel retrieval of optical thickness and droplet effective radius of inhomogeneous clouds using deep learning

NASA Astrophysics Data System (ADS)

Okamura, Rintaro; Iwabuchi, Hironobu; Schmidt, K. Sebastian

2017-12-01

Three-dimensional (3-D) radiative-transfer effects are a major source of retrieval errors in satellite-based optical remote sensing of clouds. The challenge is that 3-D effects manifest themselves across multiple satellite pixels, which traditional single-pixel approaches cannot capture. In this study, we present two multi-pixel retrieval approaches based on deep learning, a technique that is becoming increasingly successful for complex problems in engineering and other areas. Specifically, we use deep neural networks (DNNs) to obtain multi-pixel estimates of cloud optical thickness and column-mean cloud droplet effective radius from multispectral, multi-pixel radiances. The first DNN method corrects traditional bispectral retrievals based on the plane-parallel homogeneous cloud assumption using the reflectances at the same two wavelengths. The other DNN method uses so-called convolutional layers and retrieves cloud properties directly from the reflectances at four wavelengths. The DNN methods are trained and tested on cloud fields from large-eddy simulations used as input to a 3-D radiative-transfer model to simulate upward radiances. The second DNN-based retrieval, sidestepping the bispectral retrieval step through convolutional layers, is shown to be more accurate. It reduces 3-D radiative-transfer effects that would otherwise affect the radiance values and estimates cloud properties robustly even for optically thick clouds.

Three-Class Mammogram Classification Based on Descriptive CNN Features

PubMed Central

Zhang, Qianni; Jadoon, Adeel

2017-01-01

In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW) and convolutional neural network-curvelet transform (CNN-CT). An augmented data set is generated by using mammogram patches. To enhance the contrast of mammogram images, the data set is filtered by contrast limited adaptive histogram equalization (CLAHE). In the CNN-DW method, enhanced mammogram images are decomposed as its four subbands by means of two-dimensional discrete wavelet transform (2D-DWT), while in the second method discrete curvelet transform (DCT) is used. In both methods, dense scale invariant feature (DSIFT) for all subbands is extracted. Input data matrix containing these subband features of all the mammogram patches is created that is processed as input to convolutional neural network (CNN). Softmax layer and support vector machine (SVM) layer are used to train CNN for classification. Proposed methods have been compared with existing methods in terms of accuracy rate, error rate, and various validation assessment measures. CNN-DW and CNN-CT have achieved accuracy rate of 81.83% and 83.74%, respectively. Simulation results clearly validate the significance and impact of our proposed model as compared to other well-known existing techniques. PMID:28191461

Three-Class Mammogram Classification Based on Descriptive CNN Features.

PubMed

Jadoon, M Mohsin; Zhang, Qianni; Haq, Ihsan Ul; Butt, Sharjeel; Jadoon, Adeel

2017-01-01

In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW) and convolutional neural network-curvelet transform (CNN-CT). An augmented data set is generated by using mammogram patches. To enhance the contrast of mammogram images, the data set is filtered by contrast limited adaptive histogram equalization (CLAHE). In the CNN-DW method, enhanced mammogram images are decomposed as its four subbands by means of two-dimensional discrete wavelet transform (2D-DWT), while in the second method discrete curvelet transform (DCT) is used. In both methods, dense scale invariant feature (DSIFT) for all subbands is extracted. Input data matrix containing these subband features of all the mammogram patches is created that is processed as input to convolutional neural network (CNN). Softmax layer and support vector machine (SVM) layer are used to train CNN for classification. Proposed methods have been compared with existing methods in terms of accuracy rate, error rate, and various validation assessment measures. CNN-DW and CNN-CT have achieved accuracy rate of 81.83% and 83.74%, respectively. Simulation results clearly validate the significance and impact of our proposed model as compared to other well-known existing techniques.

High Performance Implementation of 3D Convolutional Neural Networks on a GPU.

PubMed

Lan, Qiang; Wang, Zelong; Wen, Mei; Zhang, Chunyuan; Wang, Yijie

2017-01-01

Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to video classification, which constitutes a 3D input and requires far larger amounts of memory and much more computation. FFT based methods can reduce the amount of computation, but this generally comes at the cost of an increased memory requirement. On the other hand, the Winograd Minimal Filtering Algorithm (WMFA) can reduce the number of operations required and thus can speed up the computation, without increasing the required memory. This strategy was shown to be successful for 2D neural networks. We implement the algorithm for 3D convolutional neural networks and apply it to a popular 3D convolutional neural network which is used to classify videos and compare it to cuDNN. For our highly optimized implementation of the algorithm, we observe a twofold speedup for most of the 3D convolution layers of our test network compared to the cuDNN version.

High Performance Implementation of 3D Convolutional Neural Networks on a GPU

PubMed Central

Wang, Zelong; Wen, Mei; Zhang, Chunyuan; Wang, Yijie

2017-01-01

Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to video classification, which constitutes a 3D input and requires far larger amounts of memory and much more computation. FFT based methods can reduce the amount of computation, but this generally comes at the cost of an increased memory requirement. On the other hand, the Winograd Minimal Filtering Algorithm (WMFA) can reduce the number of operations required and thus can speed up the computation, without increasing the required memory. This strategy was shown to be successful for 2D neural networks. We implement the algorithm for 3D convolutional neural networks and apply it to a popular 3D convolutional neural network which is used to classify videos and compare it to cuDNN. For our highly optimized implementation of the algorithm, we observe a twofold speedup for most of the 3D convolution layers of our test network compared to the cuDNN version. PMID:29250109

RD Optimized, Adaptive, Error-Resilient Transmission of MJPEG2000-Coded Video over Multiple Time-Varying Channels

NASA Astrophysics Data System (ADS)

Bezan, Scott; Shirani, Shahram

2006-12-01

To reliably transmit video over error-prone channels, the data should be both source and channel coded. When multiple channels are available for transmission, the problem extends to that of partitioning the data across these channels. The condition of transmission channels, however, varies with time. Therefore, the error protection added to the data at one instant of time may not be optimal at the next. In this paper, we propose a method for adaptively adding error correction code in a rate-distortion (RD) optimized manner using rate-compatible punctured convolutional codes to an MJPEG2000 constant rate-coded frame of video. We perform an analysis on the rate-distortion tradeoff of each of the coding units (tiles and packets) in each frame and adapt the error correction code assigned to the unit taking into account the bandwidth and error characteristics of the channels. This method is applied to both single and multiple time-varying channel environments. We compare our method with a basic protection method in which data is either not transmitted, transmitted with no protection, or transmitted with a fixed amount of protection. Simulation results show promising performance for our proposed method.

The Space Telescope SI C&DH system. [Scientific Instrument Control and Data Handling Subsystem

NASA Technical Reports Server (NTRS)

Gadwal, Govind R.; Barasch, Ronald S.

1990-01-01

The Hubble Space Telescope Scientific Instrument Control and Data Handling Subsystem (SI C&DH) is designed to interface with five scientific instruments of the Space Telescope to provide ground and autonomous control and collect health and status information using the Standard Telemetry and Command Components (STACC) multiplex data bus. It also formats high throughput science data into packets. The packetized data is interleaved and Reed-Solomon encoded for error correction and Pseudo Random encoded. An inner convolutional coding with the outer Reed-Solomon coding provides excellent error correction capability. The subsystem is designed with the capacity for orbital replacement in order to meet a mission life of fifteen years. The spacecraft computer and the SI C&DH computer coordinate the activities of the spacecraft and the scientific instruments to achieve the mission objectives.

A deep learning approach for real time prostate segmentation in freehand ultrasound guided biopsy.

PubMed

Anas, Emran Mohammad Abu; Mousavi, Parvin; Abolmaesumi, Purang

2018-06-01

Targeted prostate biopsy, incorporating multi-parametric magnetic resonance imaging (mp-MRI) and its registration with ultrasound, is currently the state-of-the-art in prostate cancer diagnosis. The registration process in most targeted biopsy systems today relies heavily on accurate segmentation of ultrasound images. Automatic or semi-automatic segmentation is typically performed offline prior to the start of the biopsy procedure. In this paper, we present a deep neural network based real-time prostate segmentation technique during the biopsy procedure, hence paving the way for dynamic registration of mp-MRI and ultrasound data. In addition to using convolutional networks for extracting spatial features, the proposed approach employs recurrent networks to exploit the temporal information among a series of ultrasound images. One of the key contributions in the architecture is to use residual convolution in the recurrent networks to improve optimization. We also exploit recurrent connections within and across different layers of the deep networks to maximize the utilization of the temporal information. Furthermore, we perform dense and sparse sampling of the input ultrasound sequence to make the network robust to ultrasound artifacts. Our architecture is trained on 2,238 labeled transrectal ultrasound images, with an additional 637 and 1,017 unseen images used for validation and testing, respectively. We obtain a mean Dice similarity coefficient of 93%, a mean surface distance error of 1.10 mm and a mean Hausdorff distance error of 3.0 mm. A comparison of the reported results with those of a state-of-the-art technique indicates statistically significant improvement achieved by the proposed approach. Copyright © 2018 Elsevier B.V. All rights reserved.

Detection of retinal changes from illumination normalized fundus images using convolutional neural networks

NASA Astrophysics Data System (ADS)

Adal, Kedir M.; van Etten, Peter G.; Martinez, Jose P.; Rouwen, Kenneth; Vermeer, Koenraad A.; van Vliet, Lucas J.

2017-03-01

Automated detection and quantification of spatio-temporal retinal changes is an important step to objectively assess disease progression and treatment effects for dynamic retinal diseases such as diabetic retinopathy (DR). However, detecting retinal changes caused by early DR lesions such as microaneurysms and dot hemorrhages from longitudinal pairs of fundus images is challenging due to intra and inter-image illumination variation between fundus images. This paper explores a method for automated detection of retinal changes from illumination normalized fundus images using a deep convolutional neural network (CNN), and compares its performance with two other CNNs trained separately on color and green channel fundus images. Illumination variation was addressed by correcting for the variability in the luminosity and contrast estimated from a large scale retinal regions. The CNN models were trained and evaluated on image patches extracted from a registered fundus image set collected from 51 diabetic eyes that were screened at two different time-points. The results show that using normalized images yield better performance than color and green channel images, suggesting that illumination normalization greatly facilitates CNNs to quickly and correctly learn distinctive local image features of DR related retinal changes.

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

PubMed Central

Qu, Xiaobo; He, Yifan

2018-01-01

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. PMID:29509666

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

PubMed

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.

MR-based synthetic CT generation using a deep convolutional neural network method.

PubMed

Han, Xiao

2017-04-01

Interests have been rapidly growing in the field of radiotherapy to replace CT with magnetic resonance imaging (MRI), due to superior soft tissue contrast offered by MRI and the desire to reduce unnecessary radiation dose. MR-only radiotherapy also simplifies clinical workflow and avoids uncertainties in aligning MR with CT. Methods, however, are needed to derive CT-equivalent representations, often known as synthetic CT (sCT), from patient MR images for dose calculation and DRR-based patient positioning. Synthetic CT estimation is also important for PET attenuation correction in hybrid PET-MR systems. We propose in this work a novel deep convolutional neural network (DCNN) method for sCT generation and evaluate its performance on a set of brain tumor patient images. The proposed method builds upon recent developments of deep learning and convolutional neural networks in the computer vision literature. The proposed DCNN model has 27 convolutional layers interleaved with pooling and unpooling layers and 35 million free parameters, which can be trained to learn a direct end-to-end mapping from MR images to their corresponding CTs. Training such a large model on our limited data is made possible through the principle of transfer learning and by initializing model weights from a pretrained model. Eighteen brain tumor patients with both CT and T1-weighted MR images are used as experimental data and a sixfold cross-validation study is performed. Each sCT generated is compared against the real CT image of the same patient on a voxel-by-voxel basis. Comparison is also made with respect to an atlas-based approach that involves deformable atlas registration and patch-based atlas fusion. The proposed DCNN method produced a mean absolute error (MAE) below 85 HU for 13 of the 18 test subjects. The overall average MAE was 84.8 ± 17.3 HU for all subjects, which was found to be significantly better than the average MAE of 94.5 ± 17.8 HU for the atlas-based method. The DCNN method also provided significantly better accuracy when being evaluated using two other metrics: the mean squared error (188.6 ± 33.7 versus 198.3 ± 33.0) and the Pearson correlation coefficient(0.906 ± 0.03 versus 0.896 ± 0.03). Although training a DCNN model can be slow, training only need be done once. Applying a trained model to generate a complete sCT volume for each new patient MR image only took 9 s, which was much faster than the atlas-based approach. A DCNN model method was developed, and shown to be able to produce highly accurate sCT estimations from conventional, single-sequence MR images in near real time. Quantitative results also showed that the proposed method competed favorably with an atlas-based method, in terms of both accuracy and computation speed at test time. Further validation on dose computation accuracy and on a larger patient cohort is warranted. Extensions of the method are also possible to further improve accuracy or to handle multi-sequence MR images. © 2017 American Association of Physicists in Medicine.

Coordinated design of coding and modulation systems

NASA Technical Reports Server (NTRS)

Massey, J. L.

1976-01-01

Work on partial unit memory codes continued; it was shown that for a given virtual state complexity, the maximum free distance over the class of all convolutional codes is achieved within the class of unit memory codes. The effect of phase-lock loop (PLL) tracking error on coding system performance was studied by using the channel cut-off rate as the measure of quality of a modulation system. Optimum modulation signal sets for a non-white Gaussian channel considered an heuristic selection rule based on a water-filling argument. The use of error correcting codes to perform data compression by the technique of syndrome source coding was researched and a weight-and-error-locations scheme was developed that is closely related to LDSC coding.

Performance analysis of the word synchronization properties of the outer code in a TDRSS decoder

NASA Technical Reports Server (NTRS)

Costello, D. J., Jr.; Lin, S.

1984-01-01

A self-synchronizing coding scheme for NASA's TDRSS satellite system is a concatenation of a (2,1,7) inner convolutional code with a (255,223) Reed-Solomon outer code. Both symbol and word synchronization are achieved without requiring that any additional symbols be transmitted. An important parameter which determines the performance of the word sync procedure is the ratio of the decoding failure probability to the undetected error probability. Ideally, the former should be as small as possible compared to the latter when the error correcting capability of the code is exceeded. A computer simulation of a (255,223) Reed-Solomon code as carried out. Results for decoding failure probability and for undetected error probability are tabulated and compared.

Neural network decoder for quantum error correcting codes

NASA Astrophysics Data System (ADS)

Krastanov, Stefan; Jiang, Liang

Artificial neural networks form a family of extremely powerful - albeit still poorly understood - tools used in anything from image and sound recognition through text generation to, in our case, decoding. We present a straightforward Recurrent Neural Network architecture capable of deducing the correcting procedure for a quantum error-correcting code from a set of repeated stabilizer measurements. We discuss the fault-tolerance of our scheme and the cost of training the neural network for a system of a realistic size. Such decoders are especially interesting when applied to codes, like the quantum LDPC codes, that lack known efficient decoding schemes.

Deep architecture neural network-based real-time image processing for image-guided radiotherapy.

PubMed

Mori, Shinichiro

2017-08-01

To develop real-time image processing for image-guided radiotherapy, we evaluated several neural network models for use with different imaging modalities, including X-ray fluoroscopic image denoising. Setup images of prostate cancer patients were acquired with two oblique X-ray fluoroscopic units. Two types of residual network were designed: a convolutional autoencoder (rCAE) and a convolutional neural network (rCNN). We changed the convolutional kernel size and number of convolutional layers for both networks, and the number of pooling and upsampling layers for rCAE. The ground-truth image was applied to the contrast-limited adaptive histogram equalization (CLAHE) method of image processing. Network models were trained to keep the quality of the output image close to that of the ground-truth image from the input image without image processing. For image denoising evaluation, noisy input images were used for the training. More than 6 convolutional layers with convolutional kernels >5×5 improved image quality. However, this did not allow real-time imaging. After applying a pair of pooling and upsampling layers to both networks, rCAEs with >3 convolutions each and rCNNs with >12 convolutions with a pair of pooling and upsampling layers achieved real-time processing at 30 frames per second (fps) with acceptable image quality. Use of our suggested network achieved real-time image processing for contrast enhancement and image denoising by the use of a conventional modern personal computer. Copyright © 2017 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.

High-Throughput Classification of Radiographs Using Deep Convolutional Neural Networks.

PubMed

Rajkomar, Alvin; Lingam, Sneha; Taylor, Andrew G; Blum, Michael; Mongan, John

2017-02-01

The study aimed to determine if computer vision techniques rooted in deep learning can use a small set of radiographs to perform clinically relevant image classification with high fidelity. One thousand eight hundred eighty-five chest radiographs on 909 patients obtained between January 2013 and July 2015 at our institution were retrieved and anonymized. The source images were manually annotated as frontal or lateral and randomly divided into training, validation, and test sets. Training and validation sets were augmented to over 150,000 images using standard image manipulations. We then pre-trained a series of deep convolutional networks based on the open-source GoogLeNet with various transformations of the open-source ImageNet (non-radiology) images. These trained networks were then fine-tuned using the original and augmented radiology images. The model with highest validation accuracy was applied to our institutional test set and a publicly available set. Accuracy was assessed by using the Youden Index to set a binary cutoff for frontal or lateral classification. This retrospective study was IRB approved prior to initiation. A network pre-trained on 1.2 million greyscale ImageNet images and fine-tuned on augmented radiographs was chosen. The binary classification method correctly classified 100 % (95 % CI 99.73-100 %) of both our test set and the publicly available images. Classification was rapid, at 38 images per second. A deep convolutional neural network created using non-radiological images, and an augmented set of radiographs is effective in highly accurate classification of chest radiograph view type and is a feasible, rapid method for high-throughput annotation.

Resting State fMRI Functional Connectivity-Based Classification Using a Convolutional Neural Network Architecture

PubMed Central

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

Face recognition: a convolutional neural-network approach.

PubMed

Lawrence, S; Giles, C L; Tsoi, A C; Back, A D

1997-01-01

We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image sampling, a self-organizing map (SOM) neural network, and a convolutional neural network. The SOM provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the SOM, and a multilayer perceptron (MLP) in place of the convolutional network for comparison. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details. We analyze the computational complexity and discuss how new classes could be added to the trained recognizer.

Resting State fMRI Functional Connectivity-Based Classification Using a Convolutional Neural Network Architecture.

PubMed

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.

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

PubMed

Rueckauer, Bodo; Lungu, Iulia-Alexandra; Hu, Yuhuang; Pfeiffer, Michael; Liu, Shih-Chii

2017-01-01

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

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

PubMed Central

Rueckauer, Bodo; Lungu, Iulia-Alexandra; Hu, Yuhuang; Pfeiffer, Michael; Liu, Shih-Chii

2017-01-01

Spiking neural networks (SNNs) can potentially offer an efficient way of doing inference because the neurons in the networks are sparsely activated and computations are event-driven. Previous work showed that simple continuous-valued deep Convolutional Neural Networks (CNNs) can be converted into accurate spiking equivalents. These networks did not include certain common operations such as max-pooling, softmax, batch-normalization and Inception-modules. This paper presents spiking equivalents of these operations therefore allowing conversion of nearly arbitrary CNN architectures. We show conversion of popular CNN architectures, including VGG-16 and Inception-v3, into SNNs that produce the best results reported to date on MNIST, CIFAR-10 and the challenging ImageNet dataset. SNNs can trade off classification error rate against the number of available operations whereas deep continuous-valued neural networks require a fixed number of operations to achieve their classification error rate. From the examples of LeNet for MNIST and BinaryNet for CIFAR-10, we show that with an increase in error rate of a few percentage points, the SNNs can achieve more than 2x reductions in operations compared to the original CNNs. This highlights the potential of SNNs in particular when deployed on power-efficient neuromorphic spiking neuron chips, for use in embedded applications. PMID:29375284

Hydraulic correction method (HCM) to enhance the efficiency of SRTM DEM in flood modeling

NASA Astrophysics Data System (ADS)

Chen, Huili; Liang, Qiuhua; Liu, Yong; Xie, Shuguang

2018-04-01

Digital Elevation Model (DEM) is one of the most important controlling factors determining the simulation accuracy of hydraulic models. However, the currently available global topographic data is confronted with limitations for application in 2-D hydraulic modeling, mainly due to the existence of vegetation bias, random errors and insufficient spatial resolution. A hydraulic correction method (HCM) for the SRTM DEM is proposed in this study to improve modeling accuracy. Firstly, we employ the global vegetation corrected DEM (i.e. Bare-Earth DEM), developed from the SRTM DEM to include both vegetation height and SRTM vegetation signal. Then, a newly released DEM, removing both vegetation bias and random errors (i.e. Multi-Error Removed DEM), is employed to overcome the limitation of height errors. Last, an approach to correct the Multi-Error Removed DEM is presented to account for the insufficiency of spatial resolution, ensuring flow connectivity of the river networks. The approach involves: (a) extracting river networks from the Multi-Error Removed DEM using an automated algorithm in ArcGIS; (b) correcting the location and layout of extracted streams with the aid of Google Earth platform and Remote Sensing imagery; and (c) removing the positive biases of the raised segment in the river networks based on bed slope to generate the hydraulically corrected DEM. The proposed HCM utilizes easily available data and tools to improve the flow connectivity of river networks without manual adjustment. To demonstrate the advantages of HCM, an extreme flood event in Huifa River Basin (China) is simulated on the original DEM, Bare-Earth DEM, Multi-Error removed DEM, and hydraulically corrected DEM using an integrated hydrologic-hydraulic model. A comparative analysis is subsequently performed to assess the simulation accuracy and performance of four different DEMs and favorable results have been obtained on the corrected DEM.

High-speed quantum networking by ship

NASA Astrophysics Data System (ADS)

Devitt, Simon J.; Greentree, Andrew D.; Stephens, Ashley M.; van Meter, Rodney

2016-11-01

Networked entanglement is an essential component for a plethora of quantum computation and communication protocols. Direct transmission of quantum signals over long distances is prevented by fibre attenuation and the no-cloning theorem, motivating the development of quantum repeaters, designed to purify entanglement, extending its range. Quantum repeaters have been demonstrated over short distances, but error-corrected, global repeater networks with high bandwidth require new technology. Here we show that error corrected quantum memories installed in cargo containers and carried by ship can provide a exible connection between local networks, enabling low-latency, high-fidelity quantum communication across global distances at higher bandwidths than previously proposed. With demonstrations of technology with sufficient fidelity to enable topological error-correction, implementation of the quantum memories is within reach, and bandwidth increases with improvements in fabrication. Our approach to quantum networking avoids technological restrictions of repeater deployment, providing an alternate path to a worldwide Quantum Internet.

High-speed quantum networking by ship

PubMed Central

Devitt, Simon J.; Greentree, Andrew D.; Stephens, Ashley M.; Van Meter, Rodney

2016-01-01

Networked entanglement is an essential component for a plethora of quantum computation and communication protocols. Direct transmission of quantum signals over long distances is prevented by fibre attenuation and the no-cloning theorem, motivating the development of quantum repeaters, designed to purify entanglement, extending its range. Quantum repeaters have been demonstrated over short distances, but error-corrected, global repeater networks with high bandwidth require new technology. Here we show that error corrected quantum memories installed in cargo containers and carried by ship can provide a exible connection between local networks, enabling low-latency, high-fidelity quantum communication across global distances at higher bandwidths than previously proposed. With demonstrations of technology with sufficient fidelity to enable topological error-correction, implementation of the quantum memories is within reach, and bandwidth increases with improvements in fabrication. Our approach to quantum networking avoids technological restrictions of repeater deployment, providing an alternate path to a worldwide Quantum Internet. PMID:27805001

High-speed quantum networking by ship.

PubMed

Devitt, Simon J; Greentree, Andrew D; Stephens, Ashley M; Van Meter, Rodney

2016-11-02

Networked entanglement is an essential component for a plethora of quantum computation and communication protocols. Direct transmission of quantum signals over long distances is prevented by fibre attenuation and the no-cloning theorem, motivating the development of quantum repeaters, designed to purify entanglement, extending its range. Quantum repeaters have been demonstrated over short distances, but error-corrected, global repeater networks with high bandwidth require new technology. Here we show that error corrected quantum memories installed in cargo containers and carried by ship can provide a exible connection between local networks, enabling low-latency, high-fidelity quantum communication across global distances at higher bandwidths than previously proposed. With demonstrations of technology with sufficient fidelity to enable topological error-correction, implementation of the quantum memories is within reach, and bandwidth increases with improvements in fabrication. Our approach to quantum networking avoids technological restrictions of repeater deployment, providing an alternate path to a worldwide Quantum Internet.

Error coding simulations in C

NASA Technical Reports Server (NTRS)

Noble, Viveca K.

1994-01-01

When data is transmitted through a noisy channel, errors are produced within the data rendering it indecipherable. Through the use of error control coding techniques, the bit error rate can be reduced to any desired level without sacrificing the transmission data rate. The Astrionics Laboratory at Marshall Space Flight Center has decided to use a modular, end-to-end telemetry data simulator to simulate the transmission of data from flight to ground and various methods of error control. The simulator includes modules for random data generation, data compression, Consultative Committee for Space Data Systems (CCSDS) transfer frame formation, error correction/detection, error generation and error statistics. The simulator utilizes a concatenated coding scheme which includes CCSDS standard (255,223) Reed-Solomon (RS) code over GF(2(exp 8)) with interleave depth of 5 as the outermost code, (7, 1/2) convolutional code as an inner code and CCSDS recommended (n, n-16) cyclic redundancy check (CRC) code as the innermost code, where n is the number of information bits plus 16 parity bits. The received signal-to-noise for a desired bit error rate is greatly reduced through the use of forward error correction techniques. Even greater coding gain is provided through the use of a concatenated coding scheme. Interleaving/deinterleaving is necessary to randomize burst errors which may appear at the input of the RS decoder. The burst correction capability length is increased in proportion to the interleave depth. The modular nature of the simulator allows for inclusion or exclusion of modules as needed. This paper describes the development and operation of the simulator, the verification of a C-language Reed-Solomon code, and the possibility of using Comdisco SPW(tm) as a tool for determining optimal error control schemes.

Effective image differencing with convolutional neural networks for real-time transient hunting

NASA Astrophysics Data System (ADS)

Sedaghat, Nima; Mahabal, Ashish

2018-06-01

Large sky surveys are increasingly relying on image subtraction pipelines for real-time (and archival) transient detection. In this process one has to contend with varying point-spread function (PSF) and small brightness variations in many sources, as well as artefacts resulting from saturated stars and, in general, matching errors. Very often the differencing is done with a reference image that is deeper than individual images and the attendant difference in noise characteristics can also lead to artefacts. We present here a deep-learning approach to transient detection that encapsulates all the steps of a traditional image-subtraction pipeline - image registration, background subtraction, noise removal, PSF matching and subtraction - in a single real-time convolutional network. Once trained, the method works lightening-fast and, given that it performs multiple steps in one go, the time saved and false positives eliminated for multi-CCD surveys like Zwicky Transient Facility and Large Synoptic Survey Telescope will be immense, as millions of subtractions will be needed per night.

Analyzing γ rays of the Galactic Center with deep learning

NASA Astrophysics Data System (ADS)

Caron, Sascha; Gómez-Vargas, Germán A.; Hendriks, Luc; Ruiz de Austri, Roberto

2018-05-01

We present the application of convolutional neural networks to a particular problem in gamma ray astronomy. Explicitly, we use this method to investigate the origin of an excess emission of GeV γ rays in the direction of the Galactic Center, reported by several groups by analyzing Fermi-LAT data. Interpretations of this excess include γ rays created by the annihilation of dark matter particles and γ rays originating from a collection of unresolved point sources, such as millisecond pulsars. We train and test convolutional neural networks with simulated Fermi-LAT images based on point and diffuse emission models of the Galactic Center tuned to measured γ ray data. Our new method allows precise measurements of the contribution and properties of an unresolved population of γ ray point sources in the interstellar diffuse emission model. The current model predicts the fraction of unresolved point sources with an error of up to 10% and this is expected to decrease with future work.

Linear-regression convolutional neural network for fully automated coronary lumen segmentation in intravascular optical coherence tomography.

PubMed

Yong, Yan Ling; Tan, Li Kuo; McLaughlin, Robert A; Chee, Kok Han; Liew, Yih Miin

2017-12-01

Intravascular optical coherence tomography (OCT) is an optical imaging modality commonly used in the assessment of coronary artery diseases during percutaneous coronary intervention. Manual segmentation to assess luminal stenosis from OCT pullback scans is challenging and time consuming. We propose a linear-regression convolutional neural network to automatically perform vessel lumen segmentation, parameterized in terms of radial distances from the catheter centroid in polar space. Benchmarked against gold-standard manual segmentation, our proposed algorithm achieves average locational accuracy of the vessel wall of 22 microns, and 0.985 and 0.970 in Dice coefficient and Jaccard similarity index, respectively. The average absolute error of luminal area estimation is 1.38%. The processing rate is 40.6 ms per image, suggesting the potential to be incorporated into a clinical workflow and to provide quantitative assessment of vessel lumen in an intraoperative time frame. (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE).

A top-down manner-based DCNN architecture for semantic image segmentation.

PubMed

Qiao, Kai; Chen, Jian; Wang, Linyuan; Zeng, Lei; Yan, Bin

2017-01-01

Given their powerful feature representation for recognition, deep convolutional neural networks (DCNNs) have been driving rapid advances in high-level computer vision tasks. However, their performance in semantic image segmentation is still not satisfactory. Based on the analysis of visual mechanism, we conclude that DCNNs in a bottom-up manner are not enough, because semantic image segmentation task requires not only recognition but also visual attention capability. In the study, superpixels containing visual attention information are introduced in a top-down manner, and an extensible architecture is proposed to improve the segmentation results of current DCNN-based methods. We employ the current state-of-the-art fully convolutional network (FCN) and FCN with conditional random field (DeepLab-CRF) as baselines to validate our architecture. Experimental results of the PASCAL VOC segmentation task qualitatively show that coarse edges and error segmentation results are well improved. We also quantitatively obtain about 2%-3% intersection over union (IOU) accuracy improvement on the PASCAL VOC 2011 and 2012 test sets.

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

PubMed

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

2018-07-01

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

Error-correction coding for digital communications

NASA Astrophysics Data System (ADS)

Clark, G. C., Jr.; Cain, J. B.

This book is written for the design engineer who must build the coding and decoding equipment and for the communication system engineer who must incorporate this equipment into a system. It is also suitable as a senior-level or first-year graduate text for an introductory one-semester course in coding theory. Fundamental concepts of coding are discussed along with group codes, taking into account basic principles, practical constraints, performance computations, coding bounds, generalized parity check codes, polynomial codes, and important classes of group codes. Other topics explored are related to simple nonalgebraic decoding techniques for group codes, soft decision decoding of block codes, algebraic techniques for multiple error correction, the convolutional code structure and Viterbi decoding, syndrome decoding techniques, and sequential decoding techniques. System applications are also considered, giving attention to concatenated codes, coding for the white Gaussian noise channel, interleaver structures for coded systems, and coding for burst noise channels.

Improved PPP Ambiguity Resolution Considering the Stochastic Characteristics of Atmospheric Corrections from Regional Networks

PubMed Central

Li, Yihe; Li, Bofeng; Gao, Yang

2015-01-01

With the increased availability of regional reference networks, Precise Point Positioning (PPP) can achieve fast ambiguity resolution (AR) and precise positioning by assimilating the satellite fractional cycle biases (FCBs) and atmospheric corrections derived from these networks. In such processing, the atmospheric corrections are usually treated as deterministic quantities. This is however unrealistic since the estimated atmospheric corrections obtained from the network data are random and furthermore the interpolated corrections diverge from the realistic corrections. This paper is dedicated to the stochastic modelling of atmospheric corrections and analyzing their effects on the PPP AR efficiency. The random errors of the interpolated corrections are processed as two components: one is from the random errors of estimated corrections at reference stations, while the other arises from the atmospheric delay discrepancies between reference stations and users. The interpolated atmospheric corrections are then applied by users as pseudo-observations with the estimated stochastic model. Two data sets are processed to assess the performance of interpolated corrections with the estimated stochastic models. The results show that when the stochastic characteristics of interpolated corrections are properly taken into account, the successful fix rate reaches 93.3% within 5 min for a medium inter-station distance network and 80.6% within 10 min for a long inter-station distance network. PMID:26633400

Improved PPP Ambiguity Resolution Considering the Stochastic Characteristics of Atmospheric Corrections from Regional Networks.

PubMed

Li, Yihe; Li, Bofeng; Gao, Yang

2015-11-30

With the increased availability of regional reference networks, Precise Point Positioning (PPP) can achieve fast ambiguity resolution (AR) and precise positioning by assimilating the satellite fractional cycle biases (FCBs) and atmospheric corrections derived from these networks. In such processing, the atmospheric corrections are usually treated as deterministic quantities. This is however unrealistic since the estimated atmospheric corrections obtained from the network data are random and furthermore the interpolated corrections diverge from the realistic corrections. This paper is dedicated to the stochastic modelling of atmospheric corrections and analyzing their effects on the PPP AR efficiency. The random errors of the interpolated corrections are processed as two components: one is from the random errors of estimated corrections at reference stations, while the other arises from the atmospheric delay discrepancies between reference stations and users. The interpolated atmospheric corrections are then applied by users as pseudo-observations with the estimated stochastic model. Two data sets are processed to assess the performance of interpolated corrections with the estimated stochastic models. The results show that when the stochastic characteristics of interpolated corrections are properly taken into account, the successful fix rate reaches 93.3% within 5 min for a medium inter-station distance network and 80.6% within 10 min for a long inter-station distance network.

Automatic pedicles detection using convolutional neural network in a 3D spine reconstruction from biplanar radiographs

NASA Astrophysics Data System (ADS)

Bakhous, Christine; Aubert, Benjamin; Vazquez, Carlos; Cresson, Thierry; Parent, Stefan; De Guise, Jacques

2018-02-01

The 3D analysis of the spine deformities (scoliosis) has a high potential in its clinical diagnosis and treatment. In a biplanar radiographs context, a 3D analysis requires a 3D reconstruction from a pair of 2D X-rays. Whether being fully-/semiautomatic or manual, this task is complex because of the noise, the structure superimposition and partial information due to a limited projections number. Being involved in the axial vertebra rotation (AVR), which is a fundamental clinical parameter for scoliosis diagnosis, pedicles are important landmarks for the 3D spine modeling and pre-operative planning. In this paper, we focus on the extension of a fully-automatic 3D spine reconstruction method where the Vertebral Body Centers (VBCs) are automatically detected using Convolutional Neural Network (CNN) and then regularized using a Statistical Shape Model (SSM) framework. In this global process, pedicles are inferred statistically during the SSM regularization. Our contribution is to add a CNN-based regression model for pedicle detection allowing a better pedicle localization and improving the clinical parameters estimation (e.g. AVR, Cobb angle). Having 476 datasets including healthy patients and Adolescent Idiopathic Scoliosis (AIS) cases with different scoliosis grades (Cobb angles up to 116°), we used 380 for training, 48 for testing and 48 for validation. Adding the local CNN-based pedicle detection decreases the mean absolute error of the AVR by 10%. The 3D mean Euclidian distance error between detected pedicles and ground truth decreases by 17% and the maximum error by 19%. Moreover, a general improvement is observed in the 3D spine reconstruction and reflected in lower errors on the Cobb angle estimation.

Pubface: Celebrity face identification based on deep learning

NASA Astrophysics Data System (ADS)

Ouanan, H.; Ouanan, M.; Aksasse, B.

2018-05-01

In this paper, we describe a new real time application called PubFace, which allows to recognize celebrities in public spaces by employs a new pose invariant face recognition deep neural network algorithm with an extremely low error rate. To build this application, we make the following contributions: firstly, we build a novel dataset with over five million faces labelled. Secondly, we fine tuning the deep convolutional neural network (CNN) VGG-16 architecture on our new dataset that we have built. Finally, we deploy this model on the Raspberry Pi 3 model B using the OpenCv dnn module (OpenCV 3.3).

Single image super-resolution based on convolutional neural networks

NASA Astrophysics Data System (ADS)

Zou, Lamei; Luo, Ming; Yang, Weidong; Li, Peng; Jin, Liujia

2018-03-01

We present a deep learning method for single image super-resolution (SISR). The proposed approach learns end-to-end mapping between low-resolution (LR) images and high-resolution (HR) images. The mapping is represented as a deep convolutional neural network which inputs the LR image and outputs the HR image. Our network uses 5 convolution layers, which kernels size include 5×5, 3×3 and 1×1. In our proposed network, we use residual-learning and combine different sizes of convolution kernels at the same layer. The experiment results show that our proposed method performs better than the existing methods in reconstructing quality index and human visual effects on benchmarked images.

Multimodal integration of micro-Doppler sonar and auditory signals for behavior classification with convolutional networks.

PubMed

Dura-Bernal, Salvador; Garreau, Guillaume; Georgiou, Julius; Andreou, Andreas G; Denham, Susan L; Wennekers, Thomas

2013-10-01

The ability to recognize the behavior of individuals is of great interest in the general field of safety (e.g. building security, crowd control, transport analysis, independent living for the elderly). Here we report a new real-time acoustic system for human action and behavior recognition that integrates passive audio and active micro-Doppler sonar signatures over multiple time scales. The system architecture is based on a six-layer convolutional neural network, trained and evaluated using a dataset of 10 subjects performing seven different behaviors. Probabilistic combination of system output through time for each modality separately yields 94% (passive audio) and 91% (micro-Doppler sonar) correct behavior classification; probabilistic multimodal integration increases classification performance to 98%. This study supports the efficacy of micro-Doppler sonar systems in characterizing human actions, which can then be efficiently classified using ConvNets. It also demonstrates that the integration of multiple sources of acoustic information can significantly improve the system's performance.

[Study on phase correction method of spatial heterodyne spectrometer].

PubMed

Wang, Xin-Qiang; Ye, Song; Zhang, Li-Juan; Xiong, Wei

2013-05-01

Phase distortion exists in collected interferogram because of a variety of measure reasons when spatial heterodyne spectrometers are used in practice. So an improved phase correction method is presented. The phase curve of interferogram was obtained through Fourier inverse transform to extract single side transform spectrum, based on which, the phase distortions were attained by fitting phase slope, so were the phase correction functions, and the convolution was processed between transform spectrum and phase correction function to implement spectrum phase correction. The method was applied to phase correction of actually measured monochromatic spectrum and emulational water vapor spectrum. Experimental results show that the low-frequency false signals in monochromatic spectrum fringe would be eliminated effectively to increase the periodicity and the symmetry of interferogram, in addition when the continuous spectrum imposed phase error was corrected, the standard deviation between it and the original spectrum would be reduced form 0.47 to 0.20, and thus the accuracy of spectrum could be improved.

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

NASA Astrophysics Data System (ADS)

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

2005-03-01

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

Classification of urine sediment based on convolution neural network

NASA Astrophysics Data System (ADS)

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.

Detection of eardrum abnormalities using ensemble deep learning approaches

NASA Astrophysics Data System (ADS)

Senaras, Caglar; Moberly, Aaron C.; Teknos, Theodoros; Essig, Garth; Elmaraghy, Charles; Taj-Schaal, Nazhat; Yua, Lianbo; Gurcan, Metin N.

2018-02-01

In this study, we proposed an approach to report the condition of the eardrum as "normal" or "abnormal" by ensembling two different deep learning architectures. In the first network (Network 1), we applied transfer learning to the Inception V3 network by using 409 labeled samples. As a second network (Network 2), we designed a convolutional neural network to take advantage of auto-encoders by using additional 673 unlabeled eardrum samples. The individual classification accuracies of the Network 1 and Network 2 were calculated as 84.4%(+/- 12.1%) and 82.6% (+/- 11.3%), respectively. Only 32% of the errors of the two networks were the same, making it possible to combine two approaches to achieve better classification accuracy. The proposed ensemble method allows us to achieve robust classification because it has high accuracy (84.4%) with the lowest standard deviation (+/- 10.3%).

Generalized quantum kinetic expansion: Higher-order corrections to multichromophoric Förster theory

NASA Astrophysics Data System (ADS)

Wu, Jianlan; Gong, Zhihao; Tang, Zhoufei

2015-08-01

For a general two-cluster energy transfer network, a new methodology of the generalized quantum kinetic expansion (GQKE) method is developed, which predicts an exact time-convolution equation for the cluster population evolution under the initial condition of the local cluster equilibrium state. The cluster-to-cluster rate kernel is expanded over the inter-cluster couplings. The lowest second-order GQKE rate recovers the multichromophoric Förster theory (MCFT) rate. The higher-order corrections to the MCFT rate are systematically included using the continued fraction resummation form, resulting in the resummed GQKE method. The reliability of the GQKE methodology is verified in two model systems, revealing the relevance of higher-order corrections.

Detection and diagnosis of colitis on computed tomography using deep convolutional neural networks.

PubMed

Liu, Jiamin; Wang, David; Lu, Le; Wei, Zhuoshi; Kim, Lauren; Turkbey, Evrim B; Sahiner, Berkman; Petrick, Nicholas A; Summers, Ronald M

2017-09-01

Colitis refers to inflammation of the inner lining of the colon that is frequently associated with infection and allergic reactions. In this paper, we propose deep convolutional neural networks methods for lesion-level colitis detection and a support vector machine (SVM) classifier for patient-level colitis diagnosis on routine abdominal CT scans. The recently developed Faster Region-based Convolutional Neural Network (Faster RCNN) is utilized for lesion-level colitis detection. For each 2D slice, rectangular region proposals are generated by region proposal networks (RPN). Then, each region proposal is jointly classified and refined by a softmax classifier and bounding-box regressor. Two convolutional neural networks, eight layers of ZF net and 16 layers of VGG net are compared for colitis detection. Finally, for each patient, the detections on all 2D slices are collected and a SVM classifier is applied to develop a patient-level diagnosis. We trained and evaluated our method with 80 colitis patients and 80 normal cases using 4 × 4-fold cross validation. For lesion-level colitis detection, with ZF net, the mean of average precisions (mAP) were 48.7% and 50.9% for RCNN and Faster RCNN, respectively. The detection system achieved sensitivities of 51.4% and 54.0% at two false positives per patient for RCNN and Faster RCNN, respectively. With VGG net, Faster RCNN increased the mAP to 56.9% and increased the sensitivity to 58.4% at two false positive per patient. For patient-level colitis diagnosis, with ZF net, the average areas under the ROC curve (AUC) were 0.978 ± 0.009 and 0.984 ± 0.008 for RCNN and Faster RCNN method, respectively. The difference was not statistically significant with P = 0.18. At the optimal operating point, the RCNN method correctly identified 90.4% (72.3/80) of the colitis patients and 94.0% (75.2/80) of normal cases. The sensitivity improved to 91.6% (73.3/80) and the specificity improved to 95.0% (76.0/80) for the Faster RCNN method. With VGG net, Faster RCNN increased the AUC to 0.986 ± 0.007 and increased the diagnosis sensitivity to 93.7% (75.0/80) and specificity was unchanged at 95.0% (76.0/80). Colitis detection and diagnosis by deep convolutional neural networks is accurate and promising for future clinical application. Published 2017. This article is a U.S. Government work and is in the public domain in the USA.

Nested neural networks

NASA Technical Reports Server (NTRS)

Baram, Yoram

1988-01-01

Nested neural networks, consisting of small interconnected subnetworks, allow for the storage and retrieval of neural state patterns of different sizes. The subnetworks are naturally categorized by layers of corresponding to spatial frequencies in the pattern field. The storage capacity and the error correction capability of the subnetworks generally increase with the degree of connectivity between layers (the nesting degree). Storage of only few subpatterns in each subnetworks results in a vast storage capacity of patterns and subpatterns in the nested network, maintaining high stability and error correction capability.

The Communication Link and Error ANalysis (CLEAN) simulator

NASA Technical Reports Server (NTRS)

Ebel, William J.; Ingels, Frank M.; Crowe, Shane

1993-01-01

During the period July 1, 1993 through December 30, 1993, significant developments to the Communication Link and Error ANalysis (CLEAN) simulator were completed and include: (1) Soft decision Viterbi decoding; (2) node synchronization for the Soft decision Viterbi decoder; (3) insertion/deletion error programs; (4) convolutional encoder; (5) programs to investigate new convolutional codes; (6) pseudo-noise sequence generator; (7) soft decision data generator; (8) RICE compression/decompression (integration of RICE code generated by Pen-Shu Yeh at Goddard Space Flight Center); (9) Markov Chain channel modeling; (10) percent complete indicator when a program is executed; (11) header documentation; and (12) help utility. The CLEAN simulation tool is now capable of simulating a very wide variety of satellite communication links including the TDRSS downlink with RFI. The RICE compression/decompression schemes allow studies to be performed on error effects on RICE decompressed data. The Markov Chain modeling programs allow channels with memory to be simulated. Memory results from filtering, forward error correction encoding/decoding, differential encoding/decoding, channel RFI, nonlinear transponders and from many other satellite system processes. Besides the development of the simulation, a study was performed to determine whether the PCI provides a performance improvement for the TDRSS downlink. There exist RFI with several duty cycles for the TDRSS downlink. We conclude that the PCI does not improve performance for any of these interferers except possibly one which occurs for the TDRS East. Therefore, the usefulness of the PCI is a function of the time spent transmitting data to the WSGT through the TDRS East transponder.

Generalization error analysis: deep convolutional neural network in mammography

NASA Astrophysics Data System (ADS)

Richter, Caleb D.; Samala, Ravi K.; Chan, Heang-Ping; Hadjiiski, Lubomir; Cha, Kenny

2018-02-01

We conducted a study to gain understanding of the generalizability of deep convolutional neural networks (DCNNs) given their inherent capability to memorize data. We examined empirically a specific DCNN trained for classification of masses on mammograms. Using a data set of 2,454 lesions from 2,242 mammographic views, a DCNN was trained to classify masses into malignant and benign classes using transfer learning from ImageNet LSVRC-2010. We performed experiments with varying amounts of label corruption and types of pixel randomization to analyze the generalization error for the DCNN. Performance was evaluated using the area under the receiver operating characteristic curve (AUC) with an N-fold cross validation. Comparisons were made between the convergence times, the inference AUCs for both the training set and the test set of the original image patches without corruption, and the root-mean-squared difference (RMSD) in the layer weights of the DCNN trained with different amounts and methods of corruption. Our experiments observed trends which revealed that the DCNN overfitted by memorizing corrupted data. More importantly, this study improved our understanding of DCNN weight updates when learning new patterns or new labels. Although we used a specific classification task with the ImageNet as example, similar methods may be useful for analysis of the DCNN learning processes, especially those that employ transfer learning for medical image analysis where sample size is limited and overfitting risk is high.

Off-resonance artifacts correction with convolution in k-space (ORACLE).

PubMed

Lin, Wei; Huang, Feng; Simonotto, Enrico; Duensing, George R; Reykowski, Arne

2012-06-01

Off-resonance artifacts hinder the wider applicability of echo-planar imaging and non-Cartesian MRI methods such as radial and spiral. In this work, a general and rapid method is proposed for off-resonance artifacts correction based on data convolution in k-space. The acquired k-space is divided into multiple segments based on their acquisition times. Off-resonance-induced artifact within each segment is removed by applying a convolution kernel, which is the Fourier transform of an off-resonance correcting spatial phase modulation term. The field map is determined from the inverse Fourier transform of a basis kernel, which is calibrated from data fitting in k-space. The technique was demonstrated in phantom and in vivo studies for radial, spiral and echo-planar imaging datasets. For radial acquisitions, the proposed method allows the self-calibration of the field map from the imaging data, when an alternating view-angle ordering scheme is used. An additional advantage for off-resonance artifacts correction based on data convolution in k-space is the reusability of convolution kernels to images acquired with the same sequence but different contrasts. Copyright © 2011 Wiley-Liss, Inc.

Convolutional neural network for road extraction

NASA Astrophysics Data System (ADS)

Li, Junping; Ding, Yazhou; Feng, Fajie; Xiong, Baoyu; Cui, Weihong

2017-11-01

In this paper, the convolution neural network with large block input and small block output was used to extract road. To reflect the complex road characteristics in the study area, a deep convolution neural network VGG19 was conducted for road extraction. Based on the analysis of the characteristics of different sizes of input block, output block and the extraction effect, the votes of deep convolutional neural networks was used as the final road prediction. The study image was from GF-2 panchromatic and multi-spectral fusion in Yinchuan. The precision of road extraction was 91%. The experiments showed that model averaging can improve the accuracy to some extent. At the same time, this paper gave some advice about the choice of input block size and output block size.

Electron beam lithographic modeling assisted by artificial intelligence technology

NASA Astrophysics Data System (ADS)

Nakayamada, Noriaki; Nishimura, Rieko; Miura, Satoru; Nomura, Haruyuki; Kamikubo, Takashi

2017-07-01

We propose a new concept of tuning a point-spread function (a "kernel" function) in the modeling of electron beam lithography using the machine learning scheme. Normally in the work of artificial intelligence, the researchers focus on the output results from a neural network, such as success ratio in image recognition or improved production yield, etc. In this work, we put more focus on the weights connecting the nodes in a convolutional neural network, which are naturally the fractions of a point-spread function, and take out those weighted fractions after learning to be utilized as a tuned kernel. Proof-of-concept of the kernel tuning has been demonstrated using the examples of proximity effect correction with 2-layer network, and charging effect correction with 3-layer network. This type of new tuning method can be beneficial to give researchers more insights to come up with a better model, yet it might be too early to be deployed to production to give better critical dimension (CD) and positional accuracy almost instantly.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Olama, Mohammed M; Matalgah, Mustafa M; Bobrek, Miljko

Traditional encryption techniques require packet overhead, produce processing time delay, and suffer from severe quality of service deterioration due to fades and interference in wireless channels. These issues reduce the effective transmission data rate (throughput) considerably in wireless communications, where data rate with limited bandwidth is the main constraint. In this paper, performance evaluation analyses are conducted for an integrated signaling-encryption mechanism that is secure and enables improved throughput and probability of bit-error in wireless channels. This mechanism eliminates the drawbacks stated herein by encrypting only a small portion of an entire transmitted frame, while the rest is not subjectmore » to traditional encryption but goes through a signaling process (designed transformation) with the plaintext of the portion selected for encryption. We also propose to incorporate error correction coding solely on the small encrypted portion of the data to drastically improve the overall bit-error rate performance while not noticeably increasing the required bit-rate. We focus on validating the signaling-encryption mechanism utilizing Hamming and convolutional error correction coding by conducting an end-to-end system-level simulation-based study. The average probability of bit-error and throughput of the encryption mechanism are evaluated over standard Gaussian and Rayleigh fading-type channels and compared to the ones of the conventional advanced encryption standard (AES).« less

The proposed coding standard at GSFC

NASA Technical Reports Server (NTRS)

Morakis, J. C.; Helgert, H. J.

1977-01-01

As part of the continuing effort to introduce standardization of spacecraft and ground equipment in satellite systems, NASA's Goddard Space Flight Center and other NASA facilities have supported the development of a set of standards for the use of error control coding in telemetry subsystems. These standards are intended to ensure compatibility between spacecraft and ground encoding equipment, while allowing sufficient flexibility to meet all anticipated mission requirements. The standards which have been developed to date cover the application of block codes in error detection and error correction modes, as well as short and long constraint length convolutional codes decoded via the Viterbi and sequential decoding algorithms, respectively. Included are detailed specifications of the codes, and their implementation. Current effort is directed toward the development of standards covering channels with burst noise characteristics, channels with feedback, and code concatenation.

A small terminal for satellite communication systems

NASA Technical Reports Server (NTRS)

Xiong, Fuqin; Wu, Dong; Jin, Min

1994-01-01

A small portable, low-cost satellite communications terminal system incorporating a modulator/demodulator and convolutional-Viterbi coder/decoder is described. Advances in signal processing and error-correction techniques in combination with higher power and higher frequencies aboard satellites allow for more efficient use of the space segment. This makes it possible to design small economical earth stations. The Advanced Communications Technology Satellite (ACTS) was chosen to test the system. ACTS, operating at the Ka band incorporates higher power, higher frequency, frequency and spatial reuse using spot beams and polarization.

Frame prediction using recurrent convolutional encoder with residual learning

NASA Astrophysics Data System (ADS)

Yue, Boxuan; Liang, Jun

2018-05-01

The prediction for the frame of a video is difficult but in urgent need in auto-driving. Conventional methods can only predict some abstract trends of the region of interest. The boom of deep learning makes the prediction for frames possible. In this paper, we propose a novel recurrent convolutional encoder and DE convolutional decoder structure to predict frames. We introduce the residual learning in the convolution encoder structure to solve the gradient issues. The residual learning can transform the gradient back propagation to an identity mapping. It can reserve the whole gradient information and overcome the gradient issues in Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN). Besides, compared with the branches in CNNs and the gated structures in RNNs, the residual learning can save the training time significantly. In the experiments, we use UCF101 dataset to train our networks, the predictions are compared with some state-of-the-art methods. The results show that our networks can predict frames fast and efficiently. Furthermore, our networks are used for the driving video to verify the practicability.

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

NASA Astrophysics Data System (ADS)

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

2017-10-01

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

Automatic cerebrospinal fluid segmentation in non-contrast CT images using a 3D convolutional network

NASA Astrophysics Data System (ADS)

Patel, Ajay; van de Leemput, Sil C.; Prokop, Mathias; van Ginneken, Bram; Manniesing, Rashindra

2017-03-01

Segmentation of anatomical structures is fundamental in the development of computer aided diagnosis systems for cerebral pathologies. Manual annotations are laborious, time consuming and subject to human error and observer variability. Accurate quantification of cerebrospinal fluid (CSF) can be employed as a morphometric measure for diagnosis and patient outcome prediction. However, segmenting CSF in non-contrast CT images is complicated by low soft tissue contrast and image noise. In this paper we propose a state-of-the-art method using a multi-scale three-dimensional (3D) fully convolutional neural network (CNN) to automatically segment all CSF within the cranial cavity. The method is trained on a small dataset comprised of four manually annotated cerebral CT images. Quantitative evaluation of a separate test dataset of four images shows a mean Dice similarity coefficient of 0.87 +/- 0.01 and mean absolute volume difference of 4.77 +/- 2.70 %. The average prediction time was 68 seconds. Our method allows for fast and fully automated 3D segmentation of cerebral CSF in non-contrast CT, and shows promising results despite a limited amount of training data.

Deep neural networks for texture classification-A theoretical analysis.

PubMed

Basu, Saikat; Mukhopadhyay, Supratik; Karki, Manohar; DiBiano, Robert; Ganguly, Sangram; Nemani, Ramakrishna; Gayaka, Shreekant

2018-01-01

We investigate the use of Deep Neural Networks for the classification of image datasets where texture features are important for generating class-conditional discriminative representations. To this end, we first derive the size of the feature space for some standard textural features extracted from the input dataset and then use the theory of Vapnik-Chervonenkis dimension to show that hand-crafted feature extraction creates low-dimensional representations which help in reducing the overall excess error rate. As a corollary to this analysis, we derive for the first time upper bounds on the VC dimension of Convolutional Neural Network as well as Dropout and Dropconnect networks and the relation between excess error rate of Dropout and Dropconnect networks. The concept of intrinsic dimension is used to validate the intuition that texture-based datasets are inherently higher dimensional as compared to handwritten digits or other object recognition datasets and hence more difficult to be shattered by neural networks. We then derive the mean distance from the centroid to the nearest and farthest sampling points in an n-dimensional manifold and show that the Relative Contrast of the sample data vanishes as dimensionality of the underlying vector space tends to infinity. Copyright © 2017 Elsevier Ltd. All rights reserved.

Resting-state fMRI data reflects default network activity rather than null data: A defense of commonly employed methods to correct for multiple comparisons.

PubMed

Slotnick, Scott D

2017-07-01

Analysis of functional magnetic resonance imaging (fMRI) data typically involves over one hundred thousand independent statistical tests; therefore, it is necessary to correct for multiple comparisons to control familywise error. In a recent paper, Eklund, Nichols, and Knutsson used resting-state fMRI data to evaluate commonly employed methods to correct for multiple comparisons and reported unacceptable rates of familywise error. Eklund et al.'s analysis was based on the assumption that resting-state fMRI data reflect null data; however, their 'null data' actually reflected default network activity that inflated familywise error. As such, Eklund et al.'s results provide no basis to question the validity of the thousands of published fMRI studies that have corrected for multiple comparisons or the commonly employed methods to correct for multiple comparisons.

Collaborative identification method for sea battlefield target based on deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Zheng, Guangdi; Pan, Mingbo; Liu, Wei; Wu, Xuetong

2018-03-01

The target identification of the sea battlefield is the prerequisite for the judgment of the enemy in the modern naval battle. In this paper, a collaborative identification method based on convolution neural network is proposed to identify the typical targets of sea battlefields. Different from the traditional single-input/single-output identification method, the proposed method constructs a multi-input/single-output co-identification architecture based on optimized convolution neural network and weighted D-S evidence theory. The simulation results show that

Melanoma segmentation based on deep learning.

PubMed

Zhang, Xiaoqing

2017-12-01

Malignant melanoma is one of the most deadly forms of skin cancer, which is one of the world's fastest-growing cancers. Early diagnosis and treatment is critical. In this study, a neural network structure is utilized to construct a broad and accurate basis for the diagnosis of skin cancer, thereby reducing screening errors. The technique is able to improve the efficacy for identification of normally indistinguishable lesions (such as pigment spots) versus clinically unknown lesions, and to ultimately improve the diagnostic accuracy. In the field of medical imaging, in general, using neural networks for image segmentation is relatively rare. The existing traditional machine-learning neural network algorithms still cannot completely solve the problem of information loss, nor detect the precise division of the boundary area. We use an improved neural network framework, described herein, to achieve efficacious feature learning, and satisfactory segmentation of melanoma images. The architecture of the network includes multiple convolution layers, dropout layers, softmax layers, multiple filters, and activation functions. The number of data sets can be increased via rotation of the training set. A non-linear activation function (such as ReLU and ELU) is employed to alleviate the problem of gradient disappearance, and RMSprop/Adam are incorporated to optimize the loss algorithm. A batch normalization layer is added between the convolution layer and the activation layer to solve the problem of gradient disappearance and explosion. Experiments, described herein, show that our improved neural network architecture achieves higher accuracy for segmentation of melanoma images as compared with existing processes.

The VLSI design of an error-trellis syndrome decoder for certain convolutional codes

NASA Technical Reports Server (NTRS)

Reed, I. S.; Jensen, J. M.; Hsu, I.-S.; Truong, T. K.

1986-01-01

A recursive algorithm using the error-trellis decoding technique is developed to decode convolutional codes (CCs). An example, illustrating the very large scale integration (VLSI) architecture of such a decode, is given for a dual-K CC. It is demonstrated that such a decoder can be realized readily on a single chip with metal-nitride-oxide-semiconductor technology.

The VLSI design of error-trellis syndrome decoding for convolutional codes

NASA Technical Reports Server (NTRS)

Reed, I. S.; Jensen, J. M.; Truong, T. K.; Hsu, I. S.

1985-01-01

A recursive algorithm using the error-trellis decoding technique is developed to decode convolutional codes (CCs). An example, illustrating the very large scale integration (VLSI) architecture of such a decode, is given for a dual-K CC. It is demonstrated that such a decoder can be realized readily on a single chip with metal-nitride-oxide-semiconductor technology.

Two high-density recording methods with run-length limited turbo code for holographic data storage system

NASA Astrophysics Data System (ADS)

Nakamura, Yusuke; Hoshizawa, Taku

2016-09-01

Two methods for increasing the data capacity of a holographic data storage system (HDSS) were developed. The first method is called “run-length-limited (RLL) high-density recording”. An RLL modulation has the same effect as enlarging the pixel pitch; namely, it optically reduces the hologram size. Accordingly, the method doubles the raw-data recording density. The second method is called “RLL turbo signal processing”. The RLL turbo code consists of \\text{RLL}(1,∞ ) trellis modulation and an optimized convolutional code. The remarkable point of the developed turbo code is that it employs the RLL modulator and demodulator as parts of the error-correction process. The turbo code improves the capability of error correction more than a conventional LDPC code, even though interpixel interference is generated. These two methods will increase the data density 1.78-fold. Moreover, by simulation and experiment, a data density of 2.4 Tbit/in.2 is confirmed.

125Mbps ultra-wideband system evaluation for cortical implant devices.

PubMed

Luo, Yi; Winstead, Chris; Chiang, Patrick

2012-01-01

This paper evaluates the performance of a 125Mbps Impulse Ratio Ultra-Wideband (IR-UWB) system for cortical implant devices by using low-Q inductive coil link operating in the near-field domain. We examine design tradeoffs between transmitted signal amplitude, reliability, noise and clock jitter. The IR-UWB system is modeled using measured parameters from a reported UWB transceiver implemented in 90nm-CMOS technology. Non-optimized inductive coupling coils with low-Q value for near-field data transmission are modeled in order to build a full channel from the transmitter (Tx) to the receiver (Rx). On-off keying (OOK) modulation is used together with a low-complexity convolutional error correcting code. The simulation results show that even though the low-Q coils decrease the amplitude of the received pulses, the UWB system can still achieve acceptable performance when error correction is used. These results predict that UWB is a good candidate for delivering high data rates in cortical implant devices.

Error control techniques for satellite and space communications

NASA Technical Reports Server (NTRS)

Costello, Daniel J., Jr.

1992-01-01

Worked performed during the reporting period is summarized. Construction of robustly good trellis codes for use with sequential decoding was developed. The robustly good trellis codes provide a much better trade off between free distance and distance profile. The unequal error protection capabilities of convolutional codes was studied. The problem of finding good large constraint length, low rate convolutional codes for deep space applications is investigated. A formula for computing the free distance of 1/n convolutional codes was discovered. Double memory (DM) codes, codes with two memory units per unit bit position, were studied; a search for optimal DM codes is being conducted. An algorithm for constructing convolutional codes from a given quasi-cyclic code was developed. Papers based on the above work are included in the appendix.

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

NASA Astrophysics Data System (ADS)

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.

76 FR 78620 - Notice of Intent To Grant an Exclusive License; Voltage Networking, LLC; Correction

Federal Register 2010, 2011, 2012, 2013, 2014

2011-12-19

... fourth line, the word ``non-assignable'' was incorrectly published. This notice corrects that error. FOR... Networking, LLC. Subsequent to the publication of that notice, DoD discovered that the word ``non-assignable...

Automated Agatston score computation in non-ECG gated CT scans using deep learning

NASA Astrophysics Data System (ADS)

Cano-Espinosa, Carlos; González, Germán.; Washko, George R.; Cazorla, Miguel; San José Estépar, Raúl

2018-03-01

Introduction: The Agatston score is a well-established metric of cardiovascular disease related to clinical outcomes. It is computed from CT scans by a) measuring the volume and intensity of the atherosclerotic plaques and b) aggregating such information in an index. Objective: To generate a convolutional neural network that inputs a non-contrast chest CT scan and outputs the Agatston score associated with it directly, without a prior segmentation of Coronary Artery Calcifications (CAC). Materials and methods: We use a database of 5973 non-contrast non-ECG gated chest CT scans where the Agatston score has been manually computed. The heart of each scan is cropped automatically using an object detector. The database is split in 4973 cases for training and 1000 for testing. We train a 3D deep convolutional neural network to regress the Agatston score directly from the extracted hearts. Results: The proposed method yields a Pearson correlation coefficient of r = 0.93; p <= 0.0001 against manual reference standard in the 1000 test cases. It further stratifies correctly 72.6% of the cases with respect to standard risk groups. This compares to more complex state-of-the-art methods based on prior segmentations of the CACs, which achieve r = 0.94 in ECG-gated pulmonary CT. Conclusions: A convolutional neural network can regress the Agatston score from the image of the heart directly, without a prior segmentation of the CACs. This is a new and simpler paradigm in the Agatston score computation that yields similar results to the state-of-the-art literature.

Detecting atrial fibrillation by deep convolutional neural networks.

PubMed

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.

Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks

PubMed Central

Yu, Haiyang; Wu, Zhihai; Wang, Shuqin; Wang, Yunpeng; Ma, Xiaolei

2017-01-01

Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network. Network-wide traffic speeds are converted into a series of static images and input into a novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for traffic forecasting. The proposed SRCNs inherit the advantages of deep convolutional neural networks (DCNNs) and long short-term memory (LSTM) neural networks. The spatial dependencies of network-wide traffic can be captured by DCNNs, and the temporal dynamics can be learned by LSTMs. An experiment on a Beijing transportation network with 278 links demonstrates that SRCNs outperform other deep learning-based algorithms in both short-term and long-term traffic prediction. PMID:28672867

Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks.

PubMed

Yu, Haiyang; Wu, Zhihai; Wang, Shuqin; Wang, Yunpeng; Ma, Xiaolei

2017-06-26

Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network. Network-wide traffic speeds are converted into a series of static images and input into a novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for traffic forecasting. The proposed SRCNs inherit the advantages of deep convolutional neural networks (DCNNs) and long short-term memory (LSTM) neural networks. The spatial dependencies of network-wide traffic can be captured by DCNNs, and the temporal dynamics can be learned by LSTMs. An experiment on a Beijing transportation network with 278 links demonstrates that SRCNs outperform other deep learning-based algorithms in both short-term and long-term traffic prediction.

Network Adjustment of Orbit Errors in SAR Interferometry

NASA Astrophysics Data System (ADS)

Bahr, Hermann; Hanssen, Ramon

2010-03-01

Orbit errors can induce significant long wavelength error signals in synthetic aperture radar (SAR) interferograms and thus bias estimates of wide-scale deformation phenomena. The presented approach aims for correcting orbit errors in a preprocessing step to deformation analysis by modifying state vectors. Whereas absolute errors in the orbital trajectory are negligible, the influence of relative errors (baseline errors) is parametrised by their parallel and perpendicular component as a linear function of time. As the sensitivity of the interferometric phase is only significant with respect to the perpendicular base-line and the rate of change of the parallel baseline, the algorithm focuses on estimating updates to these two parameters. This is achieved by a least squares approach, where the unwrapped residual interferometric phase is observed and atmospheric contributions are considered to be stochastic with constant mean. To enhance reliability, baseline errors are adjusted in an overdetermined network of interferograms, yielding individual orbit corrections per acquisition.

Exemplar-Based Image and Video Stylization Using Fully Convolutional Semantic Features.

PubMed

Zhu, Feida; Yan, Zhicheng; Bu, Jiajun; Yu, Yizhou

2017-05-10

Color and tone stylization in images and videos strives to enhance unique themes with artistic color and tone adjustments. It has a broad range of applications from professional image postprocessing to photo sharing over social networks. Mainstream photo enhancement softwares, such as Adobe Lightroom and Instagram, provide users with predefined styles, which are often hand-crafted through a trial-and-error process. Such photo adjustment tools lack a semantic understanding of image contents and the resulting global color transform limits the range of artistic styles it can represent. On the other hand, stylistic enhancement needs to apply distinct adjustments to various semantic regions. Such an ability enables a broader range of visual styles. In this paper, we first propose a novel deep learning architecture for exemplar-based image stylization, which learns local enhancement styles from image pairs. Our deep learning architecture consists of fully convolutional networks (FCNs) for automatic semantics-aware feature extraction and fully connected neural layers for adjustment prediction. Image stylization can be efficiently accomplished with a single forward pass through our deep network. To extend our deep network from image stylization to video stylization, we exploit temporal superpixels (TSPs) to facilitate the transfer of artistic styles from image exemplars to videos. Experiments on a number of datasets for image stylization as well as a diverse set of video clips demonstrate the effectiveness of our deep learning architecture.

Iterative deep convolutional encoder-decoder network for medical image segmentation.

PubMed

Jung Uk Kim; Hak Gu Kim; Yong Man Ro

2017-07-01

In this paper, we propose a novel medical image segmentation using iterative deep learning framework. We have combined an iterative learning approach and an encoder-decoder network to improve segmentation results, which enables to precisely localize the regions of interest (ROIs) including complex shapes or detailed textures of medical images in an iterative manner. The proposed iterative deep convolutional encoder-decoder network consists of two main paths: convolutional encoder path and convolutional decoder path with iterative learning. Experimental results show that the proposed iterative deep learning framework is able to yield excellent medical image segmentation performances for various medical images. The effectiveness of the proposed method has been proved by comparing with other state-of-the-art medical image segmentation methods.

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

NASA Astrophysics Data System (ADS)

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

2017-09-01

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

Fully Convolutional Architecture for Low-Dose CT Image Noise Reduction

NASA Astrophysics Data System (ADS)

Badretale, S.; Shaker, F.; Babyn, P.; Alirezaie, J.

2017-10-01

One of the critical topics in medical low-dose Computed Tomography (CT) imaging is how best to maintain image quality. As the quality of images decreases with lowering the X-ray radiation dose, improving image quality is extremely important and challenging. We have proposed a novel approach to denoise low-dose CT images. Our algorithm learns directly from an end-to-end mapping from the low-dose Computed Tomography images for denoising the normal-dose CT images. Our method is based on a deep convolutional neural network with rectified linear units. By learning various low-level to high-level features from a low-dose image the proposed algorithm is capable of creating a high-quality denoised image. We demonstrate the superiority of our technique by comparing the results with two other state-of-the-art methods in terms of the peak signal to noise ratio, root mean square error, and a structural similarity index.

Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology.

PubMed

Sharma, Harshita; Zerbe, Norman; Klempert, Iris; Hellwich, Olaf; Hufnagl, Peter

2017-11-01

Deep learning using convolutional neural networks is an actively emerging field in histological image analysis. This study explores deep learning methods for computer-aided classification in H&E stained histopathological whole slide images of gastric carcinoma. An introductory convolutional neural network architecture is proposed for two computerized applications, namely, cancer classification based on immunohistochemical response and necrosis detection based on the existence of tumor necrosis in the tissue. Classification performance of the developed deep learning approach is quantitatively compared with traditional image analysis methods in digital histopathology requiring prior computation of handcrafted features, such as statistical measures using gray level co-occurrence matrix, Gabor filter-bank responses, LBP histograms, gray histograms, HSV histograms and RGB histograms, followed by random forest machine learning. Additionally, the widely known AlexNet deep convolutional framework is comparatively analyzed for the corresponding classification problems. The proposed convolutional neural network architecture reports favorable results, with an overall classification accuracy of 0.6990 for cancer classification and 0.8144 for necrosis detection. Copyright © 2017 Elsevier Ltd. All rights reserved.

Medical reliable network using concatenated channel codes through GSM network.

PubMed

Ahmed, Emtithal; Kohno, Ryuji

2013-01-01

Although the 4(th) generation (4G) of global mobile communication network, i.e. Long Term Evolution (LTE) coexisting with the 3(rd) generation (3G) has successfully started; the 2(nd) generation (2G), i.e. Global System for Mobile communication (GSM) still playing an important role in many developing countries. Without any other reliable network infrastructure, GSM can be applied for tele-monitoring applications, where high mobility and low cost are necessary. A core objective of this paper is to introduce the design of a more reliable and dependable Medical Network Channel Code system (MNCC) through GSM Network. MNCC design based on simple concatenated channel code, which is cascade of an inner code (GSM) and an extra outer code (Convolution Code) in order to protect medical data more robust against channel errors than other data using the existing GSM network. In this paper, the MNCC system will provide Bit Error Rate (BER) equivalent to the BER for medical tele monitoring of physiological signals, which is 10(-5) or less. The performance of the MNCC has been proven and investigated using computer simulations under different channels condition such as, Additive White Gaussian Noise (AWGN), Rayleigh noise and burst noise. Generally the MNCC system has been providing better performance as compared to GSM.

Robust hepatic vessel segmentation using multi deep convolution network

NASA Astrophysics Data System (ADS)

Kitrungrotsakul, Titinunt; Han, Xian-Hua; Iwamoto, Yutaro; Foruzan, Amir Hossein; Lin, Lanfen; Chen, Yen-Wei

2017-03-01

Extraction of blood vessels of the organ is a challenging task in the area of medical image processing. It is really difficult to get accurate vessel segmentation results even with manually labeling by human being. The difficulty of vessels segmentation is the complicated structure of blood vessels and its large variations that make them hard to recognize. In this paper, we present deep artificial neural network architecture to automatically segment the hepatic vessels from computed tomography (CT) image. We proposed novel deep neural network (DNN) architecture for vessel segmentation from a medical CT volume, which consists of three deep convolution neural networks to extract features from difference planes of CT data. The three networks have share features at the first convolution layer but will separately learn their own features in the second layer. All three networks will join again at the top layer. To validate effectiveness and efficiency of our proposed method, we conduct experiments on 12 CT volumes which training data are randomly generate from 5 CT volumes and 7 using for test. Our network can yield an average dice coefficient 0.830, while 3D deep convolution neural network can yield around 0.7 and multi-scale can yield only 0.6.

Traffic sign recognition based on deep convolutional neural network

NASA Astrophysics Data System (ADS)

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.

Scatter and veiling glare corrections for quantitative digital subtraction angiography

NASA Astrophysics Data System (ADS)

Ersahin, Atila; Molloi, Sabee Y.; Qian, Yao-Jin

1994-05-01

In order to quantitate anatomical and physiological parameters such as vessel dimensions and volumetric blood flow, it is necessary to make corrections for scatter and veiling glare (SVG), which are the major sources of nonlinearities in videodensitometric digital subtraction angiography (DSA). A convolution filtering technique has been investigated to estimate SVG distribution in DSA images without the need to sample the SVG for each patient. This technique utilizes exposure parameters and image gray levels to estimate SVG intensity by predicting the total thickness for every pixel in the image. At this point, corrections were also made for variation of SVG fraction with beam energy and field size. To test its ability to estimate SVG intensity, the correction technique was applied to images of a Lucite step phantom, anthropomorphic chest phantom, head phantom, and animal models at different thicknesses, projections, and beam energies. The root-mean-square (rms) percentage error of these estimates were obtained by comparison with direct SVG measurements made behind a lead strip. The average rms percentage errors in the SVG estimate for the 25 phantom studies and for the 17 animal studies were 6.22% and 7.96%, respectively. These results indicate that the SVG intensity can be estimated for a wide range of thicknesses, projections, and beam energies.

Patient-specific and global convolutional neural networks for robust automatic liver tumor delineation in follow-up CT studies.

PubMed

Vivanti, Refael; Joskowicz, Leo; Lev-Cohain, Naama; Ephrat, Ariel; Sosna, Jacob

2018-03-10

Radiological longitudinal follow-up of tumors in CT scans is essential for disease assessment and liver tumor therapy. Currently, most tumor size measurements follow the RECIST guidelines, which can be off by as much as 50%. True volumetric measurements are more accurate but require manual delineation, which is time-consuming and user-dependent. We present a convolutional neural networks (CNN) based method for robust automatic liver tumor delineation in longitudinal CT studies that uses both global and patient specific CNNs trained on a small database of delineated images. The inputs are the baseline scan and the tumor delineation, a follow-up scan, and a liver tumor global CNN voxel classifier built from radiologist-validated liver tumor delineations. The outputs are the tumor delineations in the follow-up CT scan. The baseline scan tumor delineation serves as a high-quality prior for the tumor characterization in the follow-up scans. It is used to evaluate the global CNN performance on the new case and to reliably predict failures of the global CNN on the follow-up scan. High-scoring cases are segmented with a global CNN; low-scoring cases, which are predicted to be failures of the global CNN, are segmented with a patient-specific CNN built from the baseline scan. Our experimental results on 222 tumors from 31 patients yield an average overlap error of 17% (std = 11.2) and surface distance of 2.1 mm (std = 1.8), far better than stand-alone segmentation. Importantly, the robustness of our method improved from 67% for stand-alone global CNN segmentation to 100%. Unlike other medical imaging deep learning approaches, which require large annotated training datasets, our method exploits the follow-up framework to yield accurate tumor tracking and failure detection and correction with a small training dataset. Graphical abstract Flow diagram of the proposed method. In the offline mode (orange), a global CNN is trained as a voxel classifier to segment liver tumor as in [31]. The online mode (blue) is used for each new case. The input is baseline scan with delineation and the follow-up CT scan to be segmented. The main novelty is the ability to predict failures by trying the system on the baseline scan and the ability to correct them using the patient-specific CNN.

Improving accuracy of simultaneously reconstructed activity and attenuation maps using deep learning.

PubMed

Hwang, Donghwi; Kim, Kyeong Yun; Kang, Seung Kwan; Seo, Seongho; Paeng, Jin Chul; Lee, Dong Soo; Lee, Jae Sung

2018-02-15

Simultaneous reconstruction of activity and attenuation using the maximum likelihood reconstruction of activity and attenuation (MLAA) augmented by time-of-flight (TOF) information is a promising method for positron emission tomography (PET) attenuation correction. However, it still suffers from several problems, including crosstalk artifacts, slow convergence speed, and noisy attenuation maps (μ-maps). In this work, we developed deep convolutional neural networks (CNNs) to overcome these MLAA limitations, and we verified their feasibility using a clinical brain PET data set. Methods: We applied the proposed method to one of the most challenging PET cases for simultaneous image reconstruction ( 18 F-FP-CIT PET scans with highly specific binding to striatum of the brain). Three different CNN architectures (convolutional autoencoder (CAE), U-net, hybrid of CAE and U-net) were designed and trained to learn x-ray computed tomography (CT) derived μ-map (μ-CT) from the MLAA-generated activity distribution and μ-map (μ-MLAA). PET/CT data of 40 patients with suspected Parkinson's disease were employed for five-fold cross-validation. For the training of CNNs, 800,000 transverse PET slices and CTs augmented from 32 patient data sets were used. The similarity to μ-CT of the CNN-generated μ-maps (μ-CAE, μ-Unet, and μ-Hybrid) and μ-MLAA was compared using Dice similarity coefficients. In addition, we compared the activity concentration of specific (striatum) and non-specific binding regions (cerebellum and occipital cortex) and the binding ratios in the striatum in the PET activity images reconstructed using those μ-maps. Results: The CNNs generated less noisy and more uniform μ-maps than original μ-MLAA. Moreover, the air cavities and bones were better resolved in the proposed CNN outputs. In addition, the proposed deep learning approach was useful for mitigating the crosstalk problem in the MLAA reconstruction. The hybrid network of CAE and U-net yielded the most similar μ-maps to μ-CT (Dice similarity coefficient in the whole head = 0.79 in the bone and 0.72 in air cavities), resulting in only approximately 5% errors in activity and biding ratio quantification. Conclusion: The proposed deep learning approach is promising for accurate attenuation correction of activity distribution in TOF PET systems. Copyright © 2018 by the Society of Nuclear Medicine and Molecular Imaging, Inc.

Multichannel error correction code decoder

NASA Technical Reports Server (NTRS)

Wagner, Paul K.; Ivancic, William D.

1993-01-01

A brief overview of a processing satellite for a mesh very-small-aperture (VSAT) communications network is provided. The multichannel error correction code (ECC) decoder system, the uplink signal generation and link simulation equipment, and the time-shared decoder are described. The testing is discussed. Applications of the time-shared decoder are recommended.

High performance interconnection between high data rate networks

NASA Technical Reports Server (NTRS)

Foudriat, E. C.; Maly, K.; Overstreet, C. M.; Zhang, L.; Sun, W.

1992-01-01

The bridge/gateway system needed to interconnect a wide range of computer networks to support a wide range of user quality-of-service requirements is discussed. The bridge/gateway must handle a wide range of message types including synchronous and asynchronous traffic, large, bursty messages, short, self-contained messages, time critical messages, etc. It is shown that messages can be classified into three basic classes, synchronous and large and small asynchronous messages. The first two require call setup so that packet identification, buffer handling, etc. can be supported in the bridge/gateway. Identification enables resequences in packet size. The third class is for messages which do not require call setup. Resequencing hardware based to handle two types of resequencing problems is presented. The first is for a virtual parallel circuit which can scramble channel bytes. The second system is effective in handling both synchronous and asynchronous traffic between networks with highly differing packet sizes and data rates. The two other major needs for the bridge/gateway are congestion and error control. A dynamic, lossless congestion control scheme which can easily support effective error correction is presented. Results indicate that the congestion control scheme provides close to optimal capacity under congested conditions. Under conditions where error may develop due to intervening networks which are not lossless, intermediate error recovery and correction takes 1/3 less time than equivalent end-to-end error correction under similar conditions.

High-speed architecture for the decoding of trellis-coded modulation

NASA Technical Reports Server (NTRS)

Osborne, William P.

1992-01-01

Since 1971, when the Viterbi Algorithm was introduced as the optimal method of decoding convolutional codes, improvements in circuit technology, especially VLSI, have steadily increased its speed and practicality. Trellis-Coded Modulation (TCM) combines convolutional coding with higher level modulation (non-binary source alphabet) to provide forward error correction and spectral efficiency. For binary codes, the current stare-of-the-art is a 64-state Viterbi decoder on a single CMOS chip, operating at a data rate of 25 Mbps. Recently, there has been an interest in increasing the speed of the Viterbi Algorithm by improving the decoder architecture, or by reducing the algorithm itself. Designs employing new architectural techniques are now in existence, however these techniques are currently applied to simpler binary codes, not to TCM. The purpose of this report is to discuss TCM architectural considerations in general, and to present the design, at the logic gate level, or a specific TCM decoder which applies these considerations to achieve high-speed decoding.

Multi-Stage Target Tracking with Drift Correction and Position Prediction

NASA Astrophysics Data System (ADS)

Chen, Xin; Ren, Keyan; Hou, Yibin

2018-04-01

Most existing tracking methods are hard to combine accuracy and performance, and do not consider the shift between clarity and blur that often occurs. In this paper, we propound a multi-stage tracking framework with two particular modules: position prediction and corrective measure. We conduct tracking based on correlation filter with a corrective measure module to increase both performance and accuracy. Specifically, a convolutional network is used for solving the blur problem in realistic scene, training methodology that training dataset with blur images generated by the three blur algorithms. Then, we propose a position prediction module to reduce the computation cost and make tracker more capable of fast motion. Experimental result shows that our tracking method is more robust compared to others and more accurate on the benchmark sequences.

Publisher Correction: Evolutionary adaptations to new environments generally reverse plastic phenotypic changes.

PubMed

Ho, Wei-Chin; Zhang, Jianzhi

2018-02-21

The originally published HTML version of this Article contained errors in the three equations in the Methods sub-section 'Metabolic network analysis', whereby the Greek letter eta (η) was inadvertently used in place of beta (β) during the production process. These errors have now been corrected in the HTML version of the Article; the PDF was correct at the time of publication.

A convolutional neural network to filter artifacts in spectroscopic MRI.

PubMed

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.

Detecting of foreign object debris on airfield pavement using convolution neural network

NASA Astrophysics Data System (ADS)

Cao, Xiaoguang; Gu, Yufeng; Bai, Xiangzhi

2017-11-01

It is of great practical significance to detect foreign object debris (FOD) timely and accurately on the airfield pavement, because the FOD is a fatal threaten for runway safety in airport. In this paper, a new FOD detection framework based on Single Shot MultiBox Detector (SSD) is proposed. Two strategies include making the detection network lighter and using dilated convolution, which are proposed to better solve the FOD detection problem. The advantages mainly include: (i) the network structure becomes lighter to speed up detection task and enhance detection accuracy; (ii) dilated convolution is applied in network structure to handle smaller FOD. Thus, we get a faster and more accurate detection system.

Bulk locality and quantum error correction in AdS/CFT

NASA Astrophysics Data System (ADS)

Almheiri, Ahmed; Dong, Xi; Harlow, Daniel

2015-04-01

We point out a connection between the emergence of bulk locality in AdS/CFT and the theory of quantum error correction. Bulk notions such as Bogoliubov transformations, location in the radial direction, and the holographic entropy bound all have natural CFT interpretations in the language of quantum error correction. We also show that the question of whether bulk operator reconstruction works only in the causal wedge or all the way to the extremal surface is related to the question of whether or not the quantum error correcting code realized by AdS/CFT is also a "quantum secret sharing scheme", and suggest a tensor network calculation that may settle the issue. Interestingly, the version of quantum error correction which is best suited to our analysis is the somewhat nonstandard "operator algebra quantum error correction" of Beny, Kempf, and Kribs. Our proposal gives a precise formulation of the idea of "subregion-subregion" duality in AdS/CFT, and clarifies the limits of its validity.

Error control techniques for satellite and space communications

NASA Technical Reports Server (NTRS)

Costello, Daniel J., Jr.

1994-01-01

Brief summaries of research in the following areas are presented: (1) construction of optimum geometrically uniform trellis codes; (2) a statistical approach to constructing convolutional code generators; and (3) calculating the exact performance of a convolutional code.

Coding for spread spectrum packet radios

NASA Technical Reports Server (NTRS)

Omura, J. K.

1980-01-01

Packet radios are often expected to operate in a radio communication network environment where there tends to be man made interference signals. To combat such interference, spread spectrum waveforms are being considered for some applications. The use of convolutional coding with Viterbi decoding to further improve the performance of spread spectrum packet radios is examined. At 0.00001 bit error rates, improvements in performance of 4 db to 5 db can easily be achieved with such coding without any change in data rate nor spread spectrum bandwidth. This coding gain is more dramatic in an interference environment.

The probabilistic convolution tree: efficient exact Bayesian inference for faster LC-MS/MS protein inference.

PubMed

Serang, Oliver

2014-01-01

Exact Bayesian inference can sometimes be performed efficiently for special cases where a function has commutative and associative symmetry of its inputs (called "causal independence"). For this reason, it is desirable to exploit such symmetry on big data sets. Here we present a method to exploit a general form of this symmetry on probabilistic adder nodes by transforming those probabilistic adder nodes into a probabilistic convolution tree with which dynamic programming computes exact probabilities. A substantial speedup is demonstrated using an illustration example that can arise when identifying splice forms with bottom-up mass spectrometry-based proteomics. On this example, even state-of-the-art exact inference algorithms require a runtime more than exponential in the number of splice forms considered. By using the probabilistic convolution tree, we reduce the runtime to O(k log(k)2) and the space to O(k log(k)) where k is the number of variables joined by an additive or cardinal operator. This approach, which can also be used with junction tree inference, is applicable to graphs with arbitrary dependency on counting variables or cardinalities and can be used on diverse problems and fields like forward error correcting codes, elemental decomposition, and spectral demixing. The approach also trivially generalizes to multiple dimensions.

The Probabilistic Convolution Tree: Efficient Exact Bayesian Inference for Faster LC-MS/MS Protein Inference

PubMed Central

Serang, Oliver

2014-01-01

Exact Bayesian inference can sometimes be performed efficiently for special cases where a function has commutative and associative symmetry of its inputs (called “causal independence”). For this reason, it is desirable to exploit such symmetry on big data sets. Here we present a method to exploit a general form of this symmetry on probabilistic adder nodes by transforming those probabilistic adder nodes into a probabilistic convolution tree with which dynamic programming computes exact probabilities. A substantial speedup is demonstrated using an illustration example that can arise when identifying splice forms with bottom-up mass spectrometry-based proteomics. On this example, even state-of-the-art exact inference algorithms require a runtime more than exponential in the number of splice forms considered. By using the probabilistic convolution tree, we reduce the runtime to and the space to where is the number of variables joined by an additive or cardinal operator. This approach, which can also be used with junction tree inference, is applicable to graphs with arbitrary dependency on counting variables or cardinalities and can be used on diverse problems and fields like forward error correcting codes, elemental decomposition, and spectral demixing. The approach also trivially generalizes to multiple dimensions. PMID:24626234

Deep nets vs expert designed features in medical physics: An IMRT QA case study.

PubMed

Interian, Yannet; Rideout, Vincent; Kearney, Vasant P; Gennatas, Efstathios; Morin, Olivier; Cheung, Joey; Solberg, Timothy; Valdes, Gilmer

2018-03-30

The purpose of this study was to compare the performance of Deep Neural Networks against a technique designed by domain experts in the prediction of gamma passing rates for Intensity Modulated Radiation Therapy Quality Assurance (IMRT QA). A total of 498 IMRT plans across all treatment sites were planned in Eclipse version 11 and delivered using a dynamic sliding window technique on Clinac iX or TrueBeam Linacs. Measurements were performed using a commercial 2D diode array, and passing rates for 3%/3 mm local dose/distance-to-agreement (DTA) were recorded. Separately, fluence maps calculated for each plan were used as inputs to a convolution neural network (CNN). The CNNs were trained to predict IMRT QA gamma passing rates using TensorFlow and Keras. A set of model architectures, inspired by the convolutional blocks of the VGG-16 ImageNet model, were constructed and implemented. Synthetic data, created by rotating and translating the fluence maps during training, was created to boost the performance of the CNNs. Dropout, batch normalization, and data augmentation were utilized to help train the model. The performance of the CNNs was compared to a generalized Poisson regression model, previously developed for this application, which used 78 expert designed features. Deep Neural Networks without domain knowledge achieved comparable performance to a baseline system designed by domain experts in the prediction of 3%/3 mm Local gamma passing rates. An ensemble of neural nets resulted in a mean absolute error (MAE) of 0.70 ± 0.05 and the domain expert model resulted in a 0.74 ± 0.06. Convolutional neural networks (CNNs) with transfer learning can predict IMRT QA passing rates by automatically designing features from the fluence maps without human expert supervision. Predictions from CNNs are comparable to a system carefully designed by physicist experts. © 2018 American Association of Physicists in Medicine.

Deep Learning MR Imaging-based Attenuation Correction for PET/MR Imaging.

PubMed

Liu, Fang; Jang, Hyungseok; Kijowski, Richard; Bradshaw, Tyler; McMillan, Alan B

2018-02-01

Purpose To develop and evaluate the feasibility of deep learning approaches for magnetic resonance (MR) imaging-based attenuation correction (AC) (termed deep MRAC) in brain positron emission tomography (PET)/MR imaging. Materials and Methods A PET/MR imaging AC pipeline was built by using a deep learning approach to generate pseudo computed tomographic (CT) scans from MR images. A deep convolutional auto-encoder network was trained to identify air, bone, and soft tissue in volumetric head MR images coregistered to CT data for training. A set of 30 retrospective three-dimensional T1-weighted head images was used to train the model, which was then evaluated in 10 patients by comparing the generated pseudo CT scan to an acquired CT scan. A prospective study was carried out for utilizing simultaneous PET/MR imaging for five subjects by using the proposed approach. Analysis of covariance and paired-sample t tests were used for statistical analysis to compare PET reconstruction error with deep MRAC and two existing MR imaging-based AC approaches with CT-based AC. Results Deep MRAC provides an accurate pseudo CT scan with a mean Dice coefficient of 0.971 ± 0.005 for air, 0.936 ± 0.011 for soft tissue, and 0.803 ± 0.021 for bone. Furthermore, deep MRAC provides good PET results, with average errors of less than 1% in most brain regions. Significantly lower PET reconstruction errors were realized with deep MRAC (-0.7% ± 1.1) compared with Dixon-based soft-tissue and air segmentation (-5.8% ± 3.1) and anatomic CT-based template registration (-4.8% ± 2.2). Conclusion The authors developed an automated approach that allows generation of discrete-valued pseudo CT scans (soft tissue, bone, and air) from a single high-spatial-resolution diagnostic-quality three-dimensional MR image and evaluated it in brain PET/MR imaging. This deep learning approach for MR imaging-based AC provided reduced PET reconstruction error relative to a CT-based standard within the brain compared with current MR imaging-based AC approaches. © RSNA, 2017 Online supplemental material is available for this article.

Efficiency Improvement in a Busy Radiology Practice: Determination of Musculoskeletal Magnetic Resonance Imaging Protocol Using Deep-Learning Convolutional Neural Networks.

PubMed

Lee, Young Han

2018-04-04

The purposes of this study are to evaluate the feasibility of protocol determination with a convolutional neural networks (CNN) classifier based on short-text classification and to evaluate the agreements by comparing protocols determined by CNN with those determined by musculoskeletal radiologists. Following institutional review board approval, the database of a hospital information system (HIS) was queried for lists of MRI examinations, referring department, patient age, and patient gender. These were exported to a local workstation for analyses: 5258 and 1018 consecutive musculoskeletal MRI examinations were used for the training and test datasets, respectively. The subjects for pre-processing were routine or tumor protocols and the contents were word combinations of the referring department, region, contrast media (or not), gender, and age. The CNN Embedded vector classifier was used with Word2Vec Google news vectors. The test set was tested with each classification model and results were output as routine or tumor protocols. The CNN determinations were evaluated using the receiver operating characteristic (ROC) curves. The accuracies were evaluated by a radiologist-confirmed protocol as the reference protocols. The optimal cut-off values for protocol determination between routine protocols and tumor protocols was 0.5067 with a sensitivity of 92.10%, a specificity of 95.76%, and an area under curve (AUC) of 0.977. The overall accuracy was 94.2% for the ConvNet model. All MRI protocols were correct in the pelvic bone, upper arm, wrist, and lower leg MRIs. Deep-learning-based convolutional neural networks were clinically utilized to determine musculoskeletal MRI protocols. CNN-based text learning and applications could be extended to other radiologic tasks besides image interpretations, improving the work performance of the radiologist.

Classification of breast cancer cytological specimen using convolutional neural network

NASA Astrophysics Data System (ADS)

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.

Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection

NASA Astrophysics Data System (ADS)

Cabrera-Vives, Guillermo; Reyes, Ignacio; Förster, Francisco; Estévez, Pablo A.; Maureira, Juan-Carlos

2017-02-01

We introduce Deep-HiTS, a rotation-invariant convolutional neural network (CNN) model for classifying images of transient candidates into artifacts or real sources for the High cadence Transient Survey (HiTS). CNNs have the advantage of learning the features automatically from the data while achieving high performance. We compare our CNN model against a feature engineering approach using random forests (RFs). We show that our CNN significantly outperforms the RF model, reducing the error by almost half. Furthermore, for a fixed number of approximately 2000 allowed false transient candidates per night, we are able to reduce the misclassified real transients by approximately one-fifth. To the best of our knowledge, this is the first time CNNs have been used to detect astronomical transient events. Our approach will be very useful when processing images from next generation instruments such as the Large Synoptic Survey Telescope. We have made all our code and data available to the community for the sake of allowing further developments and comparisons at https://github.com/guille-c/Deep-HiTS. Deep-HiTS is licensed under the terms of the GNU General Public License v3.0.

Video Super-Resolution via Bidirectional Recurrent Convolutional Networks.

PubMed

Huang, Yan; Wang, Wei; Wang, Liang

2018-04-01

Super resolving a low-resolution video, namely video super-resolution (SR), is usually handled by either single-image SR or multi-frame SR. Single-Image SR deals with each video frame independently, and ignores intrinsic temporal dependency of video frames which actually plays a very important role in video SR. Multi-Frame SR generally extracts motion information, e.g., optical flow, to model the temporal dependency, but often shows high computational cost. Considering that recurrent neural networks (RNNs) can model long-term temporal dependency of video sequences well, we propose a fully convolutional RNN named bidirectional recurrent convolutional network for efficient multi-frame SR. Different from vanilla RNNs, 1) the commonly-used full feedforward and recurrent connections are replaced with weight-sharing convolutional connections. So they can greatly reduce the large number of network parameters and well model the temporal dependency in a finer level, i.e., patch-based rather than frame-based, and 2) connections from input layers at previous timesteps to the current hidden layer are added by 3D feedforward convolutions, which aim to capture discriminate spatio-temporal patterns for short-term fast-varying motions in local adjacent frames. Due to the cheap convolutional operations, our model has a low computational complexity and runs orders of magnitude faster than other multi-frame SR methods. With the powerful temporal dependency modeling, our model can super resolve videos with complex motions and achieve well performance.

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

PubMed

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

2018-07-01

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

Error correction and statistical analyses for intra-host comparisons of feline immunodeficiency virus diversity from high-throughput sequencing data.

PubMed

Liu, Yang; Chiaromonte, Francesca; Ross, Howard; Malhotra, Raunaq; Elleder, Daniel; Poss, Mary

2015-06-30

Infection with feline immunodeficiency virus (FIV) causes an immunosuppressive disease whose consequences are less severe if cats are co-infected with an attenuated FIV strain (PLV). We use virus diversity measurements, which reflect replication ability and the virus response to various conditions, to test whether diversity of virulent FIV in lymphoid tissues is altered in the presence of PLV. Our data consisted of the 3' half of the FIV genome from three tissues of animals infected with FIV alone, or with FIV and PLV, sequenced by 454 technology. Since rare variants dominate virus populations, we had to carefully distinguish sequence variation from errors due to experimental protocols and sequencing. We considered an exponential-normal convolution model used for background correction of microarray data, and modified it to formulate an error correction approach for minor allele frequencies derived from high-throughput sequencing. Similar to accounting for over-dispersion in counts, this accounts for error-inflated variability in frequencies - and quite effectively reproduces empirically observed distributions. After obtaining error-corrected minor allele frequencies, we applied ANalysis Of VAriance (ANOVA) based on a linear mixed model and found that conserved sites and transition frequencies in FIV genes differ among tissues of dual and single infected cats. Furthermore, analysis of minor allele frequencies at individual FIV genome sites revealed 242 sites significantly affected by infection status (dual vs. single) or infection status by tissue interaction. All together, our results demonstrated a decrease in FIV diversity in bone marrow in the presence of PLV. Importantly, these effects were weakened or undetectable when error correction was performed with other approaches (thresholding of minor allele frequencies; probabilistic clustering of reads). We also queried the data for cytidine deaminase activity on the viral genome, which causes an asymmetric increase in G to A substitutions, but found no evidence for this host defense strategy. Our error correction approach for minor allele frequencies (more sensitive and computationally efficient than other algorithms) and our statistical treatment of variation (ANOVA) were critical for effective use of high-throughput sequencing data in understanding viral diversity. We found that co-infection with PLV shifts FIV diversity from bone marrow to lymph node and spleen.

New Syndrome Decoding Techniques for the (n, K) Convolutional Codes

NASA Technical Reports Server (NTRS)

Reed, I. S.; Truong, T. K.

1983-01-01

This paper presents a new syndrome decoding algorithm for the (n,k) convolutional codes (CC) which differs completely from an earlier syndrome decoding algorithm of Schalkwijk and Vinck. The new algorithm is based on the general solution of the syndrome equation, a linear Diophantine equation for the error polynomial vector E(D). The set of Diophantine solutions is a coset of the CC. In this error coset a recursive, Viterbi-like algorithm is developed to find the minimum weight error vector (circumflex)E(D). An example, illustrating the new decoding algorithm, is given for the binary nonsystemmatic (3,1)CC.

Simplified Syndrome Decoding of (n, 1) Convolutional Codes

NASA Technical Reports Server (NTRS)

Reed, I. S.; Truong, T. K.

1983-01-01

A new syndrome decoding algorithm for the (n, 1) convolutional codes (CC) that is different and simpler than the previous syndrome decoding algorithm of Schalkwijk and Vinck is presented. The new algorithm uses the general solution of the polynomial linear Diophantine equation for the error polynomial vector E(D). This set of Diophantine solutions is a coset of the CC space. A recursive or Viterbi-like algorithm is developed to find the minimum weight error vector cirumflex E(D) in this error coset. An example illustrating the new decoding algorithm is given for the binary nonsymmetric (2,1)CC.

DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations.

PubMed

Kruthiventi, Srinivas S S; Ayush, Kumar; Babu, R Venkatesh

2017-09-01

Understanding and predicting the human visual attention mechanism is an active area of research in the fields of neuroscience and computer vision. In this paper, we propose DeepFix, a fully convolutional neural network, which models the bottom-up mechanism of visual attention via saliency prediction. Unlike classical works, which characterize the saliency map using various hand-crafted features, our model automatically learns features in a hierarchical fashion and predicts the saliency map in an end-to-end manner. DeepFix is designed to capture semantics at multiple scales while taking global context into account, by using network layers with very large receptive fields. Generally, fully convolutional nets are spatially invariant-this prevents them from modeling location-dependent patterns (e.g., centre-bias). Our network handles this by incorporating a novel location-biased convolutional layer. We evaluate our model on multiple challenging saliency data sets and show that it achieves the state-of-the-art results.

Image inpainting and super-resolution using non-local recursive deep convolutional network with skip connections

NASA Astrophysics Data System (ADS)

Liu, Miaofeng

2017-07-01

In recent years, deep convolutional neural networks come into use in image inpainting and super-resolution in many fields. Distinct to most of the former methods requiring to know beforehand the local information for corrupted pixels, we propose a 20-depth fully convolutional network to learn an end-to-end mapping a dataset of damaged/ground truth subimage pairs realizing non-local blind inpainting and super-resolution. As there often exist image with huge corruptions or inpainting on a low-resolution image that the existing approaches unable to perform well, we also share parameters in local area of layers to achieve spatial recursion and enlarge the receptive field. To avoid the difficulty of training this deep neural network, skip-connections between symmetric convolutional layers are designed. Experimental results shows that the proposed method outperforms state-of-the-art methods for diverse corrupting and low-resolution conditions, it works excellently when realizing super-resolution and image inpainting simultaneously

Computationally efficient target classification in multispectral image data with Deep Neural Networks

NASA Astrophysics Data System (ADS)

Cavigelli, Lukas; Bernath, Dominic; Magno, Michele; Benini, Luca

2016-10-01

Detecting and classifying targets in video streams from surveillance cameras is a cumbersome, error-prone and expensive task. Often, the incurred costs are prohibitive for real-time monitoring. This leads to data being stored locally or transmitted to a central storage site for post-incident examination. The required communication links and archiving of the video data are still expensive and this setup excludes preemptive actions to respond to imminent threats. An effective way to overcome these limitations is to build a smart camera that analyzes the data on-site, close to the sensor, and transmits alerts when relevant video sequences are detected. Deep neural networks (DNNs) have come to outperform humans in visual classifications tasks and are also performing exceptionally well on other computer vision tasks. The concept of DNNs and Convolutional Networks (ConvNets) can easily be extended to make use of higher-dimensional input data such as multispectral data. We explore this opportunity in terms of achievable accuracy and required computational effort. To analyze the precision of DNNs for scene labeling in an urban surveillance scenario we have created a dataset with 8 classes obtained in a field experiment. We combine an RGB camera with a 25-channel VIS-NIR snapshot sensor to assess the potential of multispectral image data for target classification. We evaluate several new DNNs, showing that the spectral information fused together with the RGB frames can be used to improve the accuracy of the system or to achieve similar accuracy with a 3x smaller computation effort. We achieve a very high per-pixel accuracy of 99.1%. Even for scarcely occurring, but particularly interesting classes, such as cars, 75% of the pixels are labeled correctly with errors occurring only around the border of the objects. This high accuracy was obtained with a training set of only 30 labeled images, paving the way for fast adaptation to various application scenarios.

Coding for reliable satellite communications

NASA Technical Reports Server (NTRS)

Gaarder, N. T.; Lin, S.

1986-01-01

This research project was set up to study various kinds of coding techniques for error control in satellite and space communications for NASA Goddard Space Flight Center. During the project period, researchers investigated the following areas: (1) decoding of Reed-Solomon codes in terms of dual basis; (2) concatenated and cascaded error control coding schemes for satellite and space communications; (3) use of hybrid coding schemes (error correction and detection incorporated with retransmission) to improve system reliability and throughput in satellite communications; (4) good codes for simultaneous error correction and error detection, and (5) error control techniques for ring and star networks.

Benefit of Complete State Monitoring For GPS Realtime Applications With Geo++ Gnsmart

NASA Astrophysics Data System (ADS)

Wübbena, G.; Schmitz, M.; Bagge, A.

Today, the demand for precise positioning at the cm-level in realtime is worldwide growing. An indication for this is the number of operational RTK network installa- tions, which use permanent reference station networks to derive corrections for dis- tance dependent GPS errors and to supply corrections to RTK users in realtime. Gen- erally, the inter-station distances in RTK networks are selected at several tens of km in range and operational installations cover areas of up to 50000 km x km. However, the separation of the permanent reference stations can be increased to sev- eral hundred km, while a correct modeling of all error components is applied. Such networks can be termed as sparse RTK networks, which cover larger areas with a reduced number of stations. The undifferenced GPS observable is best suited for this task estimating the complete state of a permanent GPS network in a dynamic recursive Kalman filter. A rigorous adjustment of all simultaneous reference station data is re- quired. The sparse network design essentially supports the state estimation through its large spatial extension. The benefit of the approach and its state modeling of all GPS error components is a successful ambiguity resolution in realtime over long distances. The above concepts are implemented in the operational GNSMART (GNSS State Monitoring and Representation Technique) software of Geo++. It performs a state monitoring of all error components at the mm-level, because for RTK networks this accuracy is required to sufficiently represent the distance dependent errors for kine- matic applications. One key issue of the modeling is the estimation of clocks and hard- ware delays in the undifferenced approach. This pre-requisite subsequently allows for the precise separation and modeling of all other error components. Generally most of the estimated parameters are considered as nuisance parameters with respect to pure positioning tasks. As the complete state vector of GPS errors is available in a GPS realtime network, additional information besides position can be derived e.g. regional precise satellite clocks, orbits, total ionospheric electron content, tropospheric water vapor distribution, and also dynamic reference station movements. The models of GNSMART are designed to work with regional, continental or even global data. Results from GNSMART realtime networks with inter-station distances of several hundred km are presented to demonstrate the benefits of the operational implemented concepts.

Airplane detection in remote sensing images using convolutional neural networks

NASA Astrophysics Data System (ADS)

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

2018-03-01

Airplane detection in remote sensing images remains a challenging problem and has also been taking a great interest to researchers. In this paper we propose an effective method to detect airplanes in remote sensing images using convolutional neural networks. Deep learning methods show greater advantages than the traditional methods with the rise of deep neural networks in target detection, and we give an explanation why this happens. To improve the performance on detection of airplane, we combine a region proposal algorithm with convolutional neural networks. And in the training phase, we divide the background into multi classes rather than one class, which can reduce false alarms. Our experimental results show that the proposed method is effective and robust in detecting airplane.

Subthreshold muscle twitches dissociate oscillatory neural signatures of conflicts from errors.

PubMed

Cohen, Michael X; van Gaal, Simon

2014-02-01

We investigated the neural systems underlying conflict detection and error monitoring during rapid online error correction/monitoring mechanisms. We combined data from four separate cognitive tasks and 64 subjects in which EEG and EMG (muscle activity from the thumb used to respond) were recorded. In typical neuroscience experiments, behavioral responses are classified as "error" or "correct"; however, closer inspection of our data revealed that correct responses were often accompanied by "partial errors" - a muscle twitch of the incorrect hand ("mixed correct trials," ~13% of the trials). We found that these muscle twitches dissociated conflicts from errors in time-frequency domain analyses of EEG data. In particular, both mixed-correct trials and full error trials were associated with enhanced theta-band power (4-9Hz) compared to correct trials. However, full errors were additionally associated with power and frontal-parietal synchrony in the delta band. Single-trial robust multiple regression analyses revealed a significant modulation of theta power as a function of partial error correction time, thus linking trial-to-trial fluctuations in power to conflict. Furthermore, single-trial correlation analyses revealed a qualitative dissociation between conflict and error processing, such that mixed correct trials were associated with positive theta-RT correlations whereas full error trials were associated with negative delta-RT correlations. These findings shed new light on the local and global network mechanisms of conflict monitoring and error detection, and their relationship to online action adjustment. © 2013.

DSN telemetry system performance with convolutionally coded data using operational maximum-likelihood convolutional decoders

NASA Technical Reports Server (NTRS)

Benjauthrit, B.; Mulhall, B.; Madsen, B. D.; Alberda, M. E.

1976-01-01

The DSN telemetry system performance with convolutionally coded data using the operational maximum-likelihood convolutional decoder (MCD) being implemented in the Network is described. Data rates from 80 bps to 115.2 kbps and both S- and X-band receivers are reported. The results of both one- and two-way radio losses are included.

Maximum likelihood convolutional decoding (MCD) performance due to system losses

NASA Technical Reports Server (NTRS)

Webster, L.

1976-01-01

A model for predicting the computational performance of a maximum likelihood convolutional decoder (MCD) operating in a noisy carrier reference environment is described. This model is used to develop a subroutine that will be utilized by the Telemetry Analysis Program to compute the MCD bit error rate. When this computational model is averaged over noisy reference phase errors using a high-rate interpolation scheme, the results are found to agree quite favorably with experimental measurements.

New syndrome decoder for (n, 1) convolutional codes

NASA Technical Reports Server (NTRS)

Reed, I. S.; Truong, T. K.

1983-01-01

The letter presents a new syndrome decoding algorithm for the (n, 1) convolutional codes (CC) that is different and simpler than the previous syndrome decoding algorithm of Schalkwijk and Vinck. The new technique uses the general solution of the polynomial linear Diophantine equation for the error polynomial vector E(D). A recursive, Viterbi-like, algorithm is developed to find the minimum weight error vector E(D). An example is given for the binary nonsystematic (2, 1) CC.

Automatic quality assessment of apical four-chamber echocardiograms using deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Abdi, Amir H.; Luong, Christina; Tsang, Teresa; Allan, Gregory; Nouranian, Saman; Jue, John; Hawley, Dale; Fleming, Sarah; Gin, Ken; Swift, Jody; Rohling, Robert; Abolmaesumi, Purang

2017-02-01

Echocardiography (echo) is the most common test for diagnosis and management of patients with cardiac condi- tions. While most medical imaging modalities benefit from a relatively automated procedure, this is not the case for echo and the quality of the final echo view depends on the competency and experience of the sonographer. It is not uncommon that the sonographer does not have adequate experience to adjust the transducer and acquire a high quality echo, which may further affect the clinical diagnosis. In this work, we aim to aid the operator during image acquisition by automatically assessing the quality of the echo and generating the Automatic Echo Score (AES). This quality assessment method is based on a deep convolutional neural network, trained in an end-to-end fashion on a large dataset of apical four-chamber (A4C) echo images. For this project, an expert car- diologist went through 2,904 A4C images obtained from independent studies and assessed their condition based on a 6-scale grading system. The scores assigned by the expert ranged from 0 to 5. The distribution of scores among the 6 levels were almost uniform. The network was then trained on 80% of the data (2,345 samples). The average absolute error of the trained model in calculating the AES was 0.8 +/- 0:72. The computation time of the GPU implementation of the neural network was estimated at 5 ms per frame, which is sufficient for real-time deployment.

Forecasting short-term data center network traffic load with convolutional neural networks.

PubMed

Mozo, Alberto; Ordozgoiti, Bruno; Gómez-Canaval, Sandra

2018-01-01

Efficient resource management in data centers is of central importance to content service providers as 90 percent of the network traffic is expected to go through them in the coming years. In this context we propose the use of convolutional neural networks (CNNs) to forecast short-term changes in the amount of traffic crossing a data center network. This value is an indicator of virtual machine activity and can be utilized to shape the data center infrastructure accordingly. The behaviour of network traffic at the seconds scale is highly chaotic and therefore traditional time-series-analysis approaches such as ARIMA fail to obtain accurate forecasts. We show that our convolutional neural network approach can exploit the non-linear regularities of network traffic, providing significant improvements with respect to the mean absolute and standard deviation of the data, and outperforming ARIMA by an increasingly significant margin as the forecasting granularity is above the 16-second resolution. In order to increase the accuracy of the forecasting model, we exploit the architecture of the CNNs using multiresolution input distributed among separate channels of the first convolutional layer. We validate our approach with an extensive set of experiments using a data set collected at the core network of an Internet Service Provider over a period of 5 months, totalling 70 days of traffic at the one-second resolution.

Forecasting short-term data center network traffic load with convolutional neural networks

PubMed Central

Ordozgoiti, Bruno; Gómez-Canaval, Sandra

2018-01-01

Efficient resource management in data centers is of central importance to content service providers as 90 percent of the network traffic is expected to go through them in the coming years. In this context we propose the use of convolutional neural networks (CNNs) to forecast short-term changes in the amount of traffic crossing a data center network. This value is an indicator of virtual machine activity and can be utilized to shape the data center infrastructure accordingly. The behaviour of network traffic at the seconds scale is highly chaotic and therefore traditional time-series-analysis approaches such as ARIMA fail to obtain accurate forecasts. We show that our convolutional neural network approach can exploit the non-linear regularities of network traffic, providing significant improvements with respect to the mean absolute and standard deviation of the data, and outperforming ARIMA by an increasingly significant margin as the forecasting granularity is above the 16-second resolution. In order to increase the accuracy of the forecasting model, we exploit the architecture of the CNNs using multiresolution input distributed among separate channels of the first convolutional layer. We validate our approach with an extensive set of experiments using a data set collected at the core network of an Internet Service Provider over a period of 5 months, totalling 70 days of traffic at the one-second resolution. PMID:29408936

Automated segmentation of geographic atrophy using deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Hu, Zhihong; Wang, Ziyuan; Sadda, SriniVas R.

2018-02-01

Geographic atrophy (GA) is an end-stage manifestation of the advanced age-related macular degeneration (AMD), the leading cause of blindness and visual impairment in developed nations. Techniques to rapidly and precisely detect and quantify GA would appear to be of critical importance in advancing the understanding of its pathogenesis. In this study, we develop an automated supervised classification system using deep convolutional neural networks (CNNs) for segmenting GA in fundus autofluorescene (FAF) images. More specifically, to enhance the contrast of GA relative to the background, we apply the contrast limited adaptive histogram equalization. Blood vessels may cause GA segmentation errors due to similar intensity level to GA. A tensor-voting technique is performed to identify the blood vessels and a vessel inpainting technique is applied to suppress the GA segmentation errors due to the blood vessels. To handle the large variation of GA lesion sizes, three deep CNNs with three varying sized input image patches are applied. Fifty randomly chosen FAF images are obtained from fifty subjects with GA. The algorithm-defined GA regions are compared with manual delineation by a certified grader. A two-fold cross-validation is applied to evaluate the algorithm performance. The mean segmentation accuracy, true positive rate (i.e. sensitivity), true negative rate (i.e. specificity), positive predictive value, false discovery rate, and overlap ratio, between the algorithm- and manually-defined GA regions are 0.97 +/- 0.02, 0.89 +/- 0.08, 0.98 +/- 0.02, 0.87 +/- 0.12, 0.13 +/- 0.12, and 0.79 +/- 0.12 respectively, demonstrating a high level of agreement.

Acral melanoma detection using a convolutional neural network for dermoscopy images.

PubMed

Yu, Chanki; Yang, Sejung; Kim, Wonoh; Jung, Jinwoong; Chung, Kee-Yang; Lee, Sang Wook; Oh, Byungho

2018-01-01

Acral melanoma is the most common type of melanoma in Asians, and usually results in a poor prognosis due to late diagnosis. We applied a convolutional neural network to dermoscopy images of acral melanoma and benign nevi on the hands and feet and evaluated its usefulness for the early diagnosis of these conditions. A total of 724 dermoscopy images comprising acral melanoma (350 images from 81 patients) and benign nevi (374 images from 194 patients), and confirmed by histopathological examination, were analyzed in this study. To perform the 2-fold cross validation, we split them into two mutually exclusive subsets: half of the total image dataset was selected for training and the rest for testing, and we calculated the accuracy of diagnosis comparing it with the dermatologist's and non-expert's evaluation. The accuracy (percentage of true positive and true negative from all images) of the convolutional neural network was 83.51% and 80.23%, which was higher than the non-expert's evaluation (67.84%, 62.71%) and close to that of the expert (81.08%, 81.64%). Moreover, the convolutional neural network showed area-under-the-curve values like 0.8, 0.84 and Youden's index like 0.6795, 0.6073, which were similar score with the expert. Although further data analysis is necessary to improve their accuracy, convolutional neural networks would be helpful to detect acral melanoma from dermoscopy images of the hands and feet.

Deep neural network using color and synthesized three-dimensional shape for face recognition

NASA Astrophysics Data System (ADS)

Rhee, Seon-Min; Yoo, ByungIn; Han, Jae-Joon; Hwang, Wonjun

2017-03-01

We present an approach for face recognition using synthesized three-dimensional (3-D) shape information together with two-dimensional (2-D) color in a deep convolutional neural network (DCNN). As 3-D facial shape is hardly affected by the extrinsic 2-D texture changes caused by illumination, make-up, and occlusions, it could provide more reliable complementary features in harmony with the 2-D color feature in face recognition. Unlike other approaches that use 3-D shape information with the help of an additional depth sensor, our approach generates a personalized 3-D face model by using only face landmarks in the 2-D input image. Using the personalized 3-D face model, we generate a frontalized 2-D color facial image as well as 3-D facial images (e.g., a depth image and a normal image). In our DCNN, we first feed 2-D and 3-D facial images into independent convolutional layers, where the low-level kernels are successfully learned according to their own characteristics. Then, we merge them and feed into higher-level layers under a single deep neural network. Our proposed approach is evaluated with labeled faces in the wild dataset and the results show that the error rate of the verification rate at false acceptance rate 1% is improved by up to 32.1% compared with the baseline where only a 2-D color image is used.

Integrating Online and Offline Three-Dimensional Deep Learning for Automated Polyp Detection in Colonoscopy Videos.

PubMed

Lequan Yu; Hao Chen; Qi Dou; Jing Qin; Pheng Ann Heng

2017-01-01

Automated polyp detection in colonoscopy videos has been demonstrated to be a promising way for colorectal cancer prevention and diagnosis. Traditional manual screening is time consuming, operator dependent, and error prone; hence, automated detection approach is highly demanded in clinical practice. However, automated polyp detection is very challenging due to high intraclass variations in polyp size, color, shape, and texture, and low interclass variations between polyps and hard mimics. In this paper, we propose a novel offline and online three-dimensional (3-D) deep learning integration framework by leveraging the 3-D fully convolutional network (3D-FCN) to tackle this challenging problem. Compared with the previous methods employing hand-crafted features or 2-D convolutional neural network, the 3D-FCN is capable of learning more representative spatio-temporal features from colonoscopy videos, and hence has more powerful discrimination capability. More importantly, we propose a novel online learning scheme to deal with the problem of limited training data by harnessing the specific information of an input video in the learning process. We integrate offline and online learning to effectively reduce the number of false positives generated by the offline network and further improve the detection performance. Extensive experiments on the dataset of MICCAI 2015 Challenge on Polyp Detection demonstrated the better performance of our method when compared with other competitors.

Detection of prostate cancer on multiparametric MRI

NASA Astrophysics Data System (ADS)

Seah, Jarrel C. Y.; Tang, Jennifer S. N.; Kitchen, Andy

2017-03-01

In this manuscript, we describe our approach and methods to the ProstateX challenge, which achieved an overall AUC of 0.84 and the runner-up position. We train a deep convolutional neural network to classify lesions marked on multiparametric MRI of the prostate as clinically significant or not. We implement a novel addition to the standard convolutional architecture described as auto-windowing which is clinically inspired and designed to overcome some of the difficulties faced in MRI interpretation, where high dynamic ranges and low contrast edges may cause difficulty for traditional convolutional neural networks trained on high contrast natural imagery. We demonstrate that this system can be trained end to end and outperforms a similar architecture without such additions. Although a relatively small training set was provided, we use extensive data augmentation to prevent overfitting and transfer learning to improve convergence speed, showing that deep convolutional neural networks can be feasibly trained on small datasets.

Recognition of Damaged Arrow-Road Markings by Visible Light Camera Sensor Based on Convolutional Neural Network.

PubMed

Vokhidov, Husan; Hong, Hyung Gil; Kang, Jin Kyu; Hoang, Toan Minh; Park, Kang Ryoung

2016-12-16

Automobile driver information as displayed on marked road signs indicates the state of the road, traffic conditions, proximity to schools, etc. These signs are important to insure the safety of the driver and pedestrians. They are also important input to the automated advanced driver assistance system (ADAS), installed in many automobiles. Over time, the arrow-road markings may be eroded or otherwise damaged by automobile contact, making it difficult for the driver to correctly identify the marking. Failure to properly identify an arrow-road marker creates a dangerous situation that may result in traffic accidents or pedestrian injury. Very little research exists that studies the problem of automated identification of damaged arrow-road marking painted on the road. In this study, we propose a method that uses a convolutional neural network (CNN) to recognize six types of arrow-road markings, possibly damaged, by visible light camera sensor. Experimental results with six databases of Road marking dataset, KITTI dataset, Málaga dataset 2009, Málaga urban dataset, Naver street view dataset, and Road/Lane detection evaluation 2013 dataset, show that our method outperforms conventional methods.

Recognition of Damaged Arrow-Road Markings by Visible Light Camera Sensor Based on Convolutional Neural Network

PubMed Central

Vokhidov, Husan; Hong, Hyung Gil; Kang, Jin Kyu; Hoang, Toan Minh; Park, Kang Ryoung

2016-01-01

Automobile driver information as displayed on marked road signs indicates the state of the road, traffic conditions, proximity to schools, etc. These signs are important to insure the safety of the driver and pedestrians. They are also important input to the automated advanced driver assistance system (ADAS), installed in many automobiles. Over time, the arrow-road markings may be eroded or otherwise damaged by automobile contact, making it difficult for the driver to correctly identify the marking. Failure to properly identify an arrow-road marker creates a dangerous situation that may result in traffic accidents or pedestrian injury. Very little research exists that studies the problem of automated identification of damaged arrow-road marking painted on the road. In this study, we propose a method that uses a convolutional neural network (CNN) to recognize six types of arrow-road markings, possibly damaged, by visible light camera sensor. Experimental results with six databases of Road marking dataset, KITTI dataset, Málaga dataset 2009, Málaga urban dataset, Naver street view dataset, and Road/Lane detection evaluation 2013 dataset, show that our method outperforms conventional methods. PMID:27999301

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

PubMed

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

2017-12-01

Multi-parameter magnetic resonance imaging (mp-MRI) is increasingly popular for prostate cancer (PCa) detection and diagnosis. However, interpreting mp-MRI data which typically contains multiple unregistered 3D sequences, e.g. apparent diffusion coefficient (ADC) and T2-weighted (T2w) images, is time-consuming and demands special expertise, limiting its usage for large-scale PCa screening. Therefore, solutions to computer-aided detection of PCa in mp-MRI images are highly desirable. Most recent advances in automated methods for PCa detection employ a handcrafted feature based two-stage classification flow, i.e. voxel-level classification followed by a region-level classification. This work presents an automated PCa detection system which can concurrently identify the presence of PCa in an image and localize lesions based on deep convolutional neural network (CNN) features and a single-stage SVM classifier. Specifically, the developed co-trained CNNs consist of two parallel convolutional networks for ADC and T2w images respectively. Each network is trained using images of a single modality in a weakly-supervised manner by providing a set of prostate images with image-level labels indicating only the presence of PCa without priors of lesions' locations. Discriminative visual patterns of lesions can be learned effectively from clutters of prostate and surrounding tissues. A cancer response map with each pixel indicating the likelihood to be cancerous is explicitly generated at the last convolutional layer of the network for each modality. A new back-propagated error E is defined to enforce both optimized classification results and consistent cancer response maps for different modalities, which help capture highly representative PCa-relevant features during the CNN feature learning process. The CNN features of each modality are concatenated and fed into a SVM classifier. For images which are classified to contain cancers, non-maximum suppression and adaptive thresholding are applied to the corresponding cancer response maps for PCa foci localization. Evaluation based on 160 patient data with 12-core systematic TRUS-guided prostate biopsy as the reference standard demonstrates that our system achieves a sensitivity of 0.46, 0.92 and 0.97 at 0.1, 1 and 10 false positives per normal/benign patient which is significantly superior to two state-of-the-art CNN-based methods (Oquab et al., 2015; Zhou et al., 2015) and 6-core systematic prostate biopsies. Copyright © 2017 Elsevier B.V. All rights reserved.

Protograph-Based Raptor-Like Codes

NASA Technical Reports Server (NTRS)

Divsalar, Dariush; Chen, Tsung-Yi; Wang, Jiadong; Wesel, Richard D.

2014-01-01

Theoretical analysis has long indicated that feedback improves the error exponent but not the capacity of pointto- point memoryless channels. The analytic and empirical results indicate that at short blocklength regime, practical rate-compatible punctured convolutional (RCPC) codes achieve low latency with the use of noiseless feedback. In 3GPP, standard rate-compatible turbo codes (RCPT) did not outperform the convolutional codes in the short blocklength regime. The reason is the convolutional codes for low number of states can be decoded optimally using Viterbi decoder. Despite excellent performance of convolutional codes at very short blocklengths, the strength of convolutional codes does not scale with the blocklength for a fixed number of states in its trellis.

Face recognition via Gabor and convolutional neural network

NASA Astrophysics Data System (ADS)

Lu, Tongwei; Wu, Menglu; Lu, Tao

2018-04-01

In recent years, the powerful feature learning and classification ability of convolutional neural network have attracted widely attention. Compared with the deep learning, the traditional machine learning algorithm has a good explanatory which deep learning does not have. Thus, In this paper, we propose a method to extract the feature of the traditional algorithm as the input of convolution neural network. In order to reduce the complexity of the network, the kernel function of Gabor wavelet is used to extract the feature from different position, frequency and direction of target image. It is sensitive to edge of image which can provide good direction and scale selection. The extraction of the image from eight directions on a scale are as the input of network that we proposed. The network have the advantage of weight sharing and local connection and texture feature of the input image can reduce the influence of facial expression, gesture and illumination. At the same time, we introduced a layer which combined the results of the pooling and convolution can extract deeper features. The training network used the open source caffe framework which is beneficial to feature extraction. The experiment results of the proposed method proved that the network structure effectively overcame the barrier of illumination and had a good robustness as well as more accurate and rapid than the traditional algorithm.

The analysis of convolutional codes via the extended Smith algorithm

NASA Technical Reports Server (NTRS)

Mceliece, R. J.; Onyszchuk, I.

1993-01-01

Convolutional codes have been the central part of most error-control systems in deep-space communication for many years. Almost all such applications, however, have used the restricted class of (n,1), also known as 'rate 1/n,' convolutional codes. The more general class of (n,k) convolutional codes contains many potentially useful codes, but their algebraic theory is difficult and has proved to be a stumbling block in the evolution of convolutional coding systems. In this article, the situation is improved by describing a set of practical algorithms for computing certain basic things about a convolutional code (among them the degree, the Forney indices, a minimal generator matrix, and a parity-check matrix), which are usually needed before a system using the code can be built. The approach is based on the classic Forney theory for convolutional codes, together with the extended Smith algorithm for polynomial matrices, which is introduced in this article.

DCMDN: Deep Convolutional Mixture Density Network

NASA Astrophysics Data System (ADS)

D'Isanto, Antonio; Polsterer, Kai Lars

2017-09-01

Deep Convolutional Mixture Density Network (DCMDN) estimates probabilistic photometric redshift directly from multi-band imaging data by combining a version of a deep convolutional network with a mixture density network. The estimates are expressed as Gaussian mixture models representing the probability density functions (PDFs) in the redshift space. In addition to the traditional scores, the continuous ranked probability score (CRPS) and the probability integral transform (PIT) are applied as performance criteria. DCMDN is able to predict redshift PDFs independently from the type of source, e.g. galaxies, quasars or stars and renders pre-classification of objects and feature extraction unnecessary; the method is extremely general and allows the solving of any kind of probabilistic regression problems based on imaging data, such as estimating metallicity or star formation rate in galaxies.

New syndrome decoding techniques for the (n, k) convolutional codes

NASA Technical Reports Server (NTRS)

Reed, I. S.; Truong, T. K.

1984-01-01

This paper presents a new syndrome decoding algorithm for the (n, k) convolutional codes (CC) which differs completely from an earlier syndrome decoding algorithm of Schalkwijk and Vinck. The new algorithm is based on the general solution of the syndrome equation, a linear Diophantine equation for the error polynomial vector E(D). The set of Diophantine solutions is a coset of the CC. In this error coset a recursive, Viterbi-like algorithm is developed to find the minimum weight error vector (circumflex)E(D). An example, illustrating the new decoding algorithm, is given for the binary nonsystemmatic (3, 1)CC. Previously announced in STAR as N83-34964

Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods.

PubMed

Arcos-García, Álvaro; Álvarez-García, Juan A; Soria-Morillo, Luis M

2018-03-01

This paper presents a Deep Learning approach for traffic sign recognition systems. Several classification experiments are conducted over publicly available traffic sign datasets from Germany and Belgium using a Deep Neural Network which comprises Convolutional layers and Spatial Transformer Networks. Such trials are built to measure the impact of diverse factors with the end goal of designing a Convolutional Neural Network that can improve the state-of-the-art of traffic sign classification task. First, different adaptive and non-adaptive stochastic gradient descent optimisation algorithms such as SGD, SGD-Nesterov, RMSprop and Adam are evaluated. Subsequently, multiple combinations of Spatial Transformer Networks placed at distinct positions within the main neural network are analysed. The recognition rate of the proposed Convolutional Neural Network reports an accuracy of 99.71% in the German Traffic Sign Recognition Benchmark, outperforming previous state-of-the-art methods and also being more efficient in terms of memory requirements. Copyright © 2018 Elsevier Ltd. All rights reserved.

Seismic signal auto-detecing from different features by using Convolutional Neural Network

NASA Astrophysics Data System (ADS)

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.

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

NASA Astrophysics Data System (ADS)

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.; Castillo Fernandez, R.; Cavanna, F.; Chen, H.; Church, E.; Cianci, D.; Collin, G. H.; Conrad, J. M.; Convery, M.; Crespo-Anadón, J. I.; Del Tutto, M.; Devitt, D.; Dytman, S.; Eberly, B.; Ereditato, A.; Escudero Sanchez, L.; 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.; Martinez Caicedo, D. A.; 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.; Söldner-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.

Toward Joint Hypothesis-Tests Seismic Event Screening Analysis: Ms|mb and Event Depth

DOE Office of Scientific and Technical Information (OSTI.GOV)

Anderson, Dale; Selby, Neil

2012-08-14

Well established theory can be used to combine single-phenomenology hypothesis tests into a multi-phenomenology event screening hypothesis test (Fisher's and Tippett's tests). Commonly used standard error in Ms:mb event screening hypothesis test is not fully consistent with physical basis. Improved standard error - Better agreement with physical basis, and correctly partitions error to include Model Error as a component of variance, correctly reduces station noise variance through network averaging. For 2009 DPRK test - Commonly used standard error 'rejects' H0 even with better scaling slope ({beta} = 1, Selby et al.), improved standard error 'fails to rejects' H0.

Defect detection and classification of galvanized stamping parts based on fully convolution neural network

NASA Astrophysics Data System (ADS)

Xiao, Zhitao; Leng, Yanyi; Geng, Lei; Xi, Jiangtao

2018-04-01

In this paper, a new convolution neural network method is proposed for the inspection and classification of galvanized stamping parts. Firstly, all workpieces are divided into normal and defective by image processing, and then the defective workpieces extracted from the region of interest (ROI) area are input to the trained fully convolutional networks (FCN). The network utilizes an end-to-end and pixel-to-pixel training convolution network that is currently the most advanced technology in semantic segmentation, predicts result of each pixel. Secondly, we mark the different pixel values of the workpiece, defect and background for the training image, and use the pixel value and the number of pixels to realize the recognition of the defects of the output picture. Finally, the defect area's threshold depended on the needs of the project is set to achieve the specific classification of the workpiece. The experiment results show that the proposed method can successfully achieve defect detection and classification of galvanized stamping parts under ordinary camera and illumination conditions, and its accuracy can reach 99.6%. Moreover, it overcomes the problem of complex image preprocessing and difficult feature extraction and performs better adaptability.

Lunar Circular Structure Classification from Chang 'e 2 High Resolution Lunar Images with Convolutional Neural Network

NASA Astrophysics Data System (ADS)

Zeng, X. G.; Liu, J. J.; Zuo, W.; Chen, W. L.; Liu, Y. X.

2018-04-01

Circular structures are widely distributed around the lunar surface. The most typical of them could be lunar impact crater, lunar dome, et.al. In this approach, we are trying to use the Convolutional Neural Network to classify the lunar circular structures from the lunar images.

Enhancement of digital radiography image quality using a convolutional neural network.

PubMed

Sun, Yuewen; Li, Litao; Cong, Peng; Wang, Zhentao; Guo, Xiaojing

2017-01-01

Digital radiography system is widely used for noninvasive security check and medical imaging examination. However, the system has a limitation of lower image quality in spatial resolution and signal to noise ratio. In this study, we explored whether the image quality acquired by the digital radiography system can be improved with a modified convolutional neural network to generate high-resolution images with reduced noise from the original low-quality images. The experiment evaluated on a test dataset, which contains 5 X-ray images, showed that the proposed method outperformed the traditional methods (i.e., bicubic interpolation and 3D block-matching approach) as measured by peak signal to noise ratio (PSNR) about 1.3 dB while kept highly efficient processing time within one second. Experimental results demonstrated that a residual to residual (RTR) convolutional neural network remarkably improved the image quality of object structural details by increasing the image resolution and reducing image noise. Thus, this study indicated that applying this RTR convolutional neural network system was useful to improve image quality acquired by the digital radiography system.

Evolutionary image simplification for lung nodule classification with convolutional neural networks.

PubMed

Lückehe, Daniel; von Voigt, Gabriele

2018-05-29

Understanding decisions of deep learning techniques is important. Especially in the medical field, the reasons for a decision in a classification task are as crucial as the pure classification results. In this article, we propose a new approach to compute relevant parts of a medical image. Knowing the relevant parts makes it easier to understand decisions. In our approach, a convolutional neural network is employed to learn structures of images of lung nodules. Then, an evolutionary algorithm is applied to compute a simplified version of an unknown image based on the learned structures by the convolutional neural network. In the simplified version, irrelevant parts are removed from the original image. In the results, we show simplified images which allow the observer to focus on the relevant parts. In these images, more than 50% of the pixels are simplified. The simplified pixels do not change the meaning of the images based on the learned structures by the convolutional neural network. An experimental analysis shows the potential of the approach. Besides the examples of simplified images, we analyze the run time development. Simplified images make it easier to focus on relevant parts and to find reasons for a decision. The combination of an evolutionary algorithm employing a learned convolutional neural network is well suited for the simplification task. From a research perspective, it is interesting which areas of the images are simplified and which parts are taken as relevant.

Further Developments in the Communication Link and Error Analysis (CLEAN) Simulator

NASA Technical Reports Server (NTRS)

Ebel, William J.; Ingels, Frank M.

1995-01-01

During the period 1 July 1993 - 30 June 1994, significant developments to the Communication Link and Error ANalysis (CLEAN) simulator were completed. Many of these were reported in the Semi-Annual report dated December 1993 which has been included in this report in Appendix A. Since December 1993, a number of additional modules have been added involving Unit-Memory Convolutional codes (UMC). These are: (1) Unit-Memory Convolutional Encoder module (UMCEncd); (2) Hard decision Unit-Memory Convolutional Decoder using the Viterbi decoding algorithm (VitUMC); and (3) a number of utility modules designed to investigate the performance of LTMC's such as LTMC column distance function (UMCdc), UMC free distance function (UMCdfree), UMC row distance function (UMCdr), and UMC Transformation (UMCTrans). The study of UMC's was driven, in part, by the desire to investigate high-rate convolutional codes which are better suited as inner codes for a concatenated coding scheme. A number of high-rate LTMC's were found which are good candidates for inner codes. Besides the further developments of the simulation, a study was performed to construct a table of the best known Unit-Memory Convolutional codes. Finally, a preliminary study of the usefulness of the Periodic Convolutional Interleaver (PCI) was completed and documented in a Technical note dated March 17, 1994. This technical note has also been included in this final report.

A Geophysical Inversion Model Enhancement Technique Based on the Blind Deconvolution

NASA Astrophysics Data System (ADS)

Zuo, B.; Hu, X.; Li, H.

2011-12-01

A model-enhancement technique is proposed to enhance the geophysical inversion model edges and details without introducing any additional information. Firstly, the theoretic correctness of the proposed geophysical inversion model-enhancement technique is discussed. An inversion MRM (model resolution matrix) convolution approximating PSF (Point Spread Function) method is designed to demonstrate the correctness of the deconvolution model enhancement method. Then, a total-variation regularization blind deconvolution geophysical inversion model-enhancement algorithm is proposed. In previous research, Oldenburg et al. demonstrate the connection between the PSF and the geophysical inverse solution. Alumbaugh et al. propose that more information could be provided by the PSF if we return to the idea of it behaving as an averaging or low pass filter. We consider the PSF as a low pass filter to enhance the inversion model basis on the theory of the PSF convolution approximation. Both the 1D linear and the 2D magnetotelluric inversion examples are used to analyze the validity of the theory and the algorithm. To prove the proposed PSF convolution approximation theory, the 1D linear inversion problem is considered. It shows the ratio of convolution approximation error is only 0.15%. The 2D synthetic model enhancement experiment is presented. After the deconvolution enhancement, the edges of the conductive prism and the resistive host become sharper, and the enhancement result is closer to the actual model than the original inversion model according the numerical statistic analysis. Moreover, the artifacts in the inversion model are suppressed. The overall precision of model increases 75%. All of the experiments show that the structure details and the numerical precision of inversion model are significantly improved, especially in the anomalous region. The correlation coefficient between the enhanced inversion model and the actual model are shown in Fig. 1. The figure illustrates that more information and details structure of the actual model are enhanced through the proposed enhancement algorithm. Using the proposed enhancement method can help us gain a clearer insight into the results of the inversions and help make better informed decisions.

Improved scatter correction using adaptive scatter kernel superposition

NASA Astrophysics Data System (ADS)

Sun, M.; Star-Lack, J. M.

2010-11-01

Accurate scatter correction is required to produce high-quality reconstructions of x-ray cone-beam computed tomography (CBCT) scans. This paper describes new scatter kernel superposition (SKS) algorithms for deconvolving scatter from projection data. The algorithms are designed to improve upon the conventional approach whose accuracy is limited by the use of symmetric kernels that characterize the scatter properties of uniform slabs. To model scatter transport in more realistic objects, nonstationary kernels, whose shapes adapt to local thickness variations in the projection data, are proposed. Two methods are introduced: (1) adaptive scatter kernel superposition (ASKS) requiring spatial domain convolutions and (2) fast adaptive scatter kernel superposition (fASKS) where, through a linearity approximation, convolution is efficiently performed in Fourier space. The conventional SKS algorithm, ASKS, and fASKS, were tested with Monte Carlo simulations and with phantom data acquired on a table-top CBCT system matching the Varian On-Board Imager (OBI). All three models accounted for scatter point-spread broadening due to object thickening, object edge effects, detector scatter properties and an anti-scatter grid. Hounsfield unit (HU) errors in reconstructions of a large pelvis phantom with a measured maximum scatter-to-primary ratio over 200% were reduced from -90 ± 58 HU (mean ± standard deviation) with no scatter correction to 53 ± 82 HU with SKS, to 19 ± 25 HU with fASKS and to 13 ± 21 HU with ASKS. HU accuracies and measured contrast were similarly improved in reconstructions of a body-sized elliptical Catphan phantom. The results show that the adaptive SKS methods offer significant advantages over the conventional scatter deconvolution technique.

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

NASA Astrophysics Data System (ADS)

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.

Simulations in site error estimation for direction finders

NASA Astrophysics Data System (ADS)

López, Raúl E.; Passi, Ranjit M.

1991-08-01

The performance of an algorithm for the recovery of site-specific errors of direction finder (DF) networks is tested under controlled simulated conditions. The simulations show that the algorithm has some inherent shortcomings for the recovery of site errors from the measured azimuth data. These limitations are fundamental to the problem of site error estimation using azimuth information. Several ways for resolving or ameliorating these basic complications are tested by means of simulations. From these it appears that for the effective implementation of the site error determination algorithm, one should design the networks with at least four DFs, improve the alignment of the antennas, and increase the gain of the DFs as much as it is compatible with other operational requirements. The use of a nonzero initial estimate of the site errors when working with data from networks of four or more DFs also improves the accuracy of the site error recovery. Even for networks of three DFs, reasonable site error corrections could be obtained if the antennas could be well aligned.

Pulmonary Nodule Classification with Deep Convolutional Neural Networks on Computed Tomography Images.

PubMed

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.

Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network.

PubMed

Kang, Eunhee; Chang, Won; Yoo, Jaejun; Ye, Jong Chul

2018-06-01

Model-based iterative reconstruction algorithms for low-dose X-ray computed tomography (CT) are computationally expensive. To address this problem, we recently proposed a deep convolutional neural network (CNN) for low-dose X-ray CT and won the second place in 2016 AAPM Low-Dose CT Grand Challenge. However, some of the textures were not fully recovered. To address this problem, here we propose a novel framelet-based denoising algorithm using wavelet residual network which synergistically combines the expressive power of deep learning and the performance guarantee from the framelet-based denoising algorithms. The new algorithms were inspired by the recent interpretation of the deep CNN as a cascaded convolution framelet signal representation. Extensive experimental results confirm that the proposed networks have significantly improved performance and preserve the detail texture of the original images.

Thermalnet: a Deep Convolutional Network for Synthetic Thermal Image Generation

NASA Astrophysics Data System (ADS)

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.

Design of Intelligent Cross-Layer Routing Protocols for Airborne Wireless Networks Under Dynamic Spectrum Access Paradigm

DTIC Science & Technology

2011-05-01

rate convolutional codes or the prioritized Rate - Compatible Punctured ...Quality of service RCPC Rate - compatible and punctured convolutional codes SNR Signal to noise ratio SSIM... Convolutional (RCPC) codes . The RCPC codes achieve UEP by puncturing off different amounts of coded bits of the parent code . The

Fully automatic cervical vertebrae segmentation framework for X-ray images.

PubMed

Al Arif, S M Masudur Rahman; Knapp, Karen; Slabaugh, Greg

2018-04-01

The cervical spine is a highly flexible anatomy and therefore vulnerable to injuries. Unfortunately, a large number of injuries in lateral cervical X-ray images remain undiagnosed due to human errors. Computer-aided injury detection has the potential to reduce the risk of misdiagnosis. Towards building an automatic injury detection system, in this paper, we propose a deep learning-based fully automatic framework for segmentation of cervical vertebrae in X-ray images. The framework first localizes the spinal region in the image using a deep fully convolutional neural network. Then vertebra centers are localized using a novel deep probabilistic spatial regression network. Finally, a novel shape-aware deep segmentation network is used to segment the vertebrae in the image. The framework can take an X-ray image and produce a vertebrae segmentation result without any manual intervention. Each block of the fully automatic framework has been trained on a set of 124 X-ray images and tested on another 172 images, all collected from real-life hospital emergency rooms. A Dice similarity coefficient of 0.84 and a shape error of 1.69 mm have been achieved. Copyright © 2018 Elsevier B.V. All rights reserved.

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

NASA Technical Reports Server (NTRS)

Ganguly, Sangram; Kalia, Subodh; Li, Shuang; Michaelis, Andrew; Nemani, Ramakrishna R.; Saatchi, Sassan A

2017-01-01

Uncertainties in input land cover estimates contribute to a significant bias in modeled above ground 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.

Understanding the Convolutional Neural Networks with Gradient Descent and Backpropagation

NASA Astrophysics Data System (ADS)

Zhou, XueFei

2018-04-01

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

A Real-Time Method to Estimate Speed of Object Based on Object Detection and Optical Flow Calculation

NASA Astrophysics Data System (ADS)

Liu, Kaizhan; Ye, Yunming; Li, Xutao; Li, Yan

2018-04-01

In recent years Convolutional Neural Network (CNN) has been widely used in computer vision field and makes great progress in lots of contents like object detection and classification. Even so, combining Convolutional Neural Network, which means making multiple CNN frameworks working synchronously and sharing their output information, could figure out useful message that each of them cannot provide singly. Here we introduce a method to real-time estimate speed of object by combining two CNN: YOLOv2 and FlowNet. In every frame, YOLOv2 provides object size; object location and object type while FlowNet providing the optical flow of whole image. On one hand, object size and object location help to select out the object part of optical flow image thus calculating out the average optical flow of every object. On the other hand, object type and object size help to figure out the relationship between optical flow and true speed by means of optics theory and priori knowledge. Therefore, with these two key information, speed of object can be estimated. This method manages to estimate multiple objects at real-time speed by only using a normal camera even in moving status, whose error is acceptable in most application fields like manless driving or robot vision.

A Universal 3D Voxel Descriptor for Solid-State Material Informatics with Deep Convolutional Neural Networks.

PubMed

Kajita, Seiji; Ohba, Nobuko; Jinnouchi, Ryosuke; Asahi, Ryoji

2017-12-05

Material informatics (MI) is a promising approach to liberate us from the time-consuming Edisonian (trial and error) process for material discoveries, driven by machine-learning algorithms. Several descriptors, which are encoded material features to feed computers, were proposed in the last few decades. Especially to solid systems, however, their insufficient representations of three dimensionality of field quantities such as electron distributions and local potentials have critically hindered broad and practical successes of the solid-state MI. We develop a simple, generic 3D voxel descriptor that compacts any field quantities, in such a suitable way to implement convolutional neural networks (CNNs). We examine the 3D voxel descriptor encoded from the electron distribution by a regression test with 680 oxides data. The present scheme outperforms other existing descriptors in the prediction of Hartree energies that are significantly relevant to the long-wavelength distribution of the valence electrons. The results indicate that this scheme can forecast any functionals of field quantities just by learning sufficient amount of data, if there is an explicit correlation between the target properties and field quantities. This 3D descriptor opens a way to import prominent CNNs-based algorithms of supervised, semi-supervised and reinforcement learnings into the solid-state MI.

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

NASA Astrophysics Data System (ADS)

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.

Orthogonal patterns in binary neural networks

NASA Technical Reports Server (NTRS)

Baram, Yoram

1988-01-01

A binary neural network that stores only mutually orthogonal patterns is shown to converge, when probed by any pattern, to a pattern in the memory space, i.e., the space spanned by the stored patterns. The latter are shown to be the only members of the memory space under a certain coding condition, which allows maximum storage of M=(2N) sup 0.5 patterns, where N is the number of neurons. The stored patterns are shown to have basins of attraction of radius N/(2M), within which errors are corrected with probability 1 in a single update cycle. When the probe falls outside these regions, the error correction capability can still be increased to 1 by repeatedly running the network with the same probe.

Combining Topological Hardware and Topological Software: Color-Code Quantum Computing with Topological Superconductor Networks

NASA Astrophysics Data System (ADS)

Litinski, Daniel; Kesselring, Markus S.; Eisert, Jens; von Oppen, Felix

2017-07-01

We present a scalable architecture for fault-tolerant topological quantum computation using networks of voltage-controlled Majorana Cooper pair boxes and topological color codes for error correction. Color codes have a set of transversal gates which coincides with the set of topologically protected gates in Majorana-based systems, namely, the Clifford gates. In this way, we establish color codes as providing a natural setting in which advantages offered by topological hardware can be combined with those arising from topological error-correcting software for full-fledged fault-tolerant quantum computing. We provide a complete description of our architecture, including the underlying physical ingredients. We start by showing that in topological superconductor networks, hexagonal cells can be employed to serve as physical qubits for universal quantum computation, and we present protocols for realizing topologically protected Clifford gates. These hexagonal-cell qubits allow for a direct implementation of open-boundary color codes with ancilla-free syndrome read-out and logical T gates via magic-state distillation. For concreteness, we describe how the necessary operations can be implemented using networks of Majorana Cooper pair boxes, and we give a feasibility estimate for error correction in this architecture. Our approach is motivated by nanowire-based networks of topological superconductors, but it could also be realized in alternative settings such as quantum-Hall-superconductor hybrids.

A convolutional neural network neutrino event classifier

DOE PAGES

Aurisano, A.; Radovic, A.; Rocco, D.; ...

2016-09-01

Here, 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 withoutmore » the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.« less

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

DOE PAGES

Acciarri, R.; Adams, C.; An, R.; ...

2017-03-14

Here, 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. Lastly, we also address technical issues that arise when applying this technique to data from a large LArTPCmore » at or near ground level.« less

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

NASA Astrophysics Data System (ADS)

Ryoo, M. S.; Matthies, Larry

2016-05-01

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

Gas Classification Using Deep Convolutional Neural Networks.

PubMed

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).

Gas Classification Using Deep Convolutional Neural Networks

PubMed Central

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

2018-01-01

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). PMID:29316723

A convolutional neural network neutrino event classifier

DOE Office of Scientific and Technical Information (OSTI.GOV)

Aurisano, A.; Radovic, A.; Rocco, D.

Here, 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 withoutmore » the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.« less

Comparison of rate one-half, equivalent constraint length 24, binary convolutional codes for use with sequential decoding on the deep-space channel

NASA Technical Reports Server (NTRS)

Massey, J. L.

1976-01-01

Virtually all previously-suggested rate 1/2 binary convolutional codes with KE = 24 are compared. Their distance properties are given; and their performance, both in computation and in error probability, with sequential decoding on the deep-space channel is determined by simulation. Recommendations are made both for the choice of a specific KE = 24 code as well as for codes to be included in future coding standards for the deep-space channel. A new result given in this report is a method for determining the statistical significance of error probability data when the error probability is so small that it is not feasible to perform enough decoding simulations to obtain more than a very small number of decoding errors.

Spatial and Time Domain Feature of ERP Speller System Extracted via Convolutional Neural Network.

PubMed

Yoon, Jaehong; Lee, Jungnyun; Whang, Mincheol

2018-01-01

Feature of event-related potential (ERP) has not been completely understood and illiteracy problem remains unsolved. To this end, P300 peak has been used as the feature of ERP in most brain-computer interface applications, but subjects who do not show such peak are common. Recent development of convolutional neural network provides a way to analyze spatial and temporal features of ERP. Here, we train the convolutional neural network with 2 convolutional layers whose feature maps represented spatial and temporal features of event-related potential. We have found that nonilliterate subjects' ERP show high correlation between occipital lobe and parietal lobe, whereas illiterate subjects only show correlation between neural activities from frontal lobe and central lobe. The nonilliterates showed peaks in P300, P500, and P700, whereas illiterates mostly showed peaks in around P700. P700 was strong in both subjects. We found that P700 peak may be the key feature of ERP as it appears in both illiterate and nonilliterate subjects.

Spatial and Time Domain Feature of ERP Speller System Extracted via Convolutional Neural Network

PubMed Central

2018-01-01

Feature of event-related potential (ERP) has not been completely understood and illiteracy problem remains unsolved. To this end, P300 peak has been used as the feature of ERP in most brain–computer interface applications, but subjects who do not show such peak are common. Recent development of convolutional neural network provides a way to analyze spatial and temporal features of ERP. Here, we train the convolutional neural network with 2 convolutional layers whose feature maps represented spatial and temporal features of event-related potential. We have found that nonilliterate subjects' ERP show high correlation between occipital lobe and parietal lobe, whereas illiterate subjects only show correlation between neural activities from frontal lobe and central lobe. The nonilliterates showed peaks in P300, P500, and P700, whereas illiterates mostly showed peaks in around P700. P700 was strong in both subjects. We found that P700 peak may be the key feature of ERP as it appears in both illiterate and nonilliterate subjects.

On the error statistics of Viterbi decoding and the performance of concatenated codes

NASA Technical Reports Server (NTRS)

Miller, R. L.; Deutsch, L. J.; Butman, S. A.

1981-01-01

Computer simulation results are presented on the performance of convolutional codes of constraint lengths 7 and 10 concatenated with the (255, 223) Reed-Solomon code (a proposed NASA standard). These results indicate that as much as 0.8 dB can be gained by concatenating this Reed-Solomon code with a (10, 1/3) convolutional code, instead of the (7, 1/2) code currently used by the DSN. A mathematical model of Viterbi decoder burst-error statistics is developed and is validated through additional computer simulations.

Efficient airport detection using region-based fully convolutional neural networks

NASA Astrophysics Data System (ADS)

Xin, Peng; Xu, Yuelei; Zhang, Xulei; Ma, Shiping; Li, Shuai; Lv, Chao

2018-04-01

This paper presents a model for airport detection using region-based fully convolutional neural networks. To achieve fast detection with high accuracy, we shared the conv layers between the region proposal procedure and the airport detection procedure and used graphics processing units (GPUs) to speed up the training and testing time. For lack of labeled data, we transferred the convolutional layers of ZF net pretrained by ImageNet to initialize the shared convolutional layers, then we retrained the model using the alternating optimization training strategy. The proposed model has been tested on an airport dataset consisting of 600 images. Experiments show that the proposed method can distinguish airports in our dataset from similar background scenes almost real-time with high accuracy, which is much better than traditional methods.

Global distortion of GPS networks associated with satellite antenna model errors

NASA Astrophysics Data System (ADS)

Cardellach, E.; Elósegui, P.; Davis, J. L.

2007-07-01

Recent studies of the GPS satellite phase center offsets (PCOs) suggest that these have been in error by ˜1 m. Previous studies had shown that PCO errors are absorbed mainly by parameters representing satellite clock and the radial components of site position. On the basis of the assumption that the radial errors are equal, PCO errors will therefore introduce an error in network scale. However, PCO errors also introduce distortions, or apparent deformations, within the network, primarily in the radial (vertical) component of site position that cannot be corrected via a Helmert transformation. Using numerical simulations to quantify the effects of PCO errors, we found that these PCO errors lead to a vertical network distortion of 6-12 mm per meter of PCO error. The network distortion depends on the minimum elevation angle used in the analysis of the GPS phase observables, becoming larger as the minimum elevation angle increases. The steady evolution of the GPS constellation as new satellites are launched, age, and are decommissioned, leads to the effects of PCO errors varying with time that introduce an apparent global-scale rate change. We demonstrate here that current estimates for PCO errors result in a geographically variable error in the vertical rate at the 1-2 mm yr-1 level, which will impact high-precision crustal deformation studies.

Global Distortion of GPS Networks Associated with Satellite Antenna Model Errors

NASA Technical Reports Server (NTRS)

Cardellach, E.; Elosequi, P.; Davis, J. L.

2007-01-01

Recent studies of the GPS satellite phase center offsets (PCOs) suggest that these have been in error by approx.1 m. Previous studies had shown that PCO errors are absorbed mainly by parameters representing satellite clock and the radial components of site position. On the basis of the assumption that the radial errors are equal, PCO errors will therefore introduce an error in network scale. However, PCO errors also introduce distortions, or apparent deformations, within the network, primarily in the radial (vertical) component of site position that cannot be corrected via a Helmert transformation. Using numerical simulations to quantify the effects of PC0 errors, we found that these PCO errors lead to a vertical network distortion of 6-12 mm per meter of PCO error. The network distortion depends on the minimum elevation angle used in the analysis of the GPS phase observables, becoming larger as the minimum elevation angle increases. The steady evolution of the GPS constellation as new satellites are launched, age, and are decommissioned, leads to the effects of PCO errors varying with time that introduce an apparent global-scale rate change. We demonstrate here that current estimates for PCO errors result in a geographically variable error in the vertical rate at the 1-2 mm/yr level, which will impact high-precision crustal deformation studies.

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

PubMed

Zhong, Jiandan; Lei, Tao; Yao, Guangle

2017-11-24

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

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

PubMed Central

Zhong, Jiandan; Lei, Tao; Yao, Guangle

2017-01-01

Vehicle detection in aerial images is an important and challenging task. Traditionally, many target detection models based on sliding-window fashion were developed and achieved acceptable performance, but these models are time-consuming in the detection phase. Recently, with the great success of convolutional neural networks (CNNs) in computer vision, many state-of-the-art detectors have been designed based on deep CNNs. However, these CNN-based detectors are inefficient when applied in aerial image data due to the fact that the existing CNN-based models struggle with small-size object detection and precise localization. To improve the detection accuracy without decreasing speed, we propose a CNN-based detection model combining two independent convolutional neural networks, where the first network is applied to generate a set of vehicle-like regions from multi-feature maps of different hierarchies and scales. Because the multi-feature maps combine the advantage of the deep and shallow convolutional layer, the first network performs well on locating the small targets in aerial image data. Then, the generated candidate regions are fed into the second network for feature extraction and decision making. Comprehensive experiments are conducted on the Vehicle Detection in Aerial Imagery (VEDAI) dataset and Munich vehicle dataset. The proposed cascaded detection model yields high performance, not only in detection accuracy but also in detection speed. PMID:29186756

Wireless Visual Sensor Network Resource Allocation using Cross-Layer Optimization

DTIC Science & Technology

2009-01-01

Rate Compatible Punctured Convolutional (RCPC) codes for channel...vol. 44, pp. 2943–2959, November 1998. [22] J. Hagenauer, “ Rate - compatible punctured convolutional codes (RCPC codes ) and their applications,” IEEE... coding rate for H.264/AVC video compression is determined. At the data link layer, the Rate - Compatible Puctured Convolutional (RCPC) channel coding

Cooperative MIMO communication at wireless sensor network: an error correcting code approach.

PubMed

Islam, Mohammad Rakibul; Han, Young Shin

2011-01-01

Cooperative communication in wireless sensor network (WSN) explores the energy efficient wireless communication schemes between multiple sensors and data gathering node (DGN) by exploiting multiple input multiple output (MIMO) and multiple input single output (MISO) configurations. In this paper, an energy efficient cooperative MIMO (C-MIMO) technique is proposed where low density parity check (LDPC) code is used as an error correcting code. The rate of LDPC code is varied by varying the length of message and parity bits. Simulation results show that the cooperative communication scheme outperforms SISO scheme in the presence of LDPC code. LDPC codes with different code rates are compared using bit error rate (BER) analysis. BER is also analyzed under different Nakagami fading scenario. Energy efficiencies are compared for different targeted probability of bit error p(b). It is observed that C-MIMO performs more efficiently when the targeted p(b) is smaller. Also the lower encoding rate for LDPC code offers better error characteristics.

Cooperative MIMO Communication at Wireless Sensor Network: An Error Correcting Code Approach

PubMed Central

Islam, Mohammad Rakibul; Han, Young Shin

2011-01-01

Cooperative communication in wireless sensor network (WSN) explores the energy efficient wireless communication schemes between multiple sensors and data gathering node (DGN) by exploiting multiple input multiple output (MIMO) and multiple input single output (MISO) configurations. In this paper, an energy efficient cooperative MIMO (C-MIMO) technique is proposed where low density parity check (LDPC) code is used as an error correcting code. The rate of LDPC code is varied by varying the length of message and parity bits. Simulation results show that the cooperative communication scheme outperforms SISO scheme in the presence of LDPC code. LDPC codes with different code rates are compared using bit error rate (BER) analysis. BER is also analyzed under different Nakagami fading scenario. Energy efficiencies are compared for different targeted probability of bit error pb. It is observed that C-MIMO performs more efficiently when the targeted pb is smaller. Also the lower encoding rate for LDPC code offers better error characteristics. PMID:22163732

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

PubMed

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

2018-01-01

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

Improving deep convolutional neural networks with mixed maxout units.

PubMed

Zhao, Hui-Zhen; Liu, Fu-Xian; Li, Long-Yue

2017-01-01

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.

Sequential Syndrome Decoding of Convolutional Codes

NASA Technical Reports Server (NTRS)

Reed, I. S.; Truong, T. K.

1984-01-01

The algebraic structure of convolutional codes are reviewed and sequential syndrome decoding is applied to those codes. These concepts are then used to realize by example actual sequential decoding, using the stack algorithm. The Fano metric for use in sequential decoding is modified so that it can be utilized to sequentially find the minimum weight error sequence.

Application of Two-Parameter Stabilizing Functions in Solving a Convolution-Type Integral Equation by Regularization Method

NASA Astrophysics Data System (ADS)

Maslakov, M. L.

2018-04-01

This paper examines the solution of convolution-type integral equations of the first kind by applying the Tikhonov regularization method with two-parameter stabilizing functions. The class of stabilizing functions is expanded in order to improve the accuracy of the resulting solution. The features of the problem formulation for identification and adaptive signal correction are described. A method for choosing regularization parameters in problems of identification and adaptive signal correction is suggested.

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

PubMed

Li, Siqi; Jiang, Huiyan; Pang, Wenbo

2017-05-01

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

ION Configuration Editor

NASA Technical Reports Server (NTRS)

Borgen, Richard L.

2013-01-01

The configuration of ION (Inter - planetary Overlay Network) network nodes is a manual task that is complex, time-consuming, and error-prone. This program seeks to accelerate this job and produce reliable configurations. The ION Configuration Editor is a model-based smart editor based on Eclipse Modeling Framework technology. An ION network designer uses this Eclipse-based GUI to construct a data model of the complete target network and then generate configurations. The data model is captured in an XML file. Intrinsic editor features aid in achieving model correctness, such as field fill-in, type-checking, lists of valid values, and suitable default values. Additionally, an explicit "validation" feature executes custom rules to catch more subtle model errors. A "survey" feature provides a set of reports providing an overview of the entire network, enabling a quick assessment of the model s completeness and correctness. The "configuration" feature produces the main final result, a complete set of ION configuration files (eight distinct file types) for each ION node in the network.

Optimal JPWL Forward Error Correction Rate Allocation for Robust JPEG 2000 Images and Video Streaming over Mobile Ad Hoc Networks

NASA Astrophysics Data System (ADS)

Agueh, Max; Diouris, Jean-François; Diop, Magaye; Devaux, François-Olivier; De Vleeschouwer, Christophe; Macq, Benoit

2008-12-01

Based on the analysis of real mobile ad hoc network (MANET) traces, we derive in this paper an optimal wireless JPEG 2000 compliant forward error correction (FEC) rate allocation scheme for a robust streaming of images and videos over MANET. The packet-based proposed scheme has a low complexity and is compliant to JPWL, the 11th part of the JPEG 2000 standard. The effectiveness of the proposed method is evaluated using a wireless Motion JPEG 2000 client/server application; and the ability of the optimal scheme to guarantee quality of service (QoS) to wireless clients is demonstrated.

Convolutional networks for vehicle track segmentation

NASA Astrophysics Data System (ADS)

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.

Semantic Segmentation of Convolutional Neural Network for Supervised Classification of Multispectral Remote Sensing

NASA Astrophysics Data System (ADS)

Xue, L.; Liu, C.; Wu, Y.; Li, H.

2018-04-01

Semantic segmentation is a fundamental research in remote sensing image processing. Because of the complex maritime environment, the classification of roads, vegetation, buildings and water from remote Sensing Imagery is a challenging task. Although the neural network has achieved excellent performance in semantic segmentation in the last years, there are a few of works using CNN for ground object segmentation and the results could be further improved. This paper used convolution neural network named U-Net, its structure has a contracting path and an expansive path to get high resolution output. In the network , We added BN layers, which is more conducive to the reverse pass. Moreover, after upsampling convolution , we add dropout layers to prevent overfitting. They are promoted to get more precise segmentation results. To verify this network architecture, we used a Kaggle dataset. Experimental results show that U-Net achieved good performance compared with other architectures, especially in high-resolution remote sensing imagery.

Purification of Logic-Qubit Entanglement.

PubMed

Zhou, Lan; Sheng, Yu-Bo

2016-07-05

Recently, the logic-qubit entanglement shows its potential application in future quantum communication and quantum network. However, the entanglement will suffer from the noise and decoherence. In this paper, we will investigate the first entanglement purification protocol for logic-qubit entanglement. We show that both the bit-flip error and phase-flip error in logic-qubit entanglement can be well purified. Moreover, the bit-flip error in physical-qubit entanglement can be completely corrected. The phase-flip in physical-qubit entanglement error equals to the bit-flip error in logic-qubit entanglement, which can also be purified. This entanglement purification protocol may provide some potential applications in future quantum communication and quantum network.

3D multi-scale FCN with random modality voxel dropout learning for Intervertebral Disc Localization and Segmentation from Multi-modality MR Images.

PubMed

Li, Xiaomeng; Dou, Qi; Chen, Hao; Fu, Chi-Wing; Qi, Xiaojuan; Belavý, Daniel L; Armbrecht, Gabriele; Felsenberg, Dieter; Zheng, Guoyan; Heng, Pheng-Ann

2018-04-01

Intervertebral discs (IVDs) are small joints that lie between adjacent vertebrae. The localization and segmentation of IVDs are important for spine disease diagnosis and measurement quantification. However, manual annotation is time-consuming and error-prone with limited reproducibility, particularly for volumetric data. In this work, our goal is to develop an automatic and accurate method based on fully convolutional networks (FCN) for the localization and segmentation of IVDs from multi-modality 3D MR data. Compared with single modality data, multi-modality MR images provide complementary contextual information, which contributes to better recognition performance. However, how to effectively integrate such multi-modality information to generate accurate segmentation results remains to be further explored. In this paper, we present a novel multi-scale and modality dropout learning framework to locate and segment IVDs from four-modality MR images. First, we design a 3D multi-scale context fully convolutional network, which processes the input data in multiple scales of context and then merges the high-level features to enhance the representation capability of the network for handling the scale variation of anatomical structures. Second, to harness the complementary information from different modalities, we present a random modality voxel dropout strategy which alleviates the co-adaption issue and increases the discriminative capability of the network. Our method achieved the 1st place in the MICCAI challenge on automatic localization and segmentation of IVDs from multi-modality MR images, with a mean segmentation Dice coefficient of 91.2% and a mean localization error of 0.62 mm. We further conduct extensive experiments on the extended dataset to validate our method. We demonstrate that the proposed modality dropout strategy with multi-modality images as contextual information improved the segmentation accuracy significantly. Furthermore, experiments conducted on extended data collected from two different time points demonstrate the efficacy of our method on tracking the morphological changes in a longitudinal study. Copyright © 2018 Elsevier B.V. All rights reserved.

Combining morphometric features and convolutional networks fusion for glaucoma diagnosis

NASA Astrophysics Data System (ADS)

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.

Deep learning based state recognition of substation switches

NASA Astrophysics Data System (ADS)

Wang, Jin

2018-06-01

Different from the traditional method which recognize the state of substation switches based on the running rules of electrical power system, this work proposes a novel convolutional neuron network-based state recognition approach of substation switches. Inspired by the theory of transfer learning, we first establish a convolutional neuron network model trained on the large-scale image set ILSVRC2012, then the restricted Boltzmann machine is employed to replace the full connected layer of the convolutional neuron network and trained on our small image dataset of 110kV substation switches to get a stronger model. Experiments conducted on our image dataset of 110kV substation switches show that, the proposed approach can be applicable to the substation to reduce the running cost and implement the real unattended operation.

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

NASA Astrophysics Data System (ADS)

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.

The Convolutional Visual Network for Identification and Reconstruction of NOvA Events

DOE Office of Scientific and Technical Information (OSTI.GOV)

Psihas, Fernanda

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 appearancemore » signal by 40% and studies show potential impact to the vμ disappearance analysis.« less

Processing circuit with asymmetry corrector and convolutional encoder for digital data

NASA Technical Reports Server (NTRS)

Pfiffner, Harold J. (Inventor)

1987-01-01

A processing circuit is provided for correcting for input parameter variations, such as data and clock signal symmetry, phase offset and jitter, noise and signal amplitude, in incoming data signals. An asymmetry corrector circuit performs the correcting function and furnishes the corrected data signals to a convolutional encoder circuit. The corrector circuit further forms a regenerated clock signal from clock pulses in the incoming data signals and another clock signal at a multiple of the incoming clock signal. These clock signals are furnished to the encoder circuit so that encoded data may be furnished to a modulator at a high data rate for transmission.

Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network

PubMed Central

Zhai, Xiaolong; Jelfs, Beth; Chan, Rosa H. M.; Tin, Chung

2017-01-01

Hand movement classification based on surface electromyography (sEMG) pattern recognition is a promising approach for upper limb neuroprosthetic control. However, maintaining day-to-day performance is challenged by the non-stationary nature of sEMG in real-life operation. In this study, we propose a self-recalibrating classifier that can be automatically updated to maintain a stable performance over time without the need for user retraining. Our classifier is based on convolutional neural network (CNN) using short latency dimension-reduced sEMG spectrograms as inputs. The pretrained classifier is recalibrated routinely using a corrected version of the prediction results from recent testing sessions. Our proposed system was evaluated with the NinaPro database comprising of hand movement data of 40 intact and 11 amputee subjects. Our system was able to achieve ~10.18% (intact, 50 movement types) and ~2.99% (amputee, 10 movement types) increase in classification accuracy averaged over five testing sessions with respect to the unrecalibrated classifier. When compared with a support vector machine (SVM) classifier, our CNN-based system consistently showed higher absolute performance and larger improvement as well as more efficient training. These results suggest that the proposed system can be a useful tool to facilitate long-term adoption of prosthetics for amputees in real-life applications. PMID:28744189

Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network.

PubMed

Zhai, Xiaolong; Jelfs, Beth; Chan, Rosa H M; Tin, Chung

2017-01-01

Hand movement classification based on surface electromyography (sEMG) pattern recognition is a promising approach for upper limb neuroprosthetic control. However, maintaining day-to-day performance is challenged by the non-stationary nature of sEMG in real-life operation. In this study, we propose a self-recalibrating classifier that can be automatically updated to maintain a stable performance over time without the need for user retraining. Our classifier is based on convolutional neural network (CNN) using short latency dimension-reduced sEMG spectrograms as inputs. The pretrained classifier is recalibrated routinely using a corrected version of the prediction results from recent testing sessions. Our proposed system was evaluated with the NinaPro database comprising of hand movement data of 40 intact and 11 amputee subjects. Our system was able to achieve ~10.18% (intact, 50 movement types) and ~2.99% (amputee, 10 movement types) increase in classification accuracy averaged over five testing sessions with respect to the unrecalibrated classifier. When compared with a support vector machine (SVM) classifier, our CNN-based system consistently showed higher absolute performance and larger improvement as well as more efficient training. These results suggest that the proposed system can be a useful tool to facilitate long-term adoption of prosthetics for amputees in real-life applications.

Classifying magnetic resonance image modalities with convolutional neural networks

NASA Astrophysics Data System (ADS)

Remedios, Samuel; Pham, Dzung L.; Butman, John A.; Roy, Snehashis

2018-02-01

Magnetic Resonance (MR) imaging allows the acquisition of images with different contrast properties depending on the acquisition protocol and the magnetic properties of tissues. Many MR brain image processing techniques, such as tissue segmentation, require multiple MR contrasts as inputs, and each contrast is treated differently. Thus it is advantageous to automate the identification of image contrasts for various purposes, such as facilitating image processing pipelines, and managing and maintaining large databases via content-based image retrieval (CBIR). Most automated CBIR techniques focus on a two-step process: extracting features from data and classifying the image based on these features. We present a novel 3D deep convolutional neural network (CNN)- based method for MR image contrast classification. The proposed CNN automatically identifies the MR contrast of an input brain image volume. Specifically, we explored three classification problems: (1) identify T1-weighted (T1-w), T2-weighted (T2-w), and fluid-attenuated inversion recovery (FLAIR) contrasts, (2) identify pre vs postcontrast T1, (3) identify pre vs post-contrast FLAIR. A total of 3418 image volumes acquired from multiple sites and multiple scanners were used. To evaluate each task, the proposed model was trained on 2137 images and tested on the remaining 1281 images. Results showed that image volumes were correctly classified with 97.57% accuracy.

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

PubMed

Kwon, Yea-Hoon; Shin, Sae-Byuk; Kim, Shin-Dug

2018-04-30

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

Fuzzy Logic Module of Convolutional Neural Network for Handwritten Digits Recognition

NASA Astrophysics Data System (ADS)

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.

Parameter prediction based on Improved Process neural network and ARMA error compensation in Evaporation Process

NASA Astrophysics Data System (ADS)

Qian, Xiaoshan

2018-01-01

The traditional model of evaporation process parameters have continuity and cumulative characteristics of the prediction error larger issues, based on the basis of the process proposed an adaptive particle swarm neural network forecasting method parameters established on the autoregressive moving average (ARMA) error correction procedure compensated prediction model to predict the results of the neural network to improve prediction accuracy. Taking a alumina plant evaporation process to analyze production data validation, and compared with the traditional model, the new model prediction accuracy greatly improved, can be used to predict the dynamic process of evaporation of sodium aluminate solution components.

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

PubMed

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

2018-04-01

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

A Deep Convolutional Coupling Network for Change Detection Based on Heterogeneous Optical and Radar Images.

PubMed

Liu, Jia; Gong, Maoguo; Qin, Kai; Zhang, Puzhao

2018-03-01

We propose an unsupervised deep convolutional coupling network for change detection based on two heterogeneous images acquired by optical sensors and radars on different dates. Most existing change detection methods are based on homogeneous images. Due to the complementary properties of optical and radar sensors, there is an increasing interest in change detection based on heterogeneous images. The proposed network is symmetric with each side consisting of one convolutional layer and several coupling layers. The two input images connected with the two sides of the network, respectively, are transformed into a feature space where their feature representations become more consistent. In this feature space, the different map is calculated, which then leads to the ultimate detection map by applying a thresholding algorithm. The network parameters are learned by optimizing a coupling function. The learning process is unsupervised, which is different from most existing change detection methods based on heterogeneous images. Experimental results on both homogenous and heterogeneous images demonstrate the promising performance of the proposed network compared with several existing approaches.

Trellises and Trellis-Based Decoding Algorithms for Linear Block Codes

NASA Technical Reports Server (NTRS)

Lin, Shu

1998-01-01

A code trellis is a graphical representation of a code, block or convolutional, in which every path represents a codeword (or a code sequence for a convolutional code). This representation makes it possible to implement Maximum Likelihood Decoding (MLD) of a code with reduced decoding complexity. The most well known trellis-based MLD algorithm is the Viterbi algorithm. The trellis representation was first introduced and used for convolutional codes [23]. This representation, together with the Viterbi decoding algorithm, has resulted in a wide range of applications of convolutional codes for error control in digital communications over the last two decades. There are two major reasons for this inactive period of research in this area. First, most coding theorists at that time believed that block codes did not have simple trellis structure like convolutional codes and maximum likelihood decoding of linear block codes using the Viterbi algorithm was practically impossible, except for very short block codes. Second, since almost all of the linear block codes are constructed algebraically or based on finite geometries, it was the belief of many coding theorists that algebraic decoding was the only way to decode these codes. These two reasons seriously hindered the development of efficient soft-decision decoding methods for linear block codes and their applications to error control in digital communications. This led to a general belief that block codes are inferior to convolutional codes and hence, that they were not useful. Chapter 2 gives a brief review of linear block codes. The goal is to provide the essential background material for the development of trellis structure and trellis-based decoding algorithms for linear block codes in the later chapters. Chapters 3 through 6 present the fundamental concepts, finite-state machine model, state space formulation, basic structural properties, state labeling, construction procedures, complexity, minimality, and sectionalization of trellises. Chapter 7 discusses trellis decomposition and subtrellises for low-weight codewords. Chapter 8 first presents well known methods for constructing long powerful codes from short component codes or component codes of smaller dimensions, and then provides methods for constructing their trellises which include Shannon and Cartesian product techniques. Chapter 9 deals with convolutional codes, puncturing, zero-tail termination and tail-biting.Chapters 10 through 13 present various trellis-based decoding algorithms, old and new. Chapter 10 first discusses the application of the well known Viterbi decoding algorithm to linear block codes, optimum sectionalization of a code trellis to minimize computation complexity, and design issues for IC (integrated circuit) implementation of a Viterbi decoder. Then it presents a new decoding algorithm for convolutional codes, named Differential Trellis Decoding (DTD) algorithm. Chapter 12 presents a suboptimum reliability-based iterative decoding algorithm with a low-weight trellis search for the most likely codeword. This decoding algorithm provides a good trade-off between error performance and decoding complexity. All the decoding algorithms presented in Chapters 10 through 12 are devised to minimize word error probability. Chapter 13 presents decoding algorithms that minimize bit error probability and provide the corresponding soft (reliability) information at the output of the decoder. Decoding algorithms presented are the MAP (maximum a posteriori probability) decoding algorithm and the Soft-Output Viterbi Algorithm (SOVA) algorithm. Finally, the minimization of bit error probability in trellis-based MLD is discussed.

Nonparametric Representations for Integrated Inference, Control, and Sensing

DTIC Science & Technology

2015-10-01

Learning (ICML), 2013. [20] Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, and Trevor Darrell. DeCAF: A deep ...unlimited. Multi-layer feature learning “SuperVision” Convolutional Neural Network (CNN) ImageNet Classification with Deep Convolutional Neural Networks...to develop a new framework for autonomous operations that will extend the state of the art in distributed learning and modeling from data, and

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

PubMed

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

2017-02-01

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

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

PubMed

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

2017-01-01

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

An accurate system for onsite calibration of electronic transformers with digital output.

PubMed

Zhi, Zhang; Li, Hong-Bin

2012-06-01

Calibration systems with digital output are used to replace conventional calibration systems because of principle diversity and characteristics of digital output of electronic transformers. But precision and unpredictable stability limit their onsite application even development. So fully considering the factors influencing accuracy of calibration system and employing simple but reliable structure, an all-digital calibration system with digital output is proposed in this paper. In complicated calibration environments, precision and dynamic range are guaranteed by A/D converter with 24-bit resolution, synchronization error limit is nanosecond by using the novelty synchronization method. In addition, an error correction algorithm based on the differential method by using two-order Hanning convolution window has good inhibition of frequency fluctuation and inter-harmonics interference. To verify the effectiveness, error calibration was carried out in the State Grid Electric Power Research Institute of China and results show that the proposed system can reach the precision class up to 0.05. Actual onsite calibration shows that the system has high accuracy, and is easy to operate with satisfactory stability.

An accurate system for onsite calibration of electronic transformers with digital output

DOE Office of Scientific and Technical Information (OSTI.GOV)

Zhi Zhang; Li Hongbin; State Key Laboratory of Advanced Electromagnetic Engineering and Technology, Wuhan 430074

Calibration systems with digital output are used to replace conventional calibration systems because of principle diversity and characteristics of digital output of electronic transformers. But precision and unpredictable stability limit their onsite application even development. So fully considering the factors influencing accuracy of calibration system and employing simple but reliable structure, an all-digital calibration system with digital output is proposed in this paper. In complicated calibration environments, precision and dynamic range are guaranteed by A/D converter with 24-bit resolution, synchronization error limit is nanosecond by using the novelty synchronization method. In addition, an error correction algorithm based on the differentialmore » method by using two-order Hanning convolution window has good inhibition of frequency fluctuation and inter-harmonics interference. To verify the effectiveness, error calibration was carried out in the State Grid Electric Power Research Institute of China and results show that the proposed system can reach the precision class up to 0.05. Actual onsite calibration shows that the system has high accuracy, and is easy to operate with satisfactory stability.« less

An accurate system for onsite calibration of electronic transformers with digital output

NASA Astrophysics Data System (ADS)

Zhi, Zhang; Li, Hong-Bin

2012-06-01

Calibration systems with digital output are used to replace conventional calibration systems because of principle diversity and characteristics of digital output of electronic transformers. But precision and unpredictable stability limit their onsite application even development. So fully considering the factors influencing accuracy of calibration system and employing simple but reliable structure, an all-digital calibration system with digital output is proposed in this paper. In complicated calibration environments, precision and dynamic range are guaranteed by A/D converter with 24-bit resolution, synchronization error limit is nanosecond by using the novelty synchronization method. In addition, an error correction algorithm based on the differential method by using two-order Hanning convolution window has good inhibition of frequency fluctuation and inter-harmonics interference. To verify the effectiveness, error calibration was carried out in the State Grid Electric Power Research Institute of China and results show that the proposed system can reach the precision class up to 0.05. Actual onsite calibration shows that the system has high accuracy, and is easy to operate with satisfactory stability.

A Configurable Event-Driven Convolutional Node with Rate Saturation Mechanism for Modular ConvNet Systems Implementation.

PubMed

Camuñas-Mesa, Luis A; Domínguez-Cordero, Yaisel L; Linares-Barranco, Alejandro; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabé

2018-01-01

Convolutional Neural Networks (ConvNets) are a particular type of neural network often used for many applications like image recognition, video analysis or natural language processing. They are inspired by the human brain, following a specific organization of the connectivity pattern between layers of neurons known as receptive field. These networks have been traditionally implemented in software, but they are becoming more computationally expensive as they scale up, having limitations for real-time processing of high-speed stimuli. On the other hand, hardware implementations show difficulties to be used for different applications, due to their reduced flexibility. In this paper, we propose a fully configurable event-driven convolutional node with rate saturation mechanism that can be used to implement arbitrary ConvNets on FPGAs. This node includes a convolutional processing unit and a routing element which allows to build large 2D arrays where any multilayer structure can be implemented. The rate saturation mechanism emulates the refractory behavior in biological neurons, guaranteeing a minimum separation in time between consecutive events. A 4-layer ConvNet with 22 convolutional nodes trained for poker card symbol recognition has been implemented in a Spartan6 FPGA. This network has been tested with a stimulus where 40 poker cards were observed by a Dynamic Vision Sensor (DVS) in 1 s time. Different slow-down factors were applied to characterize the behavior of the system for high speed processing. For slow stimulus play-back, a 96% recognition rate is obtained with a power consumption of 0.85 mW. At maximum play-back speed, a traffic control mechanism downsamples the input stimulus, obtaining a recognition rate above 63% when less than 20% of the input events are processed, demonstrating the robustness of the network.

A Configurable Event-Driven Convolutional Node with Rate Saturation Mechanism for Modular ConvNet Systems Implementation

PubMed Central

Camuñas-Mesa, Luis A.; Domínguez-Cordero, Yaisel L.; Linares-Barranco, Alejandro; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabé

2018-01-01

Convolutional Neural Networks (ConvNets) are a particular type of neural network often used for many applications like image recognition, video analysis or natural language processing. They are inspired by the human brain, following a specific organization of the connectivity pattern between layers of neurons known as receptive field. These networks have been traditionally implemented in software, but they are becoming more computationally expensive as they scale up, having limitations for real-time processing of high-speed stimuli. On the other hand, hardware implementations show difficulties to be used for different applications, due to their reduced flexibility. In this paper, we propose a fully configurable event-driven convolutional node with rate saturation mechanism that can be used to implement arbitrary ConvNets on FPGAs. This node includes a convolutional processing unit and a routing element which allows to build large 2D arrays where any multilayer structure can be implemented. The rate saturation mechanism emulates the refractory behavior in biological neurons, guaranteeing a minimum separation in time between consecutive events. A 4-layer ConvNet with 22 convolutional nodes trained for poker card symbol recognition has been implemented in a Spartan6 FPGA. This network has been tested with a stimulus where 40 poker cards were observed by a Dynamic Vision Sensor (DVS) in 1 s time. Different slow-down factors were applied to characterize the behavior of the system for high speed processing. For slow stimulus play-back, a 96% recognition rate is obtained with a power consumption of 0.85 mW. At maximum play-back speed, a traffic control mechanism downsamples the input stimulus, obtaining a recognition rate above 63% when less than 20% of the input events are processed, demonstrating the robustness of the network. PMID:29515349

An Improved Method of Heterogeneity Compensation for the Convolution / Superposition Algorithm

NASA Astrophysics Data System (ADS)

Jacques, Robert; McNutt, Todd

2014-03-01

Purpose: To improve the accuracy of convolution/superposition (C/S) in heterogeneous material by developing a new algorithm: heterogeneity compensated superposition (HCS). Methods: C/S has proven to be a good estimator of the dose deposited in a homogeneous volume. However, near heterogeneities electron disequilibrium occurs, leading to the faster fall-off and re-buildup of dose. We propose to filter the actual patient density in a position and direction sensitive manner, allowing the dose deposited near interfaces to be increased or decreased relative to C/S. We implemented the effective density function as a multivariate first-order recursive filter and incorporated it into GPU-accelerated, multi-energetic C/S implementation. We compared HCS against C/S using the ICCR 2000 Monte-Carlo accuracy benchmark, 23 similar accuracy benchmarks and 5 patient cases. Results: Multi-energetic HCS increased the dosimetric accuracy for the vast majority of voxels; in many cases near Monte-Carlo results were achieved. We defined the per-voxel error, %|mm, as the minimum of the distance to agreement in mm and the dosimetric percentage error relative to the maximum MC dose. HCS improved the average mean error by 0.79 %|mm for the patient volumes; reducing the average mean error from 1.93 %|mm to 1.14 %|mm. Very low densities (i.e. < 0.1 g / cm3) remained problematic, but may be solvable with a better filter function. Conclusions: HCS improved upon C/S's density scaled heterogeneity correction with a position and direction sensitive density filter. This method significantly improved the accuracy of the GPU based algorithm reaching the accuracy levels of Monte Carlo based methods with performance in a few tenths of seconds per beam. Acknowledgement: Funding for this research was provided by the NSF Cooperative Agreement EEC9731748, Elekta / IMPAC Medical Systems, Inc. and the Johns Hopkins University. James Satterthwaite provided the Monte Carlo benchmark simulations.

Communications and information research: Improved space link performance via concatenated forward error correction coding

NASA Technical Reports Server (NTRS)

Rao, T. R. N.; Seetharaman, G.; Feng, G. L.

1996-01-01

With the development of new advanced instruments for remote sensing applications, sensor data will be generated at a rate that not only requires increased onboard processing and storage capability, but imposes demands on the space to ground communication link and ground data management-communication system. Data compression and error control codes provide viable means to alleviate these demands. Two types of data compression have been studied by many researchers in the area of information theory: a lossless technique that guarantees full reconstruction of the data, and a lossy technique which generally gives higher data compaction ratio but incurs some distortion in the reconstructed data. To satisfy the many science disciplines which NASA supports, lossless data compression becomes a primary focus for the technology development. While transmitting the data obtained by any lossless data compression, it is very important to use some error-control code. For a long time, convolutional codes have been widely used in satellite telecommunications. To more efficiently transform the data obtained by the Rice algorithm, it is required to meet the a posteriori probability (APP) for each decoded bit. A relevant algorithm for this purpose has been proposed which minimizes the bit error probability in the decoding linear block and convolutional codes and meets the APP for each decoded bit. However, recent results on iterative decoding of 'Turbo codes', turn conventional wisdom on its head and suggest fundamentally new techniques. During the past several months of this research, the following approaches have been developed: (1) a new lossless data compression algorithm, which is much better than the extended Rice algorithm for various types of sensor data, (2) a new approach to determine the generalized Hamming weights of the algebraic-geometric codes defined by a large class of curves in high-dimensional spaces, (3) some efficient improved geometric Goppa codes for disk memory systems and high-speed mass memory systems, and (4) a tree based approach for data compression using dynamic programming.

Detection of high-grade small bowel obstruction on conventional radiography with convolutional neural networks.

PubMed

Cheng, Phillip M; Tejura, Tapas K; Tran, Khoa N; Whang, Gilbert

2018-05-01

The purpose of this pilot study is to determine whether a deep convolutional neural network can be trained with limited image data to detect high-grade small bowel obstruction patterns on supine abdominal radiographs. Grayscale images from 3663 clinical supine abdominal radiographs were categorized into obstructive and non-obstructive categories independently by three abdominal radiologists, and the majority classification was used as ground truth; 74 images were found to be consistent with small bowel obstruction. Images were rescaled and randomized, with 2210 images constituting the training set (39 with small bowel obstruction) and 1453 images constituting the test set (35 with small bowel obstruction). Weight parameters for the final classification layer of the Inception v3 convolutional neural network, previously trained on the 2014 Large Scale Visual Recognition Challenge dataset, were retrained on the training set. After training, the neural network achieved an AUC of 0.84 on the test set (95% CI 0.78-0.89). At the maximum Youden index (sensitivity + specificity-1), the sensitivity of the system for small bowel obstruction is 83.8%, with a specificity of 68.1%. The results demonstrate that transfer learning with convolutional neural networks, even with limited training data, may be used to train a detector for high-grade small bowel obstruction gas patterns on supine radiographs.

Beyond RGB: Very high resolution urban remote sensing with multimodal deep networks

NASA Astrophysics Data System (ADS)

Audebert, Nicolas; Le Saux, Bertrand; Lefèvre, Sébastien

2018-06-01

In this work, we investigate various methods to deal with semantic labeling of very high resolution multi-modal remote sensing data. Especially, we study how deep fully convolutional networks can be adapted to deal with multi-modal and multi-scale remote sensing data for semantic labeling. Our contributions are threefold: (a) we present an efficient multi-scale approach to leverage both a large spatial context and the high resolution data, (b) we investigate early and late fusion of Lidar and multispectral data, (c) we validate our methods on two public datasets with state-of-the-art results. Our results indicate that late fusion make it possible to recover errors steaming from ambiguous data, while early fusion allows for better joint-feature learning but at the cost of higher sensitivity to missing data.

Statistics of the residual refraction errors in laser ranging data

NASA Technical Reports Server (NTRS)

Gardner, C. S.

1977-01-01

A theoretical model for the range error covariance was derived by assuming that the residual refraction errors are due entirely to errors in the meteorological data which are used to calculate the atmospheric correction. The properties of the covariance function are illustrated by evaluating the theoretical model for the special case of a dense network of weather stations uniformly distributed within a circle.

Fully convolutional neural networks for polyp segmentation in colonoscopy

NASA Astrophysics Data System (ADS)

Brandao, Patrick; Mazomenos, Evangelos; Ciuti, Gastone; Caliò, Renato; Bianchi, Federico; Menciassi, Arianna; Dario, Paolo; Koulaouzidis, Anastasios; Arezzo, Alberto; Stoyanov, Danail

2017-03-01

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 established networks into a fully convolution architecture and fine-tuned their learned representations to the polyp segmentation task. We validate our framework on the 2015 MICCAI polyp detection challenge dataset, surpassing the state-of-the-art in automated polyp detection. Our method obtained high segmentation accuracy and a detection precision and recall of 73.61% and 86.31%, respectively.

Deep Convolutional Neural Network-Based Early Automated Detection of Diabetic Retinopathy Using Fundus Image.

PubMed

Xu, Kele; Feng, Dawei; Mi, Haibo

2017-11-23

The automatic detection of diabetic retinopathy is of vital importance, as it is the main cause of irreversible vision loss in the working-age population in the developed world. The early detection of diabetic retinopathy occurrence can be very helpful for clinical treatment; although several different feature extraction approaches have been proposed, the classification task for retinal images is still tedious even for those trained clinicians. Recently, deep convolutional neural networks have manifested superior performance in image classification compared to previous handcrafted feature-based image classification methods. Thus, in this paper, we explored the use of deep convolutional neural network methodology for the automatic classification of diabetic retinopathy using color fundus image, and obtained an accuracy of 94.5% on our dataset, outperforming the results obtained by using classical approaches.

ICD-10 procedure codes produce transition challenges.

PubMed

Boyd, Andrew D; Li, Jianrong 'John'; Kenost, Colleen; Zaim, Samir Rachid; Krive, Jacob; Mittal, Manish; Satava, Richard A; Burton, Michael; Smith, Jacob; Lussier, Yves A

2018-01-01

The transition of procedure coding from ICD-9-CM-Vol-3 to ICD-10-PCS has generated problems for the medical community at large resulting from the lack of clarity required to integrate two non-congruent coding systems. We hypothesized that quantifying these issues with network topology analyses offers a better understanding of the issues, and therefore we developed solutions (online tools) to empower hospital administrators and researchers to address these challenges. Five topologies were identified: "identity"(I), "class-to-subclass"(C2S), "subclass-toclass"(S2C), "convoluted(C)", and "no mapping"(NM). The procedure codes in the 2010 Illinois Medicaid dataset (3,290 patients, 116 institutions) were categorized as C=55%, C2S=40%, I=3%, NM=2%, and S2C=1%. Majority of the problematic and ambiguous mappings (convoluted) pertained to operations in ophthalmology cardiology, urology, gyneco-obstetrics, and dermatology. Finally, the algorithms were expanded into a user-friendly tool to identify problematic topologies and specify lists of procedural codes utilized by medical professionals and researchers for mitigating error-prone translations, simplifying research, and improving quality.http://www.lussiergroup.org/transition-to-ICD10PCS.

Decoding small surface codes with feedforward neural networks

NASA Astrophysics Data System (ADS)

Varsamopoulos, Savvas; Criger, Ben; Bertels, Koen

2018-01-01

Surface codes reach high error thresholds when decoded with known algorithms, but the decoding time will likely exceed the available time budget, especially for near-term implementations. To decrease the decoding time, we reduce the decoding problem to a classification problem that a feedforward neural network can solve. We investigate quantum error correction and fault tolerance at small code distances using neural network-based decoders, demonstrating that the neural network can generalize to inputs that were not provided during training and that they can reach similar or better decoding performance compared to previous algorithms. We conclude by discussing the time required by a feedforward neural network decoder in hardware.

An Automated Method to Generate e-Learning Quizzes from Online Language Learner Writing

ERIC Educational Resources Information Center

Flanagan, Brendan; Yin, Chengjiu; Hirokawa, Sachio; Hashimoto, Kiyota; Tabata, Yoshiyuki

2013-01-01

In this paper, the entries of Lang-8, which is a Social Networking Site (SNS) site for learning and practicing foreign languages, were analyzed and found to contain similar rates of errors for most error categories reported in previous research. These similarly rated errors were then processed using an algorithm to determine corrections suggested…

Purification of Logic-Qubit Entanglement

PubMed Central

Zhou, Lan; Sheng, Yu-Bo

2016-01-01

Recently, the logic-qubit entanglement shows its potential application in future quantum communication and quantum network. However, the entanglement will suffer from the noise and decoherence. In this paper, we will investigate the first entanglement purification protocol for logic-qubit entanglement. We show that both the bit-flip error and phase-flip error in logic-qubit entanglement can be well purified. Moreover, the bit-flip error in physical-qubit entanglement can be completely corrected. The phase-flip in physical-qubit entanglement error equals to the bit-flip error in logic-qubit entanglement, which can also be purified. This entanglement purification protocol may provide some potential applications in future quantum communication and quantum network. PMID:27377165

Tropospheric Correction for InSAR Using Interpolated ECMWF Data and GPS Zenith Total Delay

NASA Technical Reports Server (NTRS)

Webb, Frank H.; Fishbein, Evan F.; Moore, Angelyn W.; Owen, Susan E.; Fielding, Eric J.; Granger, Stephanie L.; Bjorndahl, Fredrik; Lofgren Johan

2011-01-01

To mitigate atmospheric errors caused by the troposphere, which is a limiting error source for spaceborne interferometric synthetic aperture radar (InSAR) imaging, a tropospheric correction method has been developed using data from the European Centre for Medium- Range Weather Forecasts (ECMWF) and the Global Positioning System (GPS). The ECMWF data was interpolated using a Stretched Boundary Layer Model (SBLM), and ground-based GPS estimates of the tropospheric delay from the Southern California Integrated GPS Network were interpolated using modified Gaussian and inverse distance weighted interpolations. The resulting Zenith Total Delay (ZTD) correction maps have been evaluated, both separately and using a combination of the two data sets, for three short-interval InSAR pairs from Envisat during 2006 on an area stretching from northeast from the Los Angeles basin towards Death Valley. Results show that the root mean square (rms) in the InSAR images was greatly reduced, meaning a significant reduction in the atmospheric noise of up to 32 percent. However, for some of the images, the rms increased and large errors remained after applying the tropospheric correction. The residuals showed a constant gradient over the area, suggesting that a remaining orbit error from Envisat was present. The orbit reprocessing in ROI_pac and the plane fitting both require that the only remaining error in the InSAR image be the orbit error. If this is not fulfilled, the correction can be made anyway, but it will be done using all remaining errors assuming them to be orbit errors. By correcting for tropospheric noise, the biggest error source is removed, and the orbit error becomes apparent and can be corrected for

Using soft computing techniques to predict corrected air permeability using Thomeer parameters, air porosity and grain density

NASA Astrophysics Data System (ADS)

Nooruddin, Hasan A.; Anifowose, Fatai; Abdulraheem, Abdulazeez

2014-03-01

Soft computing techniques are recently becoming very popular in the oil industry. A number of computational intelligence-based predictive methods have been widely applied in the industry with high prediction capabilities. Some of the popular methods include feed-forward neural networks, radial basis function network, generalized regression neural network, functional networks, support vector regression and adaptive network fuzzy inference system. A comparative study among most popular soft computing techniques is presented using a large dataset published in literature describing multimodal pore systems in the Arab D formation. The inputs to the models are air porosity, grain density, and Thomeer parameters obtained using mercury injection capillary pressure profiles. Corrected air permeability is the target variable. Applying developed permeability models in recent reservoir characterization workflow ensures consistency between micro and macro scale information represented mainly by Thomeer parameters and absolute permeability. The dataset was divided into two parts with 80% of data used for training and 20% for testing. The target permeability variable was transformed to the logarithmic scale as a pre-processing step and to show better correlations with the input variables. Statistical and graphical analysis of the results including permeability cross-plots and detailed error measures were created. In general, the comparative study showed very close results among the developed models. The feed-forward neural network permeability model showed the lowest average relative error, average absolute relative error, standard deviations of error and root means squares making it the best model for such problems. Adaptive network fuzzy inference system also showed very good results.

Error-Trellis Construction for Convolutional Codes Using Shifted Error/Syndrome-Subsequences

NASA Astrophysics Data System (ADS)

Tajima, Masato; Okino, Koji; Miyagoshi, Takashi

In this paper, we extend the conventional error-trellis construction for convolutional codes to the case where a given check matrix H(D) has a factor Dl in some column (row). In the first case, there is a possibility that the size of the state space can be reduced using shifted error-subsequences, whereas in the second case, the size of the state space can be reduced using shifted syndrome-subsequences. The construction presented in this paper is based on the adjoint-obvious realization of the corresponding syndrome former HT(D). In the case where all the columns and rows of H(D) are delay free, the proposed construction is reduced to the conventional one of Schalkwijk et al. We also show that the proposed construction can equally realize the state-space reduction shown by Ariel et al. Moreover, we clarify the difference between their construction and that of ours using examples.

Noise-enhanced convolutional neural networks.

PubMed

Audhkhasi, Kartik; Osoba, Osonde; Kosko, Bart

2016-06-01

Injecting carefully chosen noise can speed convergence in the backpropagation training of a convolutional neural network (CNN). The Noisy CNN algorithm speeds training on average because the backpropagation algorithm is a special case of the generalized expectation-maximization (EM) algorithm and because such carefully chosen noise always speeds up the EM algorithm on average. The CNN framework gives a practical way to learn and recognize images because backpropagation scales with training data. It has only linear time complexity in the number of training samples. The Noisy CNN algorithm finds a special separating hyperplane in the network's noise space. The hyperplane arises from the likelihood-based positivity condition that noise-boosts the EM algorithm. The hyperplane cuts through a uniform-noise hypercube or Gaussian ball in the noise space depending on the type of noise used. Noise chosen from above the hyperplane speeds training on average. Noise chosen from below slows it on average. The algorithm can inject noise anywhere in the multilayered network. Adding noise to the output neurons reduced the average per-iteration training-set cross entropy by 39% on a standard MNIST image test set of handwritten digits. It also reduced the average per-iteration training-set classification error by 47%. Adding noise to the hidden layers can also reduce these performance measures. The noise benefit is most pronounced for smaller data sets because the largest EM hill-climbing gains tend to occur in the first few iterations. This noise effect can assist random sampling from large data sets because it allows a smaller random sample to give the same or better performance than a noiseless sample gives. Copyright © 2015 Elsevier Ltd. All rights reserved.

Offline signature verification using convolution Siamese network

NASA Astrophysics Data System (ADS)

Xing, Zi-Jian; Yin, Fei; Wu, Yi-Chao; Liu, Cheng-Lin

2018-04-01

This paper presents an offline signature verification approach using convolutional Siamese neural network. Unlike the existing methods which consider feature extraction and metric learning as two independent stages, we adopt a deepleaning based framework which combines the two stages together and can be trained end-to-end. The experimental results on two offline public databases (GPDSsynthetic and CEDAR) demonstrate the superiority of our method on the offline signature verification problem.

Sculpting the UMLS Refined Semantic Network.

PubMed

He, Zhe; Morrey, C Paul; Perl, Yehoshua; Elhanan, Gai; Chen, Ling; Chen, Yan; Geller, James

2014-01-01

The Refined Semantic Network (RSN) for the UMLS was previously introduced to complement the UMLS Semantic Network (SN). The RSN partitions the UMLS Metathesaurus (META) into disjoint groups of concepts. Each such group is semantically uniform. However, the RSN was initially an order of magnitude larger than the SN, which is undesirable since to be useful, a semantic network should be compact. Most semantic types in the RSN represent combinations of semantic types in the UMLS SN. Such a "combination semantic type" is called Intersection Semantic Type (IST). Many ISTs are assigned to very few concepts. Moreover, when reviewing those concepts, many semantic type assignment inconsistencies were found. After correcting those inconsistencies many ISTs, among them some that contradicted UMLS rules, disappeared, which made the RSN smaller. The authors performed a longitudinal study with the goal of reducing the size of the RSN to become compact. This goal was achieved by correcting inconsistencies and errors in the IST assignments in the UMLS, which additionally helped identify and correct ambiguities, inconsistencies, and errors in source terminologies widely used in the realm of public health. In this paper, we discuss the process and steps employed in this longitudinal study and the intermediate results for different stages. The sculpting process includes removing redundant semantic type assignments, expanding semantic type assignments, and removing illegitimate ISTs by auditing ISTs of small extents. However, the emphasis of this paper is not on the auditing methodologies employed during the process, since they were introduced in earlier publications, but on the strategy of employing them in order to transform the RSN into a compact network. For this paper we also performed a comprehensive audit of 168 "small ISTs" in the 2013AA version of the UMLS to finalize the longitudinal study. Over the years it was found that the editors of the UMLS introduced some new inconsistencies that resulted in the reintroduction of unwarranted ISTs that had already been eliminated as a result of their previous corrections. Because of that, the transformation of the RSN into a compact network covering all necessary categories for the UMLS was slowed down. The corrections suggested by an audit of the 2013AA version of the UMLS achieve a compact RSN of equal magnitude as the UMLS SN. The number of ISTs has been reduced to 336. We also demonstrate how auditing the semantic type assignments of UMLS concepts can expose other modeling errors in the UMLS source terminologies, e.g., SNOMED CT, LOINC, and RxNORM that are important for health informatics. Such errors would otherwise stay hidden. It is hoped that the UMLS curators will implement all required corrections and use the RSN along with the SN when maintaining and extending the UMLS. When used correctly, the RSN will support the prevention of the accidental introduction of inconsistent semantic type assignments into the UMLS. Furthermore, this way the RSN will support the exposure of other hidden errors and inconsistencies in health informatics terminologies, which are sources of the UMLS. Notably, the development of the RSN materializes the deeper, more refined Semantic Network for the UMLS that its designers envisioned originally but had not implemented.

Phylogenetic convolutional neural networks in metagenomics.

PubMed

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

2018-03-08

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

Image quality assessment using deep convolutional networks

NASA Astrophysics Data System (ADS)

Li, Yezhou; Ye, Xiang; Li, Yong

2017-12-01

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

Towards dropout training for convolutional neural networks.

PubMed

Wu, Haibing; Gu, Xiaodong

2015-11-01

Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in convolutional and pooling layers is still not clear. This paper demonstrates that max-pooling dropout is equivalent to randomly picking activation based on a multinomial distribution at training time. In light of this insight, we advocate employing our proposed probabilistic weighted pooling, instead of commonly used max-pooling, to act as model averaging at test time. Empirical evidence validates the superiority of probabilistic weighted pooling. We also empirically show that the effect of convolutional dropout is not trivial, despite the dramatically reduced possibility of over-fitting due to the convolutional architecture. Elaborately designing dropout training simultaneously in max-pooling and fully-connected layers, we achieve state-of-the-art performance on MNIST, and very competitive results on CIFAR-10 and CIFAR-100, relative to other approaches without data augmentation. Finally, we compare max-pooling dropout and stochastic pooling, both of which introduce stochasticity based on multinomial distributions at pooling stage. Copyright © 2015 Elsevier Ltd. All rights reserved.

Performance enhancement of wireless mobile adhoc networks through improved error correction and ICI cancellation

NASA Astrophysics Data System (ADS)

Sabir, Zeeshan; Babar, M. Inayatullah; Shah, Syed Waqar

2012-12-01

Mobile adhoc network (MANET) refers to an arrangement of wireless mobile nodes that have the tendency of dynamically and freely self-organizing into temporary and arbitrary network topologies. Orthogonal frequency division multiplexing (OFDM) is the foremost choice for MANET system designers at the Physical Layer due to its inherent property of high data rate transmission that corresponds to its lofty spectrum efficiency. The downside of OFDM includes its sensitivity to synchronization errors (frequency offsets and symbol time). Most of the present day techniques employing OFDM for data transmission support mobility as one of the primary features. This mobility causes small frequency offsets due to the production of Doppler frequencies. It results in intercarrier interference (ICI) which degrades the signal quality due to a crosstalk between the subcarriers of OFDM symbol. An efficient frequency-domain block-type pilot-assisted ICI mitigation scheme is proposed in this article which nullifies the effect of channel frequency offsets from the received OFDM symbols. Second problem addressed in this article is the noise effect induced by different sources into the received symbol increasing its bit error rate and making it unsuitable for many applications. Forward-error-correcting turbo codes have been employed into the proposed model which adds redundant bits into the system which are later used for error detection and correction purpose. At the receiver end, maximum a posteriori (MAP) decoding algorithm is implemented using two component MAP decoders. These decoders tend to exchange interleaved extrinsic soft information among each other in the form of log likelihood ratio improving the previous estimate regarding the decoded bit in each iteration.

Automatic QRS complex detection using two-level convolutional neural network.

PubMed

Xiang, Yande; Lin, Zhitao; Meng, Jianyi

2018-01-29

The QRS complex is the most noticeable feature in the electrocardiogram (ECG) signal, therefore, its detection is critical for ECG signal analysis. The existing detection methods largely depend on hand-crafted manual features and parameters, which may introduce significant computational complexity, especially in the transform domains. In addition, fixed features and parameters are not suitable for detecting various kinds of QRS complexes under different circumstances. In this study, based on 1-D convolutional neural network (CNN), an accurate method for QRS complex detection is proposed. The CNN consists of object-level and part-level CNNs for extracting different grained ECG morphological features automatically. All the extracted morphological features are used by multi-layer perceptron (MLP) for QRS complex detection. Additionally, a simple ECG signal preprocessing technique which only contains difference operation in temporal domain is adopted. Based on the MIT-BIH arrhythmia (MIT-BIH-AR) database, the proposed detection method achieves overall sensitivity Sen = 99.77%, positive predictivity rate PPR = 99.91%, and detection error rate DER = 0.32%. In addition, the performance variation is performed according to different signal-to-noise ratio (SNR) values. An automatic QRS detection method using two-level 1-D CNN and simple signal preprocessing technique is proposed for QRS complex detection. Compared with the state-of-the-art QRS complex detection approaches, experimental results show that the proposed method acquires comparable accuracy.

A convolutional neural network-based screening tool for X-ray serial crystallography

PubMed Central

Ke, Tsung-Wei; Brewster, Aaron S.; Yu, Stella X.; Ushizima, Daniela; Yang, Chao; Sauter, Nicholas K.

2018-01-01

A new tool is introduced for screening macromolecular X-ray crystallography diffraction images produced at an X-ray free-electron laser light source. Based on a data-driven deep learning approach, the proposed tool executes a convolutional neural network to detect Bragg spots. Automatic image processing algorithms described can enable the classification of large data sets, acquired under realistic conditions consisting of noisy data with experimental artifacts. Outcomes are compared for different data regimes, including samples from multiple instruments and differing amounts of training data for neural network optimization. PMID:29714177

A convolutional neural network-based screening tool for X-ray serial crystallography.

PubMed

Ke, Tsung Wei; Brewster, Aaron S; Yu, Stella X; Ushizima, Daniela; Yang, Chao; Sauter, Nicholas K

2018-05-01

A new tool is introduced for screening macromolecular X-ray crystallography diffraction images produced at an X-ray free-electron laser light source. Based on a data-driven deep learning approach, the proposed tool executes a convolutional neural network to detect Bragg spots. Automatic image processing algorithms described can enable the classification of large data sets, acquired under realistic conditions consisting of noisy data with experimental artifacts. Outcomes are compared for different data regimes, including samples from multiple instruments and differing amounts of training data for neural network optimization. open access.

A convolutional neural network-based screening tool for X-ray serial crystallography

DOE PAGES

Ke, Tsung-Wei; Brewster, Aaron S.; Yu, Stella X.; ...

2018-04-24

A new tool is introduced for screening macromolecular X-ray crystallography diffraction images produced at an X-ray free-electron laser light source. Based on a data-driven deep learning approach, the proposed tool executes a convolutional neural network to detect Bragg spots. Automatic image processing algorithms described can enable the classification of large data sets, acquired under realistic conditions consisting of noisy data with experimental artifacts. Outcomes are compared for different data regimes, including samples from multiple instruments and differing amounts of training data for neural network optimization.

A convolutional neural network-based screening tool for X-ray serial crystallography

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ke, Tsung-Wei; Brewster, Aaron S.; Yu, Stella X.

A new tool is introduced for screening macromolecular X-ray crystallography diffraction images produced at an X-ray free-electron laser light source. Based on a data-driven deep learning approach, the proposed tool executes a convolutional neural network to detect Bragg spots. Automatic image processing algorithms described can enable the classification of large data sets, acquired under realistic conditions consisting of noisy data with experimental artifacts. Outcomes are compared for different data regimes, including samples from multiple instruments and differing amounts of training data for neural network optimization.

Detection of bars in galaxies using a deep convolutional neural network

NASA Astrophysics Data System (ADS)

Abraham, Sheelu; Aniyan, A. K.; Kembhavi, Ajit K.; Philip, N. S.; Vaghmare, Kaustubh

2018-06-01

We present an automated method for the detection of bar structure in optical images of galaxies using a deep convolutional neural network that is easy to use and provides good accuracy. In our study, we use a sample of 9346 galaxies in the redshift range of 0.009-0.2 from the Sloan Digital Sky Survey (SDSS), which has 3864 barred galaxies, the rest being unbarred. We reach a top precision of 94 per cent in identifying bars in galaxies using the trained network. This accuracy matches the accuracy reached by human experts on the same data without additional information about the images. Since deep convolutional neural networks can be scaled to handle large volumes of data, the method is expected to have great relevance in an era where astronomy data is rapidly increasing in terms of volume, variety, volatility, and velocity along with other V's that characterize big data. With the trained model, we have constructed a catalogue of barred galaxies from SDSS and made it available online.

A light and faster regional convolutional neural network for object detection in optical remote sensing images

NASA Astrophysics Data System (ADS)

Ding, Peng; Zhang, Ye; Deng, Wei-Jian; Jia, Ping; Kuijper, Arjan

2018-07-01

Detection of objects from satellite optical remote sensing images is very important for many commercial and governmental applications. With the development of deep convolutional neural networks (deep CNNs), the field of object detection has seen tremendous advances. Currently, objects in satellite remote sensing images can be detected using deep CNNs. In general, optical remote sensing images contain many dense and small objects, and the use of the original Faster Regional CNN framework does not yield a suitably high precision. Therefore, after careful analysis we adopt dense convoluted networks, a multi-scale representation and various combinations of improvement schemes to enhance the structure of the base VGG16-Net for improving the precision. We propose an approach to reduce the test-time (detection time) and memory requirements. To validate the effectiveness of our approach, we perform experiments using satellite remote sensing image datasets of aircraft and automobiles. The results show that the improved network structure can detect objects in satellite optical remote sensing images more accurately and efficiently.

Improving deep convolutional neural networks with mixed maxout units

PubMed Central

Liu, Fu-xian; Li, Long-yue

2017-01-01

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. PMID:28727737

Concatenated coding systems employing a unit-memory convolutional code and a byte-oriented decoding algorithm

NASA Technical Reports Server (NTRS)

Lee, L.-N.

1977-01-01

Concatenated coding systems utilizing a convolutional code as the inner code and a Reed-Solomon code as the outer code are considered. In order to obtain very reliable communications over a very noisy channel with relatively modest coding complexity, it is proposed to concatenate a byte-oriented unit-memory convolutional code with an RS outer code whose symbol size is one byte. It is further proposed to utilize a real-time minimal-byte-error probability decoding algorithm, together with feedback from the outer decoder, in the decoder for the inner convolutional code. The performance of the proposed concatenated coding system is studied, and the improvement over conventional concatenated systems due to each additional feature is isolated.

Concatenated coding systems employing a unit-memory convolutional code and a byte-oriented decoding algorithm

NASA Technical Reports Server (NTRS)

Lee, L. N.

1976-01-01

Concatenated coding systems utilizing a convolutional code as the inner code and a Reed-Solomon code as the outer code are considered. In order to obtain very reliable communications over a very noisy channel with relatively small coding complexity, it is proposed to concatenate a byte oriented unit memory convolutional code with an RS outer code whose symbol size is one byte. It is further proposed to utilize a real time minimal byte error probability decoding algorithm, together with feedback from the outer decoder, in the decoder for the inner convolutional code. The performance of the proposed concatenated coding system is studied, and the improvement over conventional concatenated systems due to each additional feature is isolated.

Convolutional networks for vehicle track segmentation

DOE PAGES

Quach, Tu-Thach

2017-08-19

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, 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-by-3 convolutions to segment vehicle tracks. The design of our networks considers the fact that remote sensing applications tend to operate inmore » low power and have limited training data. As a result, we aim for small, efficient networks that can be trained end-to-end to learn natural track features entirely from limited training data. We demonstrate that our 6-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.« less

Convolutional networks for vehicle track segmentation

DOE Office of Scientific and Technical Information (OSTI.GOV)

Quach, Tu-Thach

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, 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-by-3 convolutions to segment vehicle tracks. The design of our networks considers the fact that remote sensing applications tend to operate inmore » low power and have limited training data. As a result, we aim for small, efficient networks that can be trained end-to-end to learn natural track features entirely from limited training data. We demonstrate that our 6-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.« less

A fusion network for semantic segmentation using RGB-D data

NASA Astrophysics Data System (ADS)

Yuan, Jiahui; Zhang, Kun; Xia, Yifan; Qi, Lin; Dong, Junyu

2018-04-01

Semantic scene parsing is considerable in many intelligent field, including perceptual robotics. For the past few years, pixel-wise prediction tasks like semantic segmentation with RGB images has been extensively studied and has reached very remarkable parsing levels, thanks to convolutional neural networks (CNNs) and large scene datasets. With the development of stereo cameras and RGBD sensors, it is expected that additional depth information will help improving accuracy. In this paper, we propose a semantic segmentation framework incorporating RGB and complementary depth information. Motivated by the success of fully convolutional networks (FCN) in semantic segmentation field, we design a fully convolutional networks consists of two branches which extract features from both RGB and depth data simultaneously and fuse them as the network goes deeper. Instead of aggregating multiple model, our goal is to utilize RGB data and depth data more effectively in a single model. We evaluate our approach on the NYU-Depth V2 dataset, which consists of 1449 cluttered indoor scenes, and achieve competitive results with the state-of-the-art methods.

Parameter diagnostics of phases and phase transition learning by neural networks

NASA Astrophysics Data System (ADS)

Suchsland, Philippe; Wessel, Stefan

2018-05-01

We present an analysis of neural network-based machine learning schemes for phases and phase transitions in theoretical condensed matter research, focusing on neural networks with a single hidden layer. Such shallow neural networks were previously found to be efficient in classifying phases and locating phase transitions of various basic model systems. In order to rationalize the emergence of the classification process and for identifying any underlying physical quantities, it is feasible to examine the weight matrices and the convolutional filter kernels that result from the learning process of such shallow networks. Furthermore, we demonstrate how the learning-by-confusing scheme can be used, in combination with a simple threshold-value classification method, to diagnose the learning parameters of neural networks. In particular, we study the classification process of both fully-connected and convolutional neural networks for the two-dimensional Ising model with extended domain wall configurations included in the low-temperature regime. Moreover, we consider the two-dimensional XY model and contrast the performance of the learning-by-confusing scheme and convolutional neural networks trained on bare spin configurations to the case of preprocessed samples with respect to vortex configurations. We discuss these findings in relation to similar recent investigations and possible further applications.

Apply network coding for H.264/SVC multicasting

NASA Astrophysics Data System (ADS)

Wang, Hui; Kuo, C.-C. Jay

2008-08-01

In a packet erasure network environment, video streaming benefits from error control in two ways to achieve graceful degradation. The first approach is application-level (or the link-level) forward error-correction (FEC) to provide erasure protection. The second error control approach is error concealment at the decoder end to compensate lost packets. A large amount of research work has been done in the above two areas. More recently, network coding (NC) techniques have been proposed for efficient data multicast over networks. It was shown in our previous work that multicast video streaming benefits from NC for its throughput improvement. An algebraic model is given to analyze the performance in this work. By exploiting the linear combination of video packets along nodes in a network and the SVC video format, the system achieves path diversity automatically and enables efficient video delivery to heterogeneous receivers in packet erasure channels. The application of network coding can protect video packets against the erasure network environment. However, the rank defficiency problem of random linear network coding makes the error concealment inefficiently. It is shown by computer simulation that the proposed NC video multicast scheme enables heterogenous receiving according to their capacity constraints. But it needs special designing to improve the video transmission performance when applying network coding.

Neural network approach to proximity effect corrections in electron-beam lithography

NASA Astrophysics Data System (ADS)

Frye, Robert C.; Cummings, Kevin D.; Rietman, Edward A.

1990-05-01

The proximity effect, caused by electron beam backscattering during resist exposure, is an important concern in writing submicron features. It can be compensated by appropriate local changes in the incident beam dose, but computation of the optimal correction usually requires a prohibitively long time. We present an example of such a computation on a small test pattern, which we performed by an iterative method. We then used this solution as a training set for an adaptive neural network. After training, the network computed the same correction as the iterative method, but in a much shorter time. Correcting the image with a software based neural network resulted in a decrease in the computation time by a factor of 30, and a hardware based network enhanced the computation speed by more than a factor of 1000. Both methods had an acceptably small error of 0.5% compared to the results of the iterative computation. Additionally, we verified that the neural network correctly generalized the solution of the problem to include patterns not contained in its training set.

Performance of DPSK with convolutional encoding on time-varying fading channels

NASA Technical Reports Server (NTRS)

Mui, S. Y.; Modestino, J. W.

1977-01-01

The bit error probability performance of a differentially-coherent phase-shift keyed (DPSK) modem with convolutional encoding and Viterbi decoding on time-varying fading channels is examined. Both the Rician and the lognormal channels are considered. Bit error probability upper bounds on fully-interleaved (zero-memory) fading channels are derived and substantiated by computer simulation. It is shown that the resulting coded system performance is a relatively insensitive function of the choice of channel model provided that the channel parameters are related according to the correspondence developed as part of this paper. Finally, a comparison of DPSK with a number of other modulation strategies is provided.

Deep convolutional neural networks for estimating porous material parameters with ultrasound tomography

NASA Astrophysics Data System (ADS)

Lähivaara, Timo; Kärkkäinen, Leo; Huttunen, Janne M. J.; Hesthaven, Jan S.

2018-02-01

We study the feasibility of data based machine learning applied to ultrasound tomography to estimate water-saturated porous material parameters. In this work, the data to train the neural networks is simulated by solving wave propagation in coupled poroviscoelastic-viscoelastic-acoustic media. As the forward model, we consider a high-order discontinuous Galerkin method while deep convolutional neural networks are used to solve the parameter estimation problem. In the numerical experiment, we estimate the material porosity and tortuosity while the remaining parameters which are of less interest are successfully marginalized in the neural networks-based inversion. Computational examples confirms the feasibility and accuracy of this approach.

Convolutional Neural Networks for 1-D Many-Channel Data

DTIC Science & Technology

Deep convolutional neural networks (CNNs) represent the state of the art in image recognition. The same properties that led to their success in that... crack detection ( 8,000 data points, 72 channels). Though the models predictive ability is limited to fitting the trend , its partial success suggests that...originally written to classify digits in the MNIST database (28 28 pixels, 1 channel), for use on 1-D acoustic data taken from experiments focused on

Mapping and correction of the CMM workspace error with the use of an electronic gyroscope and neural networks--practical application.

PubMed

Swornowski, Pawel J

2013-01-01

The article presents the application of neural networks in determining and correction of the deformation of a coordinate measuring machine (CMM) workspace. The information about the CMM errors is acquired using an ADXRS401 electronic gyroscope. A test device (PS-20 module) was built and integrated with a commercial measurement system based on the SP25M passive scanning probe and with a PH10M module (Renishaw). The proposed solution was tested on a Kemco 600 CMM and on a DEA Global Clima CMM. In the former case, correction of the CMM errors was performed using the source code of WinIOS software owned by The Institute of Advanced Manufacturing Technology, Cracow, Poland and in the latter on an external PC. Optimum parameters of full and simplified mapping of a given layer of the CMM workspace were determined for practical applications. The proposed method can be employed for the interim check (ISO 10360-2 procedure) or to detect local CMM deformations, occurring when the CMM works at high scanning speeds (>20 mm/s). © Wiley Periodicals, Inc.

LFNet: A Novel Bidirectional Recurrent Convolutional Neural Network for Light-Field Image Super-Resolution.

PubMed

Wang, Yunlong; Liu, Fei; Zhang, Kunbo; Hou, Guangqi; Sun, Zhenan; Tan, Tieniu

2018-09-01

The low spatial resolution of light-field image poses significant difficulties in exploiting its advantage. To mitigate the dependency of accurate depth or disparity information as priors for light-field image super-resolution, we propose an implicitly multi-scale fusion scheme to accumulate contextual information from multiple scales for super-resolution reconstruction. The implicitly multi-scale fusion scheme is then incorporated into bidirectional recurrent convolutional neural network, which aims to iteratively model spatial relations between horizontally or vertically adjacent sub-aperture images of light-field data. Within the network, the recurrent convolutions are modified to be more effective and flexible in modeling the spatial correlations between neighboring views. A horizontal sub-network and a vertical sub-network of the same network structure are ensembled for final outputs via stacked generalization. Experimental results on synthetic and real-world data sets demonstrate that the proposed method outperforms other state-of-the-art methods by a large margin in peak signal-to-noise ratio and gray-scale structural similarity indexes, which also achieves superior quality for human visual systems. Furthermore, the proposed method can enhance the performance of light field applications such as depth estimation.

Splenomegaly Segmentation using Global Convolutional Kernels and Conditional Generative Adversarial Networks

PubMed Central

Huo, Yuankai; Xu, Zhoubing; Bao, Shunxing; Bermudez, Camilo; Plassard, Andrew J.; Liu, Jiaqi; Yao, Yuang; Assad, Albert; Abramson, Richard G.; Landman, Bennett A.

2018-01-01

Spleen volume estimation using automated image segmentation technique may be used to detect splenomegaly (abnormally enlarged spleen) on Magnetic Resonance Imaging (MRI) scans. In recent years, Deep Convolutional Neural Networks (DCNN) segmentation methods have demonstrated advantages for abdominal organ segmentation. However, variations in both size and shape of the spleen on MRI images may result in large false positive and false negative labeling when deploying DCNN based methods. In this paper, we propose the Splenomegaly Segmentation Network (SSNet) to address spatial variations when segmenting extraordinarily large spleens. SSNet was designed based on the framework of image-to-image conditional generative adversarial networks (cGAN). Specifically, the Global Convolutional Network (GCN) was used as the generator to reduce false negatives, while the Markovian discriminator (PatchGAN) was used to alleviate false positives. A cohort of clinically acquired 3D MRI scans (both T1 weighted and T2 weighted) from patients with splenomegaly were used to train and test the networks. The experimental results demonstrated that a mean Dice coefficient of 0.9260 and a median Dice coefficient of 0.9262 using SSNet on independently tested MRI volumes of patients with splenomegaly.

Alexnet Feature Extraction and Multi-Kernel Learning for Objectoriented Classification

NASA Astrophysics Data System (ADS)

Ding, L.; Li, H.; Hu, C.; Zhang, W.; Wang, S.

2018-04-01

In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation.

Optimized color decomposition of localized whole slide images and convolutional neural network for intermediate prostate cancer classification

NASA Astrophysics Data System (ADS)

Zhou, Naiyun; Gao, Yi

2017-03-01

This paper presents a fully automatic approach to grade intermediate prostate malignancy with hematoxylin and eosin-stained whole slide images. Deep learning architectures such as convolutional neural networks have been utilized in the domain of histopathology for automated carcinoma detection and classification. However, few work show its power in discriminating intermediate Gleason patterns, due to sporadic distribution of prostate glands on stained surgical section samples. We propose optimized hematoxylin decomposition on localized images, followed by convolutional neural network to classify Gleason patterns 3+4 and 4+3 without handcrafted features or gland segmentation. Crucial glands morphology and structural relationship of nuclei are extracted twice in different color space by the multi-scale strategy to mimic pathologists' visual examination. Our novel classification scheme evaluated on 169 whole slide images yielded a 70.41% accuracy and corresponding area under the receiver operating characteristic curve of 0.7247.

Clinical Assistant Diagnosis for Electronic Medical Record Based on Convolutional Neural Network.

PubMed

Yang, Zhongliang; Huang, Yongfeng; Jiang, Yiran; Sun, Yuxi; Zhang, Yu-Jin; Luo, Pengcheng

2018-04-20

Automatically extracting useful information from electronic medical records along with conducting disease diagnoses is a promising task for both clinical decision support(CDS) and neural language processing(NLP). Most of the existing systems are based on artificially constructed knowledge bases, and then auxiliary diagnosis is done by rule matching. In this study, we present a clinical intelligent decision approach based on Convolutional Neural Networks(CNN), which can automatically extract high-level semantic information of electronic medical records and then perform automatic diagnosis without artificial construction of rules or knowledge bases. We use collected 18,590 copies of the real-world clinical electronic medical records to train and test the proposed model. Experimental results show that the proposed model can achieve 98.67% accuracy and 96.02% recall, which strongly supports that using convolutional neural network to automatically learn high-level semantic features of electronic medical records and then conduct assist diagnosis is feasible and effective.

An Ensemble Deep Convolutional Neural Network Model with Improved D-S Evidence Fusion for Bearing Fault Diagnosis.

PubMed

Li, Shaobo; Liu, Guokai; Tang, Xianghong; Lu, Jianguang; Hu, Jianjun

2017-07-28

Intelligent machine health monitoring and fault diagnosis are becoming increasingly important for modern manufacturing industries. Current fault diagnosis approaches mostly depend on expert-designed features for building prediction models. In this paper, we proposed IDSCNN, a novel bearing fault diagnosis algorithm based on ensemble deep convolutional neural networks and an improved Dempster-Shafer theory based evidence fusion. The convolutional neural networks take the root mean square (RMS) maps from the FFT (Fast Fourier Transformation) features of the vibration signals from two sensors as inputs. The improved D-S evidence theory is implemented via distance matrix from evidences and modified Gini Index. Extensive evaluations of the IDSCNN on the Case Western Reserve Dataset showed that our IDSCNN algorithm can achieve better fault diagnosis performance than existing machine learning methods by fusing complementary or conflicting evidences from different models and sensors and adapting to different load conditions.

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

PubMed

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

2017-09-27

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

Chemical-induced disease relation extraction via convolutional neural network.

PubMed

Gu, Jinghang; Sun, Fuqing; Qian, Longhua; Zhou, Guodong

2017-01-01

This article describes our work on the BioCreative-V chemical-disease relation (CDR) extraction task, which employed a maximum entropy (ME) model and a convolutional neural network model for relation extraction at inter- and intra-sentence level, respectively. In our work, relation extraction between entity concepts in documents was simplified to relation extraction between entity mentions. We first constructed pairs of chemical and disease mentions as relation instances for training and testing stages, then we trained and applied the ME model and the convolutional neural network model for inter- and intra-sentence level, respectively. Finally, we merged the classification results from mention level to document level to acquire the final relations between chemical and disease concepts. The evaluation on the BioCreative-V CDR corpus shows the effectiveness of our proposed approach. http://www.biocreative.org/resources/corpora/biocreative-v-cdr-corpus/. © The Author(s) 2017. Published by Oxford University Press.

An Ensemble Deep Convolutional Neural Network Model with Improved D-S Evidence Fusion for Bearing Fault Diagnosis

PubMed Central

Li, Shaobo; Liu, Guokai; Tang, Xianghong; Lu, Jianguang

2017-01-01

Intelligent machine health monitoring and fault diagnosis are becoming increasingly important for modern manufacturing industries. Current fault diagnosis approaches mostly depend on expert-designed features for building prediction models. In this paper, we proposed IDSCNN, a novel bearing fault diagnosis algorithm based on ensemble deep convolutional neural networks and an improved Dempster–Shafer theory based evidence fusion. The convolutional neural networks take the root mean square (RMS) maps from the FFT (Fast Fourier Transformation) features of the vibration signals from two sensors as inputs. The improved D-S evidence theory is implemented via distance matrix from evidences and modified Gini Index. Extensive evaluations of the IDSCNN on the Case Western Reserve Dataset showed that our IDSCNN algorithm can achieve better fault diagnosis performance than existing machine learning methods by fusing complementary or conflicting evidences from different models and sensors and adapting to different load conditions. PMID:28788099

Deep Convolutional Neural Networks for Classifying Body Constitution Based on Face Image.

PubMed

Huan, Er-Yang; Wen, Gui-Hua; Zhang, Shi-Jun; Li, Dan-Yang; Hu, Yang; Chang, Tian-Yuan; Wang, Qing; Huang, Bing-Lin

2017-01-01

Body constitution classification is the basis and core content of traditional Chinese medicine constitution research. It is to extract the relevant laws from the complex constitution phenomenon and finally build the constitution classification system. Traditional identification methods have the disadvantages of inefficiency and low accuracy, for instance, questionnaires. This paper proposed a body constitution recognition algorithm based on deep convolutional neural network, which can classify individual constitution types according to face images. The proposed model first uses the convolutional neural network to extract the features of face image and then combines the extracted features with the color features. Finally, the fusion features are input to the Softmax classifier to get the classification result. Different comparison experiments show that the algorithm proposed in this paper can achieve the accuracy of 65.29% about the constitution classification. And its performance was accepted by Chinese medicine practitioners.

Analysis of the error of the developed method of determination the active conductivity reducing the insulation level between one phase of the network and ground, and insulation parameters in a non-symmetric network with isolated neutral with voltage above 1000 V

NASA Astrophysics Data System (ADS)

Utegulov, B. B.

2018-02-01

In the work the study of the developed method was carried out for reliability by analyzing the error in indirect determination of the insulation parameters in an asymmetric network with an isolated neutral voltage above 1000 V. The conducted studies of the random relative mean square errors show that the accuracy of indirect measurements in the developed method can be effectively regulated not only by selecting a capacitive additional conductivity, which are connected between phases of the electrical network and the ground, but also by the selection of measuring instruments according to the accuracy class. When choosing meters with accuracy class of 0.5 with the correct selection of capacitive additional conductivity that are connected between the phases of the electrical network and the ground, the errors in measuring the insulation parameters will not exceed 10%.

IMU-Based Gait Recognition Using Convolutional Neural Networks and Multi-Sensor Fusion.

PubMed

Dehzangi, Omid; Taherisadr, Mojtaba; ChangalVala, Raghvendar

2017-11-27

The wide spread usage of wearable sensors such as in smart watches has provided continuous access to valuable user generated data such as human motion that could be used to identify an individual based on his/her motion patterns such as, gait. Several methods have been suggested to extract various heuristic and high-level features from gait motion data to identify discriminative gait signatures and distinguish the target individual from others. However, the manual and hand crafted feature extraction is error prone and subjective. Furthermore, the motion data collected from inertial sensors have complex structure and the detachment between manual feature extraction module and the predictive learning models might limit the generalization capabilities. In this paper, we propose a novel approach for human gait identification using time-frequency (TF) expansion of human gait cycles in order to capture joint 2 dimensional (2D) spectral and temporal patterns of gait cycles. Then, we design a deep convolutional neural network (DCNN) learning to extract discriminative features from the 2D expanded gait cycles and jointly optimize the identification model and the spectro-temporal features in a discriminative fashion. We collect raw motion data from five inertial sensors placed at the chest, lower-back, right hand wrist, right knee, and right ankle of each human subject synchronously in order to investigate the impact of sensor location on the gait identification performance. We then present two methods for early (input level) and late (decision score level) multi-sensor fusion to improve the gait identification generalization performance. We specifically propose the minimum error score fusion (MESF) method that discriminatively learns the linear fusion weights of individual DCNN scores at the decision level by minimizing the error rate on the training data in an iterative manner. 10 subjects participated in this study and hence, the problem is a 10-class identification task. Based on our experimental results, 91% subject identification accuracy was achieved using the best individual IMU and 2DTF-DCNN. We then investigated our proposed early and late sensor fusion approaches, which improved the gait identification accuracy of the system to 93.36% and 97.06%, respectively.

Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands

PubMed Central

Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

2016-01-01

Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too. PMID:27656140

Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands.

PubMed

Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

2016-01-01

Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too.

Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing

DOE PAGES

Perreault Levasseur, Laurence; Hezaveh, Yashar D.; Wechsler, Risa H.

2017-11-15

In Hezaveh et al. (2017) we showed that deep learning can be used for model parameter estimation and trained convolutional neural networks to determine the parameters of strong gravitational lensing systems. Here we demonstrate a method for obtaining the uncertainties of these parameters. We review the framework of variational inference to obtain approximate posteriors of Bayesian neural networks and apply it to a network trained to estimate the parameters of the Singular Isothermal Ellipsoid plus external shear and total flux magnification. We show that the method can capture the uncertainties due to different levels of noise in the input data,more » as well as training and architecture-related errors made by the network. To evaluate the accuracy of the resulting uncertainties, we calculate the coverage probabilities of marginalized distributions for each lensing parameter. By tuning a single hyperparameter, the dropout rate, we obtain coverage probabilities approximately equal to the confidence levels for which they were calculated, resulting in accurate and precise uncertainty estimates. Our results suggest that neural networks can be a fast alternative to Monte Carlo Markov Chains for parameter uncertainty estimation in many practical applications, allowing more than seven orders of magnitude improvement in speed.« less

Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing

NASA Astrophysics Data System (ADS)

Perreault Levasseur, Laurence; Hezaveh, Yashar D.; Wechsler, Risa H.

2017-11-01

In Hezaveh et al. we showed that deep learning can be used for model parameter estimation and trained convolutional neural networks to determine the parameters of strong gravitational-lensing systems. Here we demonstrate a method for obtaining the uncertainties of these parameters. We review the framework of variational inference to obtain approximate posteriors of Bayesian neural networks and apply it to a network trained to estimate the parameters of the Singular Isothermal Ellipsoid plus external shear and total flux magnification. We show that the method can capture the uncertainties due to different levels of noise in the input data, as well as training and architecture-related errors made by the network. To evaluate the accuracy of the resulting uncertainties, we calculate the coverage probabilities of marginalized distributions for each lensing parameter. By tuning a single variational parameter, the dropout rate, we obtain coverage probabilities approximately equal to the confidence levels for which they were calculated, resulting in accurate and precise uncertainty estimates. Our results suggest that the application of approximate Bayesian neural networks to astrophysical modeling problems can be a fast alternative to Monte Carlo Markov Chains, allowing orders of magnitude improvement in speed.

Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing

DOE Office of Scientific and Technical Information (OSTI.GOV)

Perreault Levasseur, Laurence; Hezaveh, Yashar D.; Wechsler, Risa H.

In Hezaveh et al. (2017) we showed that deep learning can be used for model parameter estimation and trained convolutional neural networks to determine the parameters of strong gravitational lensing systems. Here we demonstrate a method for obtaining the uncertainties of these parameters. We review the framework of variational inference to obtain approximate posteriors of Bayesian neural networks and apply it to a network trained to estimate the parameters of the Singular Isothermal Ellipsoid plus external shear and total flux magnification. We show that the method can capture the uncertainties due to different levels of noise in the input data,more » as well as training and architecture-related errors made by the network. To evaluate the accuracy of the resulting uncertainties, we calculate the coverage probabilities of marginalized distributions for each lensing parameter. By tuning a single hyperparameter, the dropout rate, we obtain coverage probabilities approximately equal to the confidence levels for which they were calculated, resulting in accurate and precise uncertainty estimates. Our results suggest that neural networks can be a fast alternative to Monte Carlo Markov Chains for parameter uncertainty estimation in many practical applications, allowing more than seven orders of magnitude improvement in speed.« less

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

PubMed

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

2017-06-01

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

Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using Deep Convolutional Neural Networks.

PubMed

López-Linares, Karen; Aranjuelo, Nerea; Kabongo, Luis; Maclair, Gregory; Lete, Nerea; Ceresa, Mario; García-Familiar, Ainhoa; Macía, Iván; González Ballester, Miguel A

2018-05-01

Computerized Tomography Angiography (CTA) based follow-up of Abdominal Aortic Aneurysms (AAA) treated with Endovascular Aneurysm Repair (EVAR) is essential to evaluate the progress of the patient and detect complications. In this context, accurate quantification of post-operative thrombus volume is required. However, a proper evaluation is hindered by the lack of automatic, robust and reproducible thrombus segmentation algorithms. We propose a new fully automatic approach based on Deep Convolutional Neural Networks (DCNN) for robust and reproducible thrombus region of interest detection and subsequent fine thrombus segmentation. The DetecNet detection network is adapted to perform region of interest extraction from a complete CTA and a new segmentation network architecture, based on Fully Convolutional Networks and a Holistically-Nested Edge Detection Network, is presented. These networks are trained, validated and tested in 13 post-operative CTA volumes of different patients using a 4-fold cross-validation approach to provide more robustness to the results. Our pipeline achieves a Dice score of more than 82% for post-operative thrombus segmentation and provides a mean relative volume difference between ground truth and automatic segmentation that lays within the experienced human observer variance without the need of human intervention in most common cases. Copyright © 2018 Elsevier B.V. All rights reserved.

Her2Net: A Deep Framework for Semantic Segmentation and Classification of Cell Membranes and Nuclei in Breast Cancer Evaluation.

PubMed

Saha, Monjoy; Chakraborty, Chandan

2018-05-01

We present an efficient deep learning framework for identifying, segmenting, and classifying cell membranes and nuclei from human epidermal growth factor receptor-2 (HER2)-stained breast cancer images with minimal user intervention. This is a long-standing issue for pathologists because the manual quantification of HER2 is error-prone, costly, and time-consuming. Hence, we propose a deep learning-based HER2 deep neural network (Her2Net) to solve this issue. The convolutional and deconvolutional parts of the proposed Her2Net framework consisted mainly of multiple convolution layers, max-pooling layers, spatial pyramid pooling layers, deconvolution layers, up-sampling layers, and trapezoidal long short-term memory (TLSTM). A fully connected layer and a softmax layer were also used for classification and error estimation. Finally, HER2 scores were calculated based on the classification results. The main contribution of our proposed Her2Net framework includes the implementation of TLSTM and a deep learning framework for cell membrane and nucleus detection, segmentation, and classification and HER2 scoring. Our proposed Her2Net achieved 96.64% precision, 96.79% recall, 96.71% F-score, 93.08% negative predictive value, 98.33% accuracy, and a 6.84% false-positive rate. Our results demonstrate the high accuracy and wide applicability of the proposed Her2Net in the context of HER2 scoring for breast cancer evaluation.

A spatial model for a stream networks of Citarik River with the environmental variables: potential of hydrogen (PH) and temperature

NASA Astrophysics Data System (ADS)

Bachrudin, A.; Mohamed, N. B.; Supian, S.; Sukono; Hidayat, Y.

2018-03-01

Application of existing geostatistical theory of stream networks provides a number of interesting and challenging problems. Most of statistical tools in the traditional geostatistics have been based on a Euclidean distance such as autocovariance functions, but for stream data is not permissible since it deals with a stream distance. To overcome this autocovariance developed a model based on the distance the flow with using convolution kernel approach (moving average construction). Spatial model for a stream networks is widely used to monitor environmental on a river networks. In a case study of a river in province of West Java, the objective of this paper is to analyze a capability of a predictive on two environmental variables, potential of hydrogen (PH) and temperature using ordinary kriging. Several the empirical results show: (1) The best fit of autocovariance functions for temperature and potential hydrogen (ph) of Citarik River is linear which also yields the smallest root mean squared prediction error (RMSPE), (2) the spatial correlation values between the locations on upstream and on downstream of Citarik river exhibit decreasingly

Automated Detection of Diabetic Retinopathy using Deep Learning.

PubMed

Lam, Carson; Yi, Darvin; Guo, Margaret; Lindsey, Tony

2018-01-01

Diabetic retinopathy is a leading cause of blindness among working-age adults. Early detection of this condition is critical for good prognosis. In this paper, we demonstrate the use of convolutional neural networks (CNNs) on color fundus images for the recognition task of diabetic retinopathy staging. Our network models achieved test metric performance comparable to baseline literature results, with validation sensitivity of 95%. We additionally explored multinomial classification models, and demonstrate that errors primarily occur in the misclassification of mild disease as normal due to the CNNs inability to detect subtle disease features. We discovered that preprocessing with contrast limited adaptive histogram equalization and ensuring dataset fidelity by expert verification of class labels improves recognition of subtle features. Transfer learning on pretrained GoogLeNet and AlexNet models from ImageNet improved peak test set accuracies to 74.5%, 68.8%, and 57.2% on 2-ary, 3-ary, and 4-ary classification models, respectively.

LDPC-PPM Coding Scheme for Optical Communication

NASA Technical Reports Server (NTRS)

Barsoum, Maged; Moision, Bruce; Divsalar, Dariush; Fitz, Michael

2009-01-01

In a proposed coding-and-modulation/demodulation-and-decoding scheme for a free-space optical communication system, an error-correcting code of the low-density parity-check (LDPC) type would be concatenated with a modulation code that consists of a mapping of bits to pulse-position-modulation (PPM) symbols. Hence, the scheme is denoted LDPC-PPM. This scheme could be considered a competitor of a related prior scheme in which an outer convolutional error-correcting code is concatenated with an interleaving operation, a bit-accumulation operation, and a PPM inner code. Both the prior and present schemes can be characterized as serially concatenated pulse-position modulation (SCPPM) coding schemes. Figure 1 represents a free-space optical communication system based on either the present LDPC-PPM scheme or the prior SCPPM scheme. At the transmitting terminal, the original data (u) are processed by an encoder into blocks of bits (a), and the encoded data are mapped to PPM of an optical signal (c). For the purpose of design and analysis, the optical channel in which the PPM signal propagates is modeled as a Poisson point process. At the receiving terminal, the arriving optical signal (y) is demodulated to obtain an estimate (a^) of the coded data, which is then processed by a decoder to obtain an estimate (u^) of the original data.

Ordinal convolutional neural networks for predicting RDoC positive valence psychiatric symptom severity scores.

PubMed

Rios, Anthony; Kavuluru, Ramakanth

2017-11-01

The CEGS N-GRID 2016 Shared Task in Clinical Natural Language Processing (NLP) provided a set of 1000 neuropsychiatric notes to participants as part of a competition to predict psychiatric symptom severity scores. This paper summarizes our methods, results, and experiences based on our participation in the second track of the shared task. Classical methods of text classification usually fall into one of three problem types: binary, multi-class, and multi-label classification. In this effort, we study ordinal regression problems with text data where misclassifications are penalized differently based on how far apart the ground truth and model predictions are on the ordinal scale. Specifically, we present our entries (methods and results) in the N-GRID shared task in predicting research domain criteria (RDoC) positive valence ordinal symptom severity scores (absent, mild, moderate, and severe) from psychiatric notes. We propose a novel convolutional neural network (CNN) model designed to handle ordinal regression tasks on psychiatric notes. Broadly speaking, our model combines an ordinal loss function, a CNN, and conventional feature engineering (wide features) into a single model which is learned end-to-end. Given interpretability is an important concern with nonlinear models, we apply a recent approach called locally interpretable model-agnostic explanation (LIME) to identify important words that lead to instance specific predictions. Our best model entered into the shared task placed third among 24 teams and scored a macro mean absolute error (MMAE) based normalized score (100·(1-MMAE)) of 83.86. Since the competition, we improved our score (using basic ensembling) to 85.55, comparable with the winning shared task entry. Applying LIME to model predictions, we demonstrate the feasibility of instance specific prediction interpretation by identifying words that led to a particular decision. In this paper, we present a method that successfully uses wide features and an ordinal loss function applied to convolutional neural networks for ordinal text classification specifically in predicting psychiatric symptom severity scores. Our approach leads to excellent performance on the N-GRID shared task and is also amenable to interpretability using existing model-agnostic approaches. Copyright © 2017 Elsevier Inc. All rights reserved.

Accurate segmentation of lung fields on chest radiographs using deep convolutional networks

NASA Astrophysics Data System (ADS)

Arbabshirani, Mohammad R.; Dallal, Ahmed H.; Agarwal, Chirag; Patel, Aalpan; Moore, Gregory

2017-02-01

Accurate segmentation of lung fields on chest radiographs is the primary step for computer-aided detection of various conditions such as lung cancer and tuberculosis. The size, shape and texture of lung fields are key parameters for chest X-ray (CXR) based lung disease diagnosis in which the lung field segmentation is a significant primary step. Although many methods have been proposed for this problem, lung field segmentation remains as a challenge. In recent years, deep learning has shown state of the art performance in many visual tasks such as object detection, image classification and semantic image segmentation. In this study, we propose a deep convolutional neural network (CNN) framework for segmentation of lung fields. The algorithm was developed and tested on 167 clinical posterior-anterior (PA) CXR images collected retrospectively from picture archiving and communication system (PACS) of Geisinger Health System. The proposed multi-scale network is composed of five convolutional and two fully connected layers. The framework achieved IOU (intersection over union) of 0.96 on the testing dataset as compared to manual segmentation. The suggested framework outperforms state of the art registration-based segmentation by a significant margin. To our knowledge, this is the first deep learning based study of lung field segmentation on CXR images developed on a heterogeneous clinical dataset. The results suggest that convolutional neural networks could be employed reliably for lung field segmentation.

Target recognition based on convolutional neural network

NASA Astrophysics Data System (ADS)

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.

Scalable video transmission over Rayleigh fading channels using LDPC codes

NASA Astrophysics Data System (ADS)

Bansal, Manu; Kondi, Lisimachos P.

2005-03-01

In this paper, we investigate an important problem of efficiently utilizing the available resources for video transmission over wireless channels while maintaining a good decoded video quality and resilience to channel impairments. Our system consists of the video codec based on 3-D set partitioning in hierarchical trees (3-D SPIHT) algorithm and employs two different schemes using low-density parity check (LDPC) codes for channel error protection. The first method uses the serial concatenation of the constant-rate LDPC code and rate-compatible punctured convolutional (RCPC) codes. Cyclic redundancy check (CRC) is used to detect transmission errors. In the other scheme, we use the product code structure consisting of a constant rate LDPC/CRC code across the rows of the `blocks' of source data and an erasure-correction systematic Reed-Solomon (RS) code as the column code. In both the schemes introduced here, we use fixed-length source packets protected with unequal forward error correction coding ensuring a strictly decreasing protection across the bitstream. A Rayleigh flat-fading channel with additive white Gaussian noise (AWGN) is modeled for the transmission. The rate-distortion optimization algorithm is developed and carried out for the selection of source coding and channel coding rates using Lagrangian optimization. The experimental results demonstrate the effectiveness of this system under different wireless channel conditions and both the proposed methods (LDPC+RCPC/CRC and RS+LDPC/CRC) outperform the more conventional schemes such as those employing RCPC/CRC.

Automated Detection of Obstructive Sleep Apnea Events from a Single-Lead Electrocardiogram Using a Convolutional Neural Network.

PubMed

Urtnasan, Erdenebayar; Park, Jong-Uk; Joo, Eun-Yeon; Lee, Kyoung-Joung

2018-04-23

In this study, we propose a method for the automated detection of obstructive sleep apnea (OSA) from a single-lead electrocardiogram (ECG) using a convolutional neural network (CNN). A CNN model was designed with six optimized convolution layers including activation, pooling, and dropout layers. One-dimensional (1D) convolution, rectified linear units (ReLU), and max pooling were applied to the convolution, activation, and pooling layers, respectively. For training and evaluation of the CNN model, a single-lead ECG dataset was collected from 82 subjects with OSA and was divided into training (including data from 63 patients with 34,281 events) and testing (including data from 19 patients with 8571 events) datasets. Using this CNN model, a precision of 0.99%, a recall of 0.99%, and an F 1 -score of 0.99% were attained with the training dataset; these values were all 0.96% when the CNN was applied to the testing dataset. These results show that the proposed CNN model can be used to detect OSA accurately on the basis of a single-lead ECG. Ultimately, this CNN model may be used as a screening tool for those suspected to suffer from OSA.

Sculpting the UMLS Refined Semantic Network

PubMed Central

Morrey, C. Paul; Perl, Yehoshua; Elhanan, Gai; Chen, Ling; Chen, Yan; Geller, James

2014-01-01

Background The Refined Semantic Network (RSN) for the UMLS was previously introduced to complement the UMLS Semantic Network (SN). The RSN partitions the UMLS Metathesaurus (META) into disjoint groups of concepts. Each such group is semantically uniform. However, the RSN was initially an order of magnitude larger than the SN, which is undesirable since to be useful, a semantic network should be compact. Most semantic types in the RSN represent combinations of semantic types in the UMLS SN. Such a “combination semantic type” is called Intersection Semantic Type (IST). Many ISTs are assigned to very few concepts. Moreover, when reviewing those concepts, many semantic type assignment inconsistencies were found. After correcting those inconsistencies many ISTs, among them some that contradicted UMLS rules, disappeared, which made the RSN smaller. Objective The authors performed a longitudinal study with the goal of reducing the size of the RSN to become compact. This goal was achieved by correcting inconsistencies and errors in the IST assignments in the UMLS, which additionally helped identify and correct ambiguities, inconsistencies, and errors in source terminologies widely used in the realm of public health. Methods In this paper, we discuss the process and steps employed in this longitudinal study and the intermediate results for different stages. The sculpting process includes removing redundant semantic type assignments, expanding semantic type assignments, and removing illegitimate ISTs by auditing ISTs of small extents. However, the emphasis of this paper is not on the auditing methodologies employed during the process, since they were introduced in earlier publications, but on the strategy of employing them in order to transform the RSN into a compact network. For this paper we also performed a comprehensive audit of 168 “small ISTs” in the 2013AA version of the UMLS to finalize the longitudinal study. Results Over the years it was found that the editors of the UMLS introduced some new inconsistencies that resulted in the reintroduction of unwarranted ISTs that had already been eliminated as a result of their previous corrections. Because of that, the transformation of the RSN into a compact network covering all necessary categories for the UMLS was slowed down. The corrections suggested by an audit of the 2013AA version of the UMLS achieve a compact RSN of equal magnitude as the UMLS SN. The number of ISTs has been reduced to 336. We also demonstrate how auditing the semantic type assignments of UMLS concepts can expose other modeling errors in the UMLS source terminologies, e.g., SNOMED CT, LOINC, and RxNORM that are important for health informatics. Such errors would otherwise stay hidden. Conclusions It is hoped that the UMLS curators will implement all required corrections and use the RSN along with the SN when maintaining and extending the UMLS. When used correctly, the RSN will support the prevention of the accidental introduction of inconsistent semantic type assignments into the UMLS. Furthermore, this way the RSN will support the exposure of other hidden errors and inconsistencies in health informatics terminologies, which are sources of the UMLS. Notably, the development of the RSN materializes the deeper, more refined Semantic Network for the UMLS that its designers envisioned originally but had not implemented. PMID:25422719

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

NASA Astrophysics Data System (ADS)

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

2017-03-01

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

Deep Neural Networks as a Computational Model for Human Shape Sensitivity

PubMed Central

Op de Beeck, Hans P.

2016-01-01

Theories of object recognition agree that shape is of primordial importance, but there is no consensus about how shape might be represented, and so far attempts to implement a model of shape perception that would work with realistic stimuli have largely failed. Recent studies suggest that state-of-the-art convolutional ‘deep’ neural networks (DNNs) capture important aspects of human object perception. We hypothesized that these successes might be partially related to a human-like representation of object shape. Here we demonstrate that sensitivity for shape features, characteristic to human and primate vision, emerges in DNNs when trained for generic object recognition from natural photographs. We show that these models explain human shape judgments for several benchmark behavioral and neural stimulus sets on which earlier models mostly failed. In particular, although never explicitly trained for such stimuli, DNNs develop acute sensitivity to minute variations in shape and to non-accidental properties that have long been implicated to form the basis for object recognition. Even more strikingly, when tested with a challenging stimulus set in which shape and category membership are dissociated, the most complex model architectures capture human shape sensitivity as well as some aspects of the category structure that emerges from human judgments. As a whole, these results indicate that convolutional neural networks not only learn physically correct representations of object categories but also develop perceptually accurate representational spaces of shapes. An even more complete model of human object representations might be in sight by training deep architectures for multiple tasks, which is so characteristic in human development. PMID:27124699

Neural Decoder for Topological Codes

NASA Astrophysics Data System (ADS)

Torlai, Giacomo; Melko, Roger G.

2017-07-01

We present an algorithm for error correction in topological codes that exploits modern machine learning techniques. Our decoder is constructed from a stochastic neural network called a Boltzmann machine, of the type extensively used in deep learning. We provide a general prescription for the training of the network and a decoding strategy that is applicable to a wide variety of stabilizer codes with very little specialization. We demonstrate the neural decoder numerically on the well-known two-dimensional toric code with phase-flip errors.

Identifying Corresponding Patches in SAR and Optical Images With a Pseudo-Siamese CNN

NASA Astrophysics Data System (ADS)

Hughes, Lloyd H.; Schmitt, Michael; Mou, Lichao; Wang, Yuanyuan; Zhu, Xiao Xiang

2018-05-01

In this letter, we propose a pseudo-siamese convolutional neural network (CNN) architecture that enables to solve the task of identifying corresponding patches in very-high-resolution (VHR) optical and synthetic aperture radar (SAR) remote sensing imagery. Using eight convolutional layers each in two parallel network streams, a fully connected layer for the fusion of the features learned in each stream, and a loss function based on binary cross-entropy, we achieve a one-hot indication if two patches correspond or not. The network is trained and tested on an automatically generated dataset that is based on a deterministic alignment of SAR and optical imagery via previously reconstructed and subsequently co-registered 3D point clouds. The satellite images, from which the patches comprising our dataset are extracted, show a complex urban scene containing many elevated objects (i.e. buildings), thus providing one of the most difficult experimental environments. The achieved results show that the network is able to predict corresponding patches with high accuracy, thus indicating great potential for further development towards a generalized multi-sensor key-point matching procedure. Index Terms-synthetic aperture radar (SAR), optical imagery, data fusion, deep learning, convolutional neural networks (CNN), image matching, deep matching

Convolutional neural networks for event-related potential detection: impact of the architecture.

PubMed

Cecotti, H

2017-07-01

The detection of brain responses at the single-trial level in the electroencephalogram (EEG) such as event-related potentials (ERPs) is a difficult problem that requires different processing steps to extract relevant discriminant features. While most of the signal and classification techniques for the detection of brain responses are based on linear algebra, different pattern recognition techniques such as convolutional neural network (CNN), as a type of deep learning technique, have shown some interests as they are able to process the signal after limited pre-processing. In this study, we propose to investigate the performance of CNNs in relation of their architecture and in relation to how they are evaluated: a single system for each subject, or a system for all the subjects. More particularly, we want to address the change of performance that can be observed between specifying a neural network to a subject, or by considering a neural network for a group of subjects, taking advantage of a larger number of trials from different subjects. The results support the conclusion that a convolutional neural network trained on different subjects can lead to an AUC above 0.9 by using an appropriate architecture using spatial filtering and shift invariant layers.

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

PubMed

Savalia, Shalin; Emamian, Vahid

2018-05-04

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

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

NASA Astrophysics Data System (ADS)

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.

Optical transmission testing based on asynchronous sampling techniques: images analysis containing chromatic dispersion using convolutional neural network

NASA Astrophysics Data System (ADS)

Mrozek, T.; Perlicki, K.; Tajmajer, T.; Wasilewski, P.

2017-08-01

The article presents an image analysis method, obtained from an asynchronous delay tap sampling (ADTS) technique, which is used for simultaneous monitoring of various impairments occurring in the physical layer of the optical network. The ADTS method enables the visualization of the optical signal in the form of characteristics (so called phase portraits) that change their shape under the influence of impairments such as chromatic dispersion, polarization mode dispersion and ASE noise. Using this method, a simulation model was built with OptSim 4.0. After the simulation study, data were obtained in the form of images that were further analyzed using the convolutional neural network algorithm. The main goal of the study was to train a convolutional neural network to recognize the selected impairment (distortion); then to test its accuracy and estimate the impairment for the selected set of test images. The input data consisted of processed binary images in the form of two-dimensional matrices, with the position of the pixel. This article focuses only on the analysis of images containing chromatic dispersion.

TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions

PubMed Central

2017-01-01

Although deep learning approaches have had tremendous success in image, video and audio processing, computer vision, and speech recognition, their applications to three-dimensional (3D) biomolecular structural data sets have been hindered by the geometric and biological complexity. To address this problem we introduce the element-specific persistent homology (ESPH) method. ESPH represents 3D complex geometry by one-dimensional (1D) topological invariants and retains important biological information via a multichannel image-like representation. This representation reveals hidden structure-function relationships in biomolecules. We further integrate ESPH and deep convolutional neural networks to construct a multichannel topological neural network (TopologyNet) for the predictions of protein-ligand binding affinities and protein stability changes upon mutation. To overcome the deep learning limitations from small and noisy training sets, we propose a multi-task multichannel topological convolutional neural network (MM-TCNN). We demonstrate that TopologyNet outperforms the latest methods in the prediction of protein-ligand binding affinities, mutation induced globular protein folding free energy changes, and mutation induced membrane protein folding free energy changes. Availability: weilab.math.msu.edu/TDL/ PMID:28749969

Image statistics decoding for convolutional codes

NASA Technical Reports Server (NTRS)

Pitt, G. H., III; Swanson, L.; Yuen, J. H.

1987-01-01

It is a fact that adjacent pixels in a Voyager image are very similar in grey level. This fact can be used in conjunction with the Maximum-Likelihood Convolutional Decoder (MCD) to decrease the error rate when decoding a picture from Voyager. Implementing this idea would require no changes in the Voyager spacecraft and could be used as a backup to the current system without too much expenditure, so the feasibility of it and the possible gains for Voyager were investigated. Simulations have shown that the gain could be as much as 2 dB at certain error rates, and experiments with real data inspired new ideas on ways to get the most information possible out of the received symbol stream.

$$\\mu / \\pi$$ Separation using Convolutional Neural Networks for the MicroBooNE Charged Current Inclusive Cross Section Measurement

DOE Office of Scientific and Technical Information (OSTI.GOV)

Esquivel, Jessica Nicole

The purpose of this thesis was to use Convolutional Neural Networks (CNN) to separatemore » $$\\mu^{\\prime}$$s and $$\\pi^{\\prime}$$s for use in increasing the acceptance rate of $$\\mu^{\\prime}$$s below the implemented 75cm track length cut in the Charged Current Inclusive (CC-Inclusive) event selection for the CC-Inclusive Cross-Section Measurement. In doing this, we increase acceptance rate for CC-Inclusive events below a specific momentum range.« less

Crosslinking EEG time-frequency decomposition and fMRI in error monitoring.

PubMed

Hoffmann, Sven; Labrenz, Franziska; Themann, Maria; Wascher, Edmund; Beste, Christian

2014-03-01

Recent studies implicate a common response monitoring system, being active during erroneous and correct responses. Converging evidence from time-frequency decompositions of the response-related ERP revealed that evoked theta activity at fronto-central electrode positions differentiates correct from erroneous responses in simple tasks, but also in more complex tasks. However, up to now it is unclear how different electrophysiological parameters of error processing, especially at the level of neural oscillations are related, or predictive for BOLD signal changes reflecting error processing at a functional-neuroanatomical level. The present study aims to provide crosslinks between time domain information, time-frequency information, MRI BOLD signal and behavioral parameters in a task examining error monitoring due to mistakes in a mental rotation task. The results show that BOLD signal changes reflecting error processing on a functional-neuroanatomical level are best predicted by evoked oscillations in the theta frequency band. Although the fMRI results in this study account for an involvement of the anterior cingulate cortex, middle frontal gyrus, and the Insula in error processing, the correlation of evoked oscillations and BOLD signal was restricted to a coupling of evoked theta and anterior cingulate cortex BOLD activity. The current results indicate that although there is a distributed functional-neuroanatomical network mediating error processing, only distinct parts of this network seem to modulate electrophysiological properties of error monitoring.

Deep Learning Automates the Quantitative Analysis of Individual Cells in Live-Cell Imaging Experiments.

PubMed

Van Valen, David A; Kudo, Takamasa; Lane, Keara M; Macklin, Derek N; Quach, Nicolas T; DeFelice, Mialy M; Maayan, Inbal; Tanouchi, Yu; Ashley, Euan A; Covert, Markus W

2016-11-01

Live-cell imaging has opened an exciting window into the role cellular heterogeneity plays in dynamic, living systems. A major critical challenge for this class of experiments is the problem of image segmentation, or determining which parts of a microscope image correspond to which individual cells. Current approaches require many hours of manual curation and depend on approaches that are difficult to share between labs. They are also unable to robustly segment the cytoplasms of mammalian cells. Here, we show that deep convolutional neural networks, a supervised machine learning method, can solve this challenge for multiple cell types across the domains of life. We demonstrate that this approach can robustly segment fluorescent images of cell nuclei as well as phase images of the cytoplasms of individual bacterial and mammalian cells from phase contrast images without the need for a fluorescent cytoplasmic marker. These networks also enable the simultaneous segmentation and identification of different mammalian cell types grown in co-culture. A quantitative comparison with prior methods demonstrates that convolutional neural networks have improved accuracy and lead to a significant reduction in curation time. We relay our experience in designing and optimizing deep convolutional neural networks for this task and outline several design rules that we found led to robust performance. We conclude that deep convolutional neural networks are an accurate method that require less curation time, are generalizable to a multiplicity of cell types, from bacteria to mammalian cells, and expand live-cell imaging capabilities to include multi-cell type systems.

Finding strong lenses in CFHTLS using convolutional neural networks

NASA Astrophysics Data System (ADS)

Jacobs, C.; Glazebrook, K.; Collett, T.; More, A.; McCarthy, C.

2017-10-01

We train and apply convolutional neural networks, a machine learning technique developed to learn from and classify image data, to Canada-France-Hawaii Telescope Legacy Survey (CFHTLS) imaging for the identification of potential strong lensing systems. An ensemble of four convolutional neural networks was trained on images of simulated galaxy-galaxy lenses. The training sets consisted of a total of 62 406 simulated lenses and 64 673 non-lens negative examples generated with two different methodologies. An ensemble of trained networks was applied to all of the 171 deg2 of the CFHTLS wide field image data, identifying 18 861 candidates including 63 known and 139 other potential lens candidates. A second search of 1.4 million early-type galaxies selected from the survey catalogue as potential deflectors, identified 2465 candidates including 117 previously known lens candidates, 29 confirmed lenses/high-quality lens candidates, 266 novel probable or potential lenses and 2097 candidates we classify as false positives. For the catalogue-based search we estimate a completeness of 21-28 per cent with respect to detectable lenses and a purity of 15 per cent, with a false-positive rate of 1 in 671 images tested. We predict a human astronomer reviewing candidates produced by the system would identify 20 probable lenses and 100 possible lenses per hour in a sample selected by the robot. Convolutional neural networks are therefore a promising tool for use in the search for lenses in current and forthcoming surveys such as the Dark Energy Survey and the Large Synoptic Survey Telescope.

TernaryNet: faster deep model inference without GPUs for medical 3D segmentation using sparse and binary convolutions.

PubMed

Heinrich, Mattias P; Blendowski, Max; Oktay, Ozan

2018-05-30

Deep convolutional neural networks (DCNN) are currently ubiquitous in medical imaging. While their versatility and high-quality results for common image analysis tasks including segmentation, localisation and prediction is astonishing, the large representational power comes at the cost of highly demanding computational effort. This limits their practical applications for image-guided interventions and diagnostic (point-of-care) support using mobile devices without graphics processing units (GPU). We propose a new scheme that approximates both trainable weights and neural activations in deep networks by ternary values and tackles the open question of backpropagation when dealing with non-differentiable functions. Our solution enables the removal of the expensive floating-point matrix multiplications throughout any convolutional neural network and replaces them by energy- and time-preserving binary operators and population counts. We evaluate our approach for the segmentation of the pancreas in CT. Here, our ternary approximation within a fully convolutional network leads to more than 90% memory reductions and high accuracy (without any post-processing) with a Dice overlap of 71.0% that comes close to the one obtained when using networks with high-precision weights and activations. We further provide a concept for sub-second inference without GPUs and demonstrate significant improvements in comparison with binary quantisation and without our proposed ternary hyperbolic tangent continuation. We present a key enabling technique for highly efficient DCNN inference without GPUs that will help to bring the advances of deep learning to practical clinical applications. It has also great promise for improving accuracies in large-scale medical data retrieval.

Deep Learning Automates the Quantitative Analysis of Individual Cells in Live-Cell Imaging Experiments

DOE PAGES

Van Valen, David A.; Kudo, Takamasa; Lane, Keara M.; ...

2016-11-04

Live-cell imaging has opened an exciting window into the role cellular heterogeneity plays in dynamic, living systems. A major critical challenge for this class of experiments is the problem of image segmentation, or determining which parts of a microscope image correspond to which individual cells. Current approaches require many hours of manual curation and depend on approaches that are difficult to share between labs. They are also unable to robustly segment the cytoplasms of mammalian cells. Here, we show that deep convolutional neural networks, a supervised machine learning method, can solve this challenge for multiple cell types across the domainsmore » of life. We demonstrate that this approach can robustly segment fluorescent images of cell nuclei as well as phase images of the cytoplasms of individual bacterial and mammalian cells from phase contrast images without the need for a fluorescent cytoplasmic marker. These networks also enable the simultaneous segmentation and identification of different mammalian cell types grown in co-culture. A quantitative comparison with prior methods demonstrates that convolutional neural networks have improved accuracy and lead to a significant reduction in curation time. We relay our experience in designing and optimizing deep convolutional neural networks for this task and outline several design rules that we found led to robust performance. We conclude that deep convolutional neural networks are an accurate method that require less curation time, are generalizable to a multiplicity of cell types, from bacteria to mammalian cells, and expand live-cell imaging capabilities to include multi-cell type systems.« less

Radio Galaxy Zoo: compact and extended radio source classification with deep learning

NASA Astrophysics Data System (ADS)

Lukic, V.; Brüggen, M.; Banfield, J. K.; Wong, O. I.; Rudnick, L.; Norris, R. P.; Simmons, B.

2018-05-01

Machine learning techniques have been increasingly useful in astronomical applications over the last few years, for example in the morphological classification of galaxies. Convolutional neural networks have proven to be highly effective in classifying objects in image data. In the context of radio-interferometric imaging in astronomy, we looked for ways to identify multiple components of individual sources. To this effect, we design a convolutional neural network to differentiate between different morphology classes using sources from the Radio Galaxy Zoo (RGZ) citizen science project. In this first step, we focus on exploring the factors that affect the performance of such neural networks, such as the amount of training data, number and nature of layers, and the hyperparameters. We begin with a simple experiment in which we only differentiate between two extreme morphologies, using compact and multiple-component extended sources. We found that a three-convolutional layer architecture yielded very good results, achieving a classification accuracy of 97.4 per cent on a test data set. The same architecture was then tested on a four-class problem where we let the network classify sources into compact and three classes of extended sources, achieving a test accuracy of 93.5 per cent. The best-performing convolutional neural network set-up has been verified against RGZ Data Release 1 where a final test accuracy of 94.8 per cent was obtained, using both original and augmented images. The use of sigma clipping does not offer a significant benefit overall, except in cases with a small number of training images.

Deep-Learning Convolutional Neural Networks Accurately Classify Genetic Mutations in Gliomas.

PubMed

Chang, P; Grinband, J; Weinberg, B D; Bardis, M; Khy, M; Cadena, G; Su, M-Y; Cha, S; Filippi, C G; Bota, D; Baldi, P; Poisson, L M; Jain, R; Chow, D

2018-05-10

The World Health Organization has recently placed new emphasis on the integration of genetic information for gliomas. While tissue sampling remains the criterion standard, noninvasive imaging techniques may provide complimentary insight into clinically relevant genetic mutations. Our aim was to train a convolutional neural network to independently predict underlying molecular genetic mutation status in gliomas with high accuracy and identify the most predictive imaging features for each mutation. MR imaging data and molecular information were retrospectively obtained from The Cancer Imaging Archives for 259 patients with either low- or high-grade gliomas. A convolutional neural network was trained to classify isocitrate dehydrogenase 1 ( IDH1 ) mutation status, 1p/19q codeletion, and O6-methylguanine-DNA methyltransferase ( MGMT ) promotor methylation status. Principal component analysis of the final convolutional neural network layer was used to extract the key imaging features critical for successful classification. Classification had high accuracy: IDH1 mutation status, 94%; 1p/19q codeletion, 92%; and MGMT promotor methylation status, 83%. Each genetic category was also associated with distinctive imaging features such as definition of tumor margins, T1 and FLAIR suppression, extent of edema, extent of necrosis, and textural features. Our results indicate that for The Cancer Imaging Archives dataset, machine-learning approaches allow classification of individual genetic mutations of both low- and high-grade gliomas. We show that relevant MR imaging features acquired from an added dimensionality-reduction technique demonstrate that neural networks are capable of learning key imaging components without prior feature selection or human-directed training. © 2018 by American Journal of Neuroradiology.

Deep Learning Automates the Quantitative Analysis of Individual Cells in Live-Cell Imaging Experiments

DOE Office of Scientific and Technical Information (OSTI.GOV)

Van Valen, David A.; Kudo, Takamasa; Lane, Keara M.

Live-cell imaging has opened an exciting window into the role cellular heterogeneity plays in dynamic, living systems. A major critical challenge for this class of experiments is the problem of image segmentation, or determining which parts of a microscope image correspond to which individual cells. Current approaches require many hours of manual curation and depend on approaches that are difficult to share between labs. They are also unable to robustly segment the cytoplasms of mammalian cells. Here, we show that deep convolutional neural networks, a supervised machine learning method, can solve this challenge for multiple cell types across the domainsmore » of life. We demonstrate that this approach can robustly segment fluorescent images of cell nuclei as well as phase images of the cytoplasms of individual bacterial and mammalian cells from phase contrast images without the need for a fluorescent cytoplasmic marker. These networks also enable the simultaneous segmentation and identification of different mammalian cell types grown in co-culture. A quantitative comparison with prior methods demonstrates that convolutional neural networks have improved accuracy and lead to a significant reduction in curation time. We relay our experience in designing and optimizing deep convolutional neural networks for this task and outline several design rules that we found led to robust performance. We conclude that deep convolutional neural networks are an accurate method that require less curation time, are generalizable to a multiplicity of cell types, from bacteria to mammalian cells, and expand live-cell imaging capabilities to include multi-cell type systems.« less

Deep Learning Automates the Quantitative Analysis of Individual Cells in Live-Cell Imaging Experiments

PubMed Central

Van Valen, David A.; Lane, Keara M.; Quach, Nicolas T.; Maayan, Inbal

2016-01-01

Live-cell imaging has opened an exciting window into the role cellular heterogeneity plays in dynamic, living systems. A major critical challenge for this class of experiments is the problem of image segmentation, or determining which parts of a microscope image correspond to which individual cells. Current approaches require many hours of manual curation and depend on approaches that are difficult to share between labs. They are also unable to robustly segment the cytoplasms of mammalian cells. Here, we show that deep convolutional neural networks, a supervised machine learning method, can solve this challenge for multiple cell types across the domains of life. We demonstrate that this approach can robustly segment fluorescent images of cell nuclei as well as phase images of the cytoplasms of individual bacterial and mammalian cells from phase contrast images without the need for a fluorescent cytoplasmic marker. These networks also enable the simultaneous segmentation and identification of different mammalian cell types grown in co-culture. A quantitative comparison with prior methods demonstrates that convolutional neural networks have improved accuracy and lead to a significant reduction in curation time. We relay our experience in designing and optimizing deep convolutional neural networks for this task and outline several design rules that we found led to robust performance. We conclude that deep convolutional neural networks are an accurate method that require less curation time, are generalizable to a multiplicity of cell types, from bacteria to mammalian cells, and expand live-cell imaging capabilities to include multi-cell type systems. PMID:27814364

Fast temporal neural learning using teacher forcing

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad (Inventor); Bahren, Jacob (Inventor)

1992-01-01

A neural network is trained to output a time dependent target vector defined over a predetermined time interval in response to a time dependent input vector defined over the same time interval by applying corresponding elements of the error vector, or difference between the target vector and the actual neuron output vector, to the inputs of corresponding output neurons of the network as corrective feedback. This feedback decreases the error and quickens the learning process, so that a much smaller number of training cycles are required to complete the learning process. A conventional gradient descent algorithm is employed to update the neural network parameters at the end of the predetermined time interval. The foregoing process is repeated in repetitive cycles until the actual output vector corresponds to the target vector. In the preferred embodiment, as the overall error of the neural network output decreasing during successive training cycles, the portion of the error fed back to the output neurons is decreased accordingly, allowing the network to learn with greater freedom from teacher forcing as the network parameters converge to their optimum values. The invention may also be used to train a neural network with stationary training and target vectors.

Fast temporal neural learning using teacher forcing

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad (Inventor); Bahren, Jacob (Inventor)

1995-01-01

A neural network is trained to output a time dependent target vector defined over a predetermined time interval in response to a time dependent input vector defined over the same time interval by applying corresponding elements of the error vector, or difference between the target vector and the actual neuron output vector, to the inputs of corresponding output neurons of the network as corrective feedback. This feedback decreases the error and quickens the learning process, so that a much smaller number of training cycles are required to complete the learning process. A conventional gradient descent algorithm is employed to update the neural network parameters at the end of the predetermined time interval. The foregoing process is repeated in repetitive cycles until the actual output vector corresponds to the target vector. In the preferred embodiment, as the overall error of the neural network output decreasing during successive training cycles, the portion of the error fed back to the output neurons is decreased accordingly, allowing the network to learn with greater freedom from teacher forcing as the network parameters converge to their optimum values. The invention may also be used to train a neural network with stationary training and target vectors.

A False Alarm Reduction Method for a Gas Sensor Based Electronic Nose

PubMed Central

Rahman, Mohammad Mizanur; Suksompong, Prapun; Toochinda, Pisanu; Taparugssanagorn, Attaphongse

2017-01-01

Electronic noses (E-Noses) are becoming popular for food and fruit quality assessment due to their robustness and repeated usability without fatigue, unlike human experts. An E-Nose equipped with classification algorithms and having open ended classification boundaries such as the k-nearest neighbor (k-NN), support vector machine (SVM), and multilayer perceptron neural network (MLPNN), are found to suffer from false classification errors of irrelevant odor data. To reduce false classification and misclassification errors, and to improve correct rejection performance; algorithms with a hyperspheric boundary, such as a radial basis function neural network (RBFNN) and generalized regression neural network (GRNN) with a Gaussian activation function in the hidden layer should be used. The simulation results presented in this paper show that GRNN has more correct classification efficiency and false alarm reduction capability compared to RBFNN. As the design of a GRNN and RBFNN is complex and expensive due to large numbers of neuron requirements, a simple hyperspheric classification method based on minimum, maximum, and mean (MMM) values of each class of the training dataset was presented. The MMM algorithm was simple and found to be fast and efficient in correctly classifying data of training classes, and correctly rejecting data of extraneous odors, and thereby reduced false alarms. PMID:28895910

A False Alarm Reduction Method for a Gas Sensor Based Electronic Nose.

PubMed

Rahman, Mohammad Mizanur; Charoenlarpnopparut, Chalie; Suksompong, Prapun; Toochinda, Pisanu; Taparugssanagorn, Attaphongse

2017-09-12

Electronic noses (E-Noses) are becoming popular for food and fruit quality assessment due to their robustness and repeated usability without fatigue, unlike human experts. An E-Nose equipped with classification algorithms and having open ended classification boundaries such as the k -nearest neighbor ( k -NN), support vector machine (SVM), and multilayer perceptron neural network (MLPNN), are found to suffer from false classification errors of irrelevant odor data. To reduce false classification and misclassification errors, and to improve correct rejection performance; algorithms with a hyperspheric boundary, such as a radial basis function neural network (RBFNN) and generalized regression neural network (GRNN) with a Gaussian activation function in the hidden layer should be used. The simulation results presented in this paper show that GRNN has more correct classification efficiency and false alarm reduction capability compared to RBFNN. As the design of a GRNN and RBFNN is complex and expensive due to large numbers of neuron requirements, a simple hyperspheric classification method based on minimum, maximum, and mean (MMM) values of each class of the training dataset was presented. The MMM algorithm was simple and found to be fast and efficient in correctly classifying data of training classes, and correctly rejecting data of extraneous odors, and thereby reduced false alarms.

Using the Abstraction Network in Complement to Description Logics for Quality Assurance in Biomedical Terminologies - A Case Study in SNOMED CT

PubMed Central

Wei, Duo; Bodenreider, Olivier

2015-01-01

Objectives To investigate errors identified in SNOMED CT by human reviewers with help from the Abstraction Network methodology and examine why they had escaped detection by the Description Logic (DL) classifier. Case study; Two examples of errors are presented in detail (one missing IS-A relation and one duplicate concept). After correction, SNOMED CT is reclassified to ensure that no new inconsistency was introduced. Conclusions DL-based auditing techniques built in terminology development environments ensure the logical consistency of the terminology. However, complementary approaches are needed for identifying and addressing other types of errors. PMID:20841848

Using the abstraction network in complement to description logics for quality assurance in biomedical terminologies - a case study in SNOMED CT.

PubMed

Wei, Duo; Bodenreider, Olivier

2010-01-01

To investigate errors identified in SNOMED CT by human reviewers with help from the Abstraction Network methodology and examine why they had escaped detection by the Description Logic (DL) classifier. Case study; Two examples of errors are presented in detail (one missing IS-A relation and one duplicate concept). After correction, SNOMED CT is reclassified to ensure that no new inconsistency was introduced. DL-based auditing techniques built in terminology development environments ensure the logical consistency of the terminology. However, complementary approaches are needed for identifying and addressing other types of errors.

UFCN: a fully convolutional neural network for road extraction in RGB imagery acquired by remote sensing from an unmanned aerial vehicle

NASA Astrophysics Data System (ADS)

Kestur, Ramesh; Farooq, Shariq; Abdal, Rameen; Mehraj, Emad; Narasipura, Omkar; Mudigere, Meenavathi

2018-01-01

Road extraction in imagery acquired by low altitude remote sensing (LARS) carried out using an unmanned aerial vehicle (UAV) is presented. LARS is carried out using a fixed wing UAV with a high spatial resolution vision spectrum (RGB) camera as the payload. Deep learning techniques, particularly fully convolutional network (FCN), are adopted to extract roads by dense semantic segmentation. The proposed model, UFCN (U-shaped FCN) is an FCN architecture, which is comprised of a stack of convolutions followed by corresponding stack of mirrored deconvolutions with the usage of skip connections in between for preserving the local information. The limited dataset (76 images and their ground truths) is subjected to real-time data augmentation during training phase to increase the size effectively. Classification performance is evaluated using precision, recall, accuracy, F1 score, and brier score parameters. The performance is compared with support vector machine (SVM) classifier, a one-dimensional convolutional neural network (1D-CNN) model, and a standard two-dimensional CNN (2D-CNN). The UFCN model outperforms the SVM, 1D-CNN, and 2D-CNN models across all the performance parameters. Further, the prediction time of the proposed UFCN model is comparable with SVM, 1D-CNN, and 2D-CNN models.

Deep convolutional neural network based antenna selection in multiple-input multiple-output system

NASA Astrophysics Data System (ADS)

Cai, Jiaxin; Li, Yan; Hu, Ying

2018-03-01

Antenna selection of wireless communication system has attracted increasing attention due to the challenge of keeping a balance between communication performance and computational complexity in large-scale Multiple-Input MultipleOutput antenna systems. Recently, deep learning based methods have achieved promising performance for large-scale data processing and analysis in many application fields. This paper is the first attempt to introduce the deep learning technique into the field of Multiple-Input Multiple-Output antenna selection in wireless communications. First, the label of attenuation coefficients channel matrix is generated by minimizing the key performance indicator of training antenna systems. Then, a deep convolutional neural network that explicitly exploits the massive latent cues of attenuation coefficients is learned on the training antenna systems. Finally, we use the adopted deep convolutional neural network to classify the channel matrix labels of test antennas and select the optimal antenna subset. Simulation experimental results demonstrate that our method can achieve better performance than the state-of-the-art baselines for data-driven based wireless antenna selection.

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

PubMed

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

2018-05-29

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

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

PubMed

Zhang, Jianhua; Li, Sunan; Wang, Rubin

2017-01-01

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

A Data-Driven Response Virtual Sensor Technique with Partial Vibration Measurements Using Convolutional Neural Network.

PubMed

Sun, Shan-Bin; He, Yuan-Yuan; Zhou, Si-Da; Yue, Zhen-Jiang

2017-12-12

Measurement of dynamic responses plays an important role in structural health monitoring, damage detection and other fields of research. However, in aerospace engineering, the physical sensors are limited in the operational conditions of spacecraft, due to the severe environment in outer space. This paper proposes a virtual sensor model with partial vibration measurements using a convolutional neural network. The transmissibility function is employed as prior knowledge. A four-layer neural network with two convolutional layers, one fully connected layer, and an output layer is proposed as the predicting model. Numerical examples of two different structural dynamic systems demonstrate the performance of the proposed approach. The excellence of the novel technique is further indicated using a simply supported beam experiment comparing to a modal-model-based virtual sensor, which uses modal parameters, such as mode shapes, for estimating the responses of the faulty sensors. The results show that the presented data-driven response virtual sensor technique can predict structural response with high accuracy.

A Data-Driven Response Virtual Sensor Technique with Partial Vibration Measurements Using Convolutional Neural Network

PubMed Central

Sun, Shan-Bin; He, Yuan-Yuan; Zhou, Si-Da; Yue, Zhen-Jiang

2017-01-01

Measurement of dynamic responses plays an important role in structural health monitoring, damage detection and other fields of research. However, in aerospace engineering, the physical sensors are limited in the operational conditions of spacecraft, due to the severe environment in outer space. This paper proposes a virtual sensor model with partial vibration measurements using a convolutional neural network. The transmissibility function is employed as prior knowledge. A four-layer neural network with two convolutional layers, one fully connected layer, and an output layer is proposed as the predicting model. Numerical examples of two different structural dynamic systems demonstrate the performance of the proposed approach. The excellence of the novel technique is further indicated using a simply supported beam experiment comparing to a modal-model-based virtual sensor, which uses modal parameters, such as mode shapes, for estimating the responses of the faulty sensors. The results show that the presented data-driven response virtual sensor technique can predict structural response with high accuracy. PMID:29231868

Spotting L3 slice in CT scans using deep convolutional network and transfer learning.

PubMed

Belharbi, Soufiane; Chatelain, Clément; Hérault, Romain; Adam, Sébastien; Thureau, Sébastien; Chastan, Mathieu; Modzelewski, Romain

2017-08-01

In this article, we present a complete automated system for spotting a particular slice in a complete 3D Computed Tomography exam (CT scan). Our approach does not require any assumptions on which part of the patient's body is covered by the scan. It relies on an original machine learning regression approach. Our models are learned using the transfer learning trick by exploiting deep architectures that have been pre-trained on imageNet database, and therefore it requires very little annotation for its training. The whole pipeline consists of three steps: i) conversion of the CT scans into Maximum Intensity Projection (MIP) images, ii) prediction from a Convolutional Neural Network (CNN) applied in a sliding window fashion over the MIP image, and iii) robust analysis of the prediction sequence to predict the height of the desired slice within the whole CT scan. Our approach is applied to the detection of the third lumbar vertebra (L3) slice that has been found to be representative to the whole body composition. Our system is evaluated on a database collected in our clinical center, containing 642 CT scans from different patients. We obtained an average localization error of 1.91±2.69 slices (less than 5 mm) in an average time of less than 2.5 s/CT scan, allowing integration of the proposed system into daily clinical routines. Copyright © 2017 Elsevier Ltd. All rights reserved.

ICD-10 procedure codes produce transition challenges

PubMed Central

Boyd, Andrew D.; Li, Jianrong ‘John’; Kenost, Colleen; Zaim, Samir Rachid; Krive, Jacob; Mittal, Manish; Satava, Richard A.; Burton, Michael; Smith, Jacob; Lussier, Yves A.

2018-01-01

The transition of procedure coding from ICD-9-CM-Vol-3 to ICD-10-PCS has generated problems for the medical community at large resulting from the lack of clarity required to integrate two non-congruent coding systems. We hypothesized that quantifying these issues with network topology analyses offers a better understanding of the issues, and therefore we developed solutions (online tools) to empower hospital administrators and researchers to address these challenges. Five topologies were identified: “identity”(I), “class-to-subclass”(C2S), “subclass-toclass”(S2C), “convoluted(C)”, and “no mapping”(NM). The procedure codes in the 2010 Illinois Medicaid dataset (3,290 patients, 116 institutions) were categorized as C=55%, C2S=40%, I=3%, NM=2%, and S2C=1%. Majority of the problematic and ambiguous mappings (convoluted) pertained to operations in ophthalmology cardiology, urology, gyneco-obstetrics, and dermatology. Finally, the algorithms were expanded into a user-friendly tool to identify problematic topologies and specify lists of procedural codes utilized by medical professionals and researchers for mitigating error-prone translations, simplifying research, and improving quality.http://www.lussiergroup.org/transition-to-ICD10PCS PMID:29888037

Hand pose estimation in depth image using CNN and random forest

NASA Astrophysics Data System (ADS)

Chen, Xi; Cao, Zhiguo; Xiao, Yang; Fang, Zhiwen

2018-03-01

Thanks to the availability of low cost depth cameras, like Microsoft Kinect, 3D hand pose estimation attracted special research attention in these years. Due to the large variations in hand`s viewpoint and the high dimension of hand motion, 3D hand pose estimation is still challenging. In this paper we propose a two-stage framework which joint with CNN and Random Forest to boost the performance of hand pose estimation. First, we use a standard Convolutional Neural Network (CNN) to regress the hand joints` locations. Second, using a Random Forest to refine the joints from the first stage. In the second stage, we propose a pyramid feature which merges the information flow of the CNN. Specifically, we get the rough joints` location from first stage, then rotate the convolutional feature maps (and image). After this, for each joint, we map its location to each feature map (and image) firstly, then crop features at each feature map (and image) around its location, put extracted features to Random Forest to refine at last. Experimentally, we evaluate our proposed method on ICVL dataset and get the mean error about 11mm, our method is also real-time on a desktop.

SU-C-207B-07: Deep Convolutional Neural Network Image Matching for Ultrasound Guidance in Radiotherapy

DOE Office of Scientific and Technical Information (OSTI.GOV)

Zhu, N; Najafi, M; Hancock, S

Purpose: Robust matching of ultrasound images is a challenging problem as images of the same anatomy often present non-trivial differences. This poses an obstacle for ultrasound guidance in radiotherapy. Thus our objective is to overcome this obstacle by designing and evaluating an image blocks matching framework based on a two channel deep convolutional neural network. Methods: We extend to 3D an algorithmic structure previously introduced for 2D image feature learning [1]. To obtain the similarity between two 3D image blocks A and B, the 3D image blocks are divided into 2D patches Ai and Bi. The similarity is then calculatedmore » as the average similarity score of Ai and Bi. The neural network was then trained with public non-medical image pairs, and subsequently evaluated on ultrasound image blocks for the following scenarios: (S1) same image blocks with/without shifts (A and A-shift-x); (S2) non-related random block pairs; (S3) ground truth registration matched pairs of different ultrasound images with/without shifts (A-i and A-reg-i-shift-x). Results: For S1 the similarity scores of A and A-shift-x were 32.63, 18.38, 12.95, 9.23, 2.15 and 0.43 for x=ranging from 0 mm to 10 mm in 2 mm increments. For S2 the average similarity score for non-related block pairs was −1.15. For S3 the average similarity score of ground truth registration matched blocks A-i and A-reg-i-shift-0 (1≤i≤5) was 12.37. After translating A-reg-i-shift-0 by 0 mm, 2 mm, 4 mm, 6 mm, 8 mm, and 10 mm, the average similarity scores of A-i and A-reg-i-shift-x were 11.04, 8.42, 4.56, 2.27, and 0.29 respectively. Conclusion: The proposed method correctly assigns highest similarity to corresponding 3D ultrasound image blocks despite differences in image content and thus can form the basis for ultrasound image registration and tracking.[1] Zagoruyko, Komodakis, “Learning to compare image patches via convolutional neural networks', IEEE CVPR 2015,pp.4353–4361.« less

Machine learning vortices at the Kosterlitz-Thouless transition

NASA Astrophysics Data System (ADS)

Beach, Matthew J. S.; Golubeva, Anna; Melko, Roger G.

2018-01-01

Efficient and automated classification of phases from minimally processed data is one goal of machine learning in condensed-matter and statistical physics. Supervised algorithms trained on raw samples of microstates can successfully detect conventional phase transitions via learning a bulk feature such as an order parameter. In this paper, we investigate whether neural networks can learn to classify phases based on topological defects. We address this question on the two-dimensional classical XY model which exhibits a Kosterlitz-Thouless transition. We find significant feature engineering of the raw spin states is required to convincingly claim that features of the vortex configurations are responsible for learning the transition temperature. We further show a single-layer network does not correctly classify the phases of the XY model, while a convolutional network easily performs classification by learning the global magnetization. Finally, we design a deep network capable of learning vortices without feature engineering. We demonstrate the detection of vortices does not necessarily result in the best classification accuracy, especially for lattices of less than approximately 1000 spins. For larger systems, it remains a difficult task to learn vortices.

Experimental study of digital image processing techniques for LANDSAT data

NASA Technical Reports Server (NTRS)

Rifman, S. S. (Principal Investigator); Allendoerfer, W. B.; Caron, R. H.; Pemberton, L. J.; Mckinnon, D. M.; Polanski, G.; Simon, K. W.

1976-01-01

The author has identified the following significant results. Results are reported for: (1) subscene registration, (2) full scene rectification and registration, (3) resampling techniques, (4) and ground control point (GCP) extraction. Subscenes (354 pixels x 234 lines) were registered to approximately 1/4 pixel accuracy and evaluated by change detection imagery for three cases: (1) bulk data registration, (2) precision correction of a reference subscene using GCP data, and (3) independently precision processed subscenes. Full scene rectification and registration results were evaluated by using a correlation technique to measure registration errors of 0.3 pixel rms thoughout the full scene. Resampling evaluations of nearest neighbor and TRW cubic convolution processed data included change detection imagery and feature classification. Resampled data were also evaluated for an MSS scene containing specular solar reflections.

Salient regions detection using convolutional neural networks and color volume

NASA Astrophysics Data System (ADS)

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.

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

NASA Astrophysics Data System (ADS)

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

2017-10-01

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

Majorana Braiding with Thermal Noise.

PubMed

Pedrocchi, Fabio L; DiVincenzo, David P

2015-09-18

We investigate the self-correcting properties of a network of Majorana wires, in the form of a trijunction, in contact with a parity-preserving thermal environment. As opposed to the case where Majorana bound states are immobile, braiding Majorana bound states within a trijunction introduces dangerous error processes that we identify. Such errors prevent the lifetime of the memory from increasing with the size of the system. We confirm our predictions with Monte Carlo simulations. Our findings put a restriction on the degree of self-correction of this specific quantum computing architecture.

Spine centerline extraction and efficient spine reading of MRI and CT data

NASA Astrophysics Data System (ADS)

Lorenz, C.; Vogt, N.; Börnert, P.; Brosch, T.

2018-03-01

Radiological assessment of the spine is performed regularly in the context of orthopedics, neurology, oncology, and trauma management. Due to the extension and curved geometry of the spinal column, reading is time-consuming and requires substantial user interaction to navigate through the data during inspection. In this paper a spine geometry guided viewing approach is proposed facilitating reading by reducing the degrees of freedom to be manipulated during inspection of the data. The method is using the spine centerline as a representation of the spine geometry. We assume that renderings most useful for reading are those that can be locally defined based on a rotation and translation relative to the spine centerline. The resulting renderings conserve locally the relation to the spine and lead to curved planar reformats that can be adjusted using a small set of parameters to minimize user interaction. The spine centerline is extracted by an automated image to image foveal fully convolutional neural network (FFCN) based approach. The network consists of three parallel convolutional pathways working on different levels of resolution and processed fields of view. The outputs of the parallel pathways are combined by a subsequent feature integration pathway to yield the (final) centerline probability map, which is converted into a set of spine centerline points. The network has been trained separately using two data set types, one comprising a mixture of T1 and T2 weighted spine MR images and one using CT image data. We achieve an average centerline position error of 1.7 mm for MR and 0.9 mm for CT and a DICE coefficient of 0.84 for MR and 0.95 for CT. Based on the thus obtained centerline viewing and multi-planar reformatting can be easily facilitated.

Visual properties and memorising scenes: Effects of image-space sparseness and uniformity.

PubMed

Lukavský, Jiří; Děchtěrenko, Filip

2017-10-01

Previous studies have demonstrated that humans have a remarkable capacity to memorise a large number of scenes. The research on memorability has shown that memory performance can be predicted by the content of an image. We explored how remembering an image is affected by the image properties within the context of the reference set, including the extent to which it is different from its neighbours (image-space sparseness) and if it belongs to the same category as its neighbours (uniformity). We used a reference set of 2,048 scenes (64 categories), evaluated pairwise scene similarity using deep features from a pretrained convolutional neural network (CNN), and calculated the image-space sparseness and uniformity for each image. We ran three memory experiments, varying the memory workload with experiment length and colour/greyscale presentation. We measured the sensitivity and criterion value changes as a function of image-space sparseness and uniformity. Across all three experiments, we found separate effects of 1) sparseness on memory sensitivity, and 2) uniformity on the recognition criterion. People better remembered (and correctly rejected) images that were more separated from others. People tended to make more false alarms and fewer miss errors in images from categorically uniform portions of the image-space. We propose that both image-space properties affect human decisions when recognising images. Additionally, we found that colour presentation did not yield better memory performance over grayscale images.

The network impact of hijacking a quantum repeater

NASA Astrophysics Data System (ADS)

Satoh, Takahiko; Nagayama, Shota; Oka, Takafumi; Van Meter, Rodney

2018-07-01

In quantum networking, repeater hijacking menaces the security and utility of quantum applications. To deal with this problem, it is important to take a measure of the impact of quantum repeater hijacking. First, we quantify the work of each quantum repeater with regards to each quantum communication. Based on this, we show the costs for repeater hijacking detection using distributed quantum state tomography and the amount of work loss and rerouting penalties caused by hijacking. This quantitative evaluation covers both purification-entanglement swapping and quantum error correction repeater networks. Naive implementation of the checks necessary for correct network operation can be subverted by a single hijacker to bring down an entire network. Fortunately, the simple fix of randomly assigned testing can prevent such an attack.

Deterministic error correction for nonlocal spatial-polarization hyperentanglement

PubMed Central

Li, Tao; Wang, Guan-Yu; Deng, Fu-Guo; Long, Gui-Lu

2016-01-01

Hyperentanglement is an effective quantum source for quantum communication network due to its high capacity, low loss rate, and its unusual character in teleportation of quantum particle fully. Here we present a deterministic error-correction scheme for nonlocal spatial-polarization hyperentangled photon pairs over collective-noise channels. In our scheme, the spatial-polarization hyperentanglement is first encoded into a spatial-defined time-bin entanglement with identical polarization before it is transmitted over collective-noise channels, which leads to the error rejection of the spatial entanglement during the transmission. The polarization noise affecting the polarization entanglement can be corrected with a proper one-step decoding procedure. The two parties in quantum communication can, in principle, obtain a nonlocal maximally entangled spatial-polarization hyperentanglement in a deterministic way, which makes our protocol more convenient than others in long-distance quantum communication. PMID:26861681

Deterministic error correction for nonlocal spatial-polarization hyperentanglement.

PubMed

Li, Tao; Wang, Guan-Yu; Deng, Fu-Guo; Long, Gui-Lu

2016-02-10

Hyperentanglement is an effective quantum source for quantum communication network due to its high capacity, low loss rate, and its unusual character in teleportation of quantum particle fully. Here we present a deterministic error-correction scheme for nonlocal spatial-polarization hyperentangled photon pairs over collective-noise channels. In our scheme, the spatial-polarization hyperentanglement is first encoded into a spatial-defined time-bin entanglement with identical polarization before it is transmitted over collective-noise channels, which leads to the error rejection of the spatial entanglement during the transmission. The polarization noise affecting the polarization entanglement can be corrected with a proper one-step decoding procedure. The two parties in quantum communication can, in principle, obtain a nonlocal maximally entangled spatial-polarization hyperentanglement in a deterministic way, which makes our protocol more convenient than others in long-distance quantum communication.

Application of the Convolution Formalism to the Ocean Tide Potential: Results from the Gravity and Recovery and Climate Experiment (GRACE)

NASA Technical Reports Server (NTRS)

Desai, S. D.; Yuan, D. -N.

2006-01-01

A computationally efficient approach to reducing omission errors in ocean tide potential models is derived and evaluated using data from the Gravity Recovery and Climate Experiment (GRACE) mission. Ocean tide height models are usually explicitly available at a few frequencies, and a smooth unit response is assumed to infer the response across the tidal spectrum. The convolution formalism of Munk and Cartwright (1966) models this response function with a Fourier series. This allows the total ocean tide height, and therefore the total ocean tide potential, to be modeled as a weighted sum of past, present, and future values of the tide-generating potential. Previous applications of the convolution formalism have usually been limited to tide height models, but we extend it to ocean tide potential models. We use luni-solar ephemerides to derive the required tide-generating potential so that the complete spectrum of the ocean tide potential is efficiently represented. In contrast, the traditionally adopted harmonic model of the ocean tide potential requires the explicit sum of the contributions from individual tidal frequencies. It is therefore subject to omission errors from neglected frequencies and is computationally more intensive. Intersatellite range rate data from the GRACE mission are used to compare convolution and harmonic models of the ocean tide potential. The monthly range rate residual variance is smaller by 4-5%, and the daily residual variance is smaller by as much as 15% when using the convolution model than when using a harmonic model that is defined by twice the number of parameters.

"Effects of networking on career success: A longitudinal study": Correction to Wolff and Moser (2009).

PubMed

2017-02-01

Reports an error in "Effects of networking on career success: A longitudinal study" by Hans-Georg Wolff and Klaus Moser ( Journal of Applied Psychology , 2009[Jan], Vol 94[1], 196-206). In the article, results from a confirmatory factor analysis on subjective career success in the Measures section contained an error in the reported Chi-square (i.e., χ² (5, N = 257) = 9.17). This error does not alter any conclusions or substantive statements in the original article. The correct fit indices are " χ²(5, N = 257) 9.67, p = .08, RMSEA = 0.059, CFI = 1.00." (The following abstract of the original article appeared in record 2009-00697-007.) Previous research has reported effects of networking, defined as building, maintaining, and using relationships, on career success. However, empirical studies have relied exclusively on concurrent or retrospective designs that rest upon strong assumptions about the causal direction of this relation and depict a static snapshot of the relation at a given point in time. This study provides a dynamic perspective on the effects of networking on career success and reports results of a longitudinal study. Networking was assessed with 6 subscales that resulted from combining measures of the facets of (a) internal versus external networking and (b) building versus maintaining versus using contacts. Objective (salary) and subjective (career satisfaction) measures of career success were obtained for 3 consecutive years. Multilevel analyses showed that networking is related to concurrent salary and that it is related to the growth rate of salary over time. Networking is also related to concurrent career satisfaction. As satisfaction remained stable over time, no effects of networking on the growth of career satisfaction were found. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

Piezocomposite Actuator Arrays for Correcting and Controlling Wavefront Error in Reflectors

NASA Technical Reports Server (NTRS)

Bradford, Samuel Case; Peterson, Lee D.; Ohara, Catherine M.; Shi, Fang; Agnes, Greg S.; Hoffman, Samuel M.; Wilkie, William Keats

2012-01-01

Three reflectors have been developed and tested to assess the performance of a distributed network of piezocomposite actuators for correcting thermal deformations and total wave-front error. The primary testbed article is an active composite reflector, composed of a spherically curved panel with a graphite face sheet and aluminum honeycomb core composite, and then augmented with a network of 90 distributed piezoelectric composite actuators. The piezoelectric actuator system may be used for correcting as-built residual shape errors, and for controlling low-order, thermally-induced quasi-static distortions of the panel. In this study, thermally-induced surface deformations of 1 to 5 microns were deliberately introduced onto the reflector, then measured using a speckle holography interferometer system. The reflector surface figure was subsequently corrected to a tolerance of 50 nm using the actuators embedded in the reflector's back face sheet. Two additional test articles were constructed: a borosilicate at window at 150 mm diameter with 18 actuators bonded to the back surface; and a direct metal laser sintered reflector with spherical curvature, 230 mm diameter, and 12 actuators bonded to the back surface. In the case of the glass reflector, absolute measurements were performed with an interferometer and the absolute surface was corrected. These test articles were evaluated to determine their absolute surface control capabilities, as well as to assess a multiphysics modeling effort developed under this program for the prediction of active reflector response. This paper will describe the design, construction, and testing of active reflector systems under thermal loads, and subsequent correction of surface shape via distributed peizeoelctric actuation.

A Family of Algorithms for Computing Consensus about Node State from Network Data

PubMed Central

Brush, Eleanor R.; Krakauer, David C.; Flack, Jessica C.

2013-01-01

Biological and social networks are composed of heterogeneous nodes that contribute differentially to network structure and function. A number of algorithms have been developed to measure this variation. These algorithms have proven useful for applications that require assigning scores to individual nodes–from ranking websites to determining critical species in ecosystems–yet the mechanistic basis for why they produce good rankings remains poorly understood. We show that a unifying property of these algorithms is that they quantify consensus in the network about a node's state or capacity to perform a function. The algorithms capture consensus by either taking into account the number of a target node's direct connections, and, when the edges are weighted, the uniformity of its weighted in-degree distribution (breadth), or by measuring net flow into a target node (depth). Using data from communication, social, and biological networks we find that that how an algorithm measures consensus–through breadth or depth– impacts its ability to correctly score nodes. We also observe variation in sensitivity to source biases in interaction/adjacency matrices: errors arising from systematic error at the node level or direct manipulation of network connectivity by nodes. Our results indicate that the breadth algorithms, which are derived from information theory, correctly score nodes (assessed using independent data) and are robust to errors. However, in cases where nodes “form opinions” about other nodes using indirect information, like reputation, depth algorithms, like Eigenvector Centrality, are required. One caveat is that Eigenvector Centrality is not robust to error unless the network is transitive or assortative. In these cases the network structure allows the depth algorithms to effectively capture breadth as well as depth. Finally, we discuss the algorithms' cognitive and computational demands. This is an important consideration in systems in which individuals use the collective opinions of others to make decisions. PMID:23874167

An emerging network storage management standard: Media error monitoring and reporting information (MEMRI) - to determine optical tape data integrity

NASA Technical Reports Server (NTRS)

Podio, Fernando; Vollrath, William; Williams, Joel; Kobler, Ben; Crouse, Don

1998-01-01

Sophisticated network storage management applications are rapidly evolving to satisfy a market demand for highly reliable data storage systems with large data storage capacities and performance requirements. To preserve a high degree of data integrity, these applications must rely on intelligent data storage devices that can provide reliable indicators of data degradation. Error correction activity generally occurs within storage devices without notification to the host. Early indicators of degradation and media error monitoring 333 and reporting (MEMR) techniques implemented in data storage devices allow network storage management applications to notify system administrators of these events and to take appropriate corrective actions before catastrophic errors occur. Although MEMR techniques have been implemented in data storage devices for many years, until 1996 no MEMR standards existed. In 1996 the American National Standards Institute (ANSI) approved the only known (world-wide) industry standard specifying MEMR techniques to verify stored data on optical disks. This industry standard was developed under the auspices of the Association for Information and Image Management (AIIM). A recently formed AIIM Optical Tape Subcommittee initiated the development of another data integrity standard specifying a set of media error monitoring tools and media error monitoring information (MEMRI) to verify stored data on optical tape media. This paper discusses the need for intelligent storage devices that can provide data integrity metadata, the content of the existing data integrity standard for optical disks, and the content of the MEMRI standard being developed by the AIIM Optical Tape Subcommittee.

Reducing weight precision of convolutional neural networks towards large-scale on-chip image recognition

NASA Astrophysics Data System (ADS)

Ji, Zhengping; Ovsiannikov, Ilia; Wang, Yibing; Shi, Lilong; Zhang, Qiang

2015-05-01

In this paper, we develop a server-client quantization scheme to reduce bit resolution of deep learning architecture, i.e., Convolutional Neural Networks, for image recognition tasks. Low bit resolution is an important factor in bringing the deep learning neural network into hardware implementation, which directly determines the cost and power consumption. We aim to reduce the bit resolution of the network without sacrificing its performance. To this end, we design a new quantization algorithm called supervised iterative quantization to reduce the bit resolution of learned network weights. In the training stage, the supervised iterative quantization is conducted via two steps on server - apply k-means based adaptive quantization on learned network weights and retrain the network based on quantized weights. These two steps are alternated until the convergence criterion is met. In this testing stage, the network configuration and low-bit weights are loaded to the client hardware device to recognize coming input in real time, where optimized but expensive quantization becomes infeasible. Considering this, we adopt a uniform quantization for the inputs and internal network responses (called feature maps) to maintain low on-chip expenses. The Convolutional Neural Network with reduced weight and input/response precision is demonstrated in recognizing two types of images: one is hand-written digit images and the other is real-life images in office scenarios. Both results show that the new network is able to achieve the performance of the neural network with full bit resolution, even though in the new network the bit resolution of both weight and input are significantly reduced, e.g., from 64 bits to 4-5 bits.

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

PubMed

Zhao, Yu; Ge, Fangfei; Liu, Tianming

2018-07-01

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

Automated Detection of Clinically Significant Prostate Cancer in mp-MRI Images Based on an End-to-End Deep Neural Network.

PubMed

Wang, Zhiwei; Liu, Chaoyue; Cheng, Danpeng; Wang, Liang; Yang, Xin; Cheng, Kwang-Ting

2018-05-01

Automated methods for detecting clinically significant (CS) prostate cancer (PCa) in multi-parameter magnetic resonance images (mp-MRI) are of high demand. Existing methods typically employ several separate steps, each of which is optimized individually without considering the error tolerance of other steps. As a result, they could either involve unnecessary computational cost or suffer from errors accumulated over steps. In this paper, we present an automated CS PCa detection system, where all steps are optimized jointly in an end-to-end trainable deep neural network. The proposed neural network consists of concatenated subnets: 1) a novel tissue deformation network (TDN) for automated prostate detection and multimodal registration and 2) a dual-path convolutional neural network (CNN) for CS PCa detection. Three types of loss functions, i.e., classification loss, inconsistency loss, and overlap loss, are employed for optimizing all parameters of the proposed TDN and CNN. In the training phase, the two nets mutually affect each other and effectively guide registration and extraction of representative CS PCa-relevant features to achieve results with sufficient accuracy. The entire network is trained in a weakly supervised manner by providing only image-level annotations (i.e., presence/absence of PCa) without exact priors of lesions' locations. Compared with most existing systems which require supervised labels, e.g., manual delineation of PCa lesions, it is much more convenient for clinical usage. Comprehensive evaluation based on fivefold cross validation using 360 patient data demonstrates that our system achieves a high accuracy for CS PCa detection, i.e., a sensitivity of 0.6374 and 0.8978 at 0.1 and 1 false positives per normal/benign patient.

Why phase errors affect the electron function more than amplitude errors.

PubMed

Lattman, Eaton; DeRosier, David

2008-03-01

If Fexp(ialpha) are the set of structure factors for a structure f, the amplitudes can be converted to those of an uncorrelated structure g (amplitude swapping) by multiplying each F by the positive number G/F. Correspondingly, the image f is convoluted with k, the Fourier transform of G/F; k has a large peak at the origin, so that f * k approximately f. For swapped phases, the image f is convoluted with l, the Fourier transform of exp(iDeltaalpha), where Deltaalpha, the phase difference between F and G, is a random variable; l does not have a large peak at the origin, so that f * l does not resemble f. The paper provides quantitative descriptions of these arguments.

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

NASA Astrophysics Data System (ADS)

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.

Independent Oscillatory Patterns Determine Performance Fluctuations in Children with Attention Deficit/Hyperactivity Disorder

ERIC Educational Resources Information Center

Yordanova, Juliana; Albrecht, Bjorn; Uebel, Henrik; Kirov, Roumen; Banaschewski, Tobias; Rothenberger, Aribert; Kolev, Vasil

2011-01-01

The maintenance of stable goal-directed behaviour is a hallmark of conscious executive control in humans. Notably, both correct and error human actions may have a subconscious activation-based determination. One possible source of subconscious interference may be the default mode network that, in contrast to attentional network, manifests…

Assessment of second- and third-order ionospheric effects on regional networks: case study in China with longer CMONOC GPS coordinate time series

NASA Astrophysics Data System (ADS)

Deng, Liansheng; Jiang, Weiping; Li, Zhao; Chen, Hua; Wang, Kaihua; Ma, Yifang

2017-02-01

Higher-order ionospheric (HOI) delays are one of the principal technique-specific error sources in precise global positioning system analysis and have been proposed to become a standard part of precise GPS data processing. In this research, we apply HOI delay corrections to the Crustal Movement Observation Network of China's (CMONOC) data processing (from January 2000 to December 2013) and furnish quantitative results for the effects of HOI on CMONOC coordinate time series. The results for both a regional reference frame and global reference frame are analyzed and compared to clarify the HOI effects on the CMONOC network. We find that HOI corrections can effectively reduce the semi-annual signals in the northern and vertical components. For sites with lower semi-annual amplitudes, the average decrease in magnitude can reach 30 and 10 % for the northern and vertical components, respectively. The noise amplitudes with HOI corrections and those without HOI corrections are not significantly different. Generally, the HOI effects on CMONOC networks in a global reference frame are less obvious than the results in the regional reference frame, probably because the HOI-induced errors are smaller in comparison to the higher noise levels seen when using a global reference frame. Furthermore, we investigate the combined contributions of environmental loading and HOI effects on the CMONOC stations. The largest loading effects on the vertical displacement are found in the mid- to high-latitude areas. The weighted root mean square differences between the corrected and original weekly GPS height time series of the loading model indicate that the mass loading adequately reduced the scatter on the CMONOC height time series, whereas the results in the global reference frame showed better agreements between the GPS coordinate time series and the environmental loading. When combining the effects of environmental loading and HOI corrections, the results with the HOI corrections reduced the scatter on the observed GPS height coordinates better than the height when estimated without HOI corrections, and the combined solutions in the regional reference frame indicate more preferred improvements. Therefore, regional reference frames are recommended to investigate the HOI effects on regional networks.

Deep Convolutional Extreme Learning Machine and Its Application in Handwritten Digit Classification

PubMed Central

Yang, Xinyi

2016-01-01

In recent years, some deep learning methods have been developed and applied to image classification applications, such as convolutional neuron network (CNN) and deep belief network (DBN). However they are suffering from some problems like local minima, slow convergence rate, and intensive human intervention. In this paper, we propose a rapid learning method, namely, deep convolutional extreme learning machine (DC-ELM), which combines the power of CNN and fast training of ELM. It uses multiple alternate convolution layers and pooling layers to effectively abstract high level features from input images. Then the abstracted features are fed to an ELM classifier, which leads to better generalization performance with faster learning speed. DC-ELM also introduces stochastic pooling in the last hidden layer to reduce dimensionality of features greatly, thus saving much training time and computation resources. We systematically evaluated the performance of DC-ELM on two handwritten digit data sets: MNIST and USPS. Experimental results show that our method achieved better testing accuracy with significantly shorter training time in comparison with deep learning methods and other ELM methods. PMID:27610128

Alcoholism Detection by Data Augmentation and Convolutional Neural Network with Stochastic Pooling.

PubMed

Wang, Shui-Hua; Lv, Yi-Ding; Sui, Yuxiu; Liu, Shuai; Wang, Su-Jing; Zhang, Yu-Dong

2017-11-17

Alcohol use disorder (AUD) is an important brain disease. It alters the brain structure. Recently, scholars tend to use computer vision based techniques to detect AUD. We collected 235 subjects, 114 alcoholic and 121 non-alcoholic. Among the 235 image, 100 images were used as training set, and data augmentation method was used. The rest 135 images were used as test set. Further, we chose the latest powerful technique-convolutional neural network (CNN) based on convolutional layer, rectified linear unit layer, pooling layer, fully connected layer, and softmax layer. We also compared three different pooling techniques: max pooling, average pooling, and stochastic pooling. The results showed that our method achieved a sensitivity of 96.88%, a specificity of 97.18%, and an accuracy of 97.04%. Our method was better than three state-of-the-art approaches. Besides, stochastic pooling performed better than other max pooling and average pooling. We validated CNN with five convolution layers and two fully connected layers performed the best. The GPU yielded a 149× acceleration in training and a 166× acceleration in test, compared to CPU.

Deep Convolutional Extreme Learning Machine and Its Application in Handwritten Digit Classification.

PubMed

Pang, Shan; Yang, Xinyi

2016-01-01

In recent years, some deep learning methods have been developed and applied to image classification applications, such as convolutional neuron network (CNN) and deep belief network (DBN). However they are suffering from some problems like local minima, slow convergence rate, and intensive human intervention. In this paper, we propose a rapid learning method, namely, deep convolutional extreme learning machine (DC-ELM), which combines the power of CNN and fast training of ELM. It uses multiple alternate convolution layers and pooling layers to effectively abstract high level features from input images. Then the abstracted features are fed to an ELM classifier, which leads to better generalization performance with faster learning speed. DC-ELM also introduces stochastic pooling in the last hidden layer to reduce dimensionality of features greatly, thus saving much training time and computation resources. We systematically evaluated the performance of DC-ELM on two handwritten digit data sets: MNIST and USPS. Experimental results show that our method achieved better testing accuracy with significantly shorter training time in comparison with deep learning methods and other ELM methods.

Hybrid optical CDMA-FSO communications network under spatially correlated gamma-gamma scintillation.

PubMed

Jurado-Navas, Antonio; Raddo, Thiago R; Garrido-Balsells, José María; Borges, Ben-Hur V; Olmos, Juan José Vegas; Monroy, Idelfonso Tafur

2016-07-25

In this paper, we propose a new hybrid network solution based on asynchronous optical code-division multiple-access (OCDMA) and free-space optical (FSO) technologies for last-mile access networks, where fiber deployment is impractical. The architecture of the proposed hybrid OCDMA-FSO network is thoroughly described. The users access the network in a fully asynchronous manner by means of assigned fast frequency hopping (FFH)-based codes. In the FSO receiver, an equal gain-combining technique is employed along with intensity modulation and direct detection. New analytical formalisms for evaluating the average bit error rate (ABER) performance are also proposed. These formalisms, based on the spatially correlated gamma-gamma statistical model, are derived considering three distinct scenarios, namely, uncorrelated, totally correlated, and partially correlated channels. Numerical results show that users can successfully achieve error-free ABER levels for the three scenarios considered as long as forward error correction (FEC) algorithms are employed. Therefore, OCDMA-FSO networks can be a prospective alternative to deliver high-speed communication services to access networks with deficient fiber infrastructure.

Classifying medical relations in clinical text via convolutional neural networks.

PubMed

He, Bin; Guan, Yi; Dai, Rui

2018-05-16

Deep learning research on relation classification has achieved solid performance in the general domain. This study proposes a convolutional neural network (CNN) architecture with a multi-pooling operation for medical relation classification on clinical records and explores a loss function with a category-level constraint matrix. Experiments using the 2010 i2b2/VA relation corpus demonstrate these models, which do not depend on any external features, outperform previous single-model methods and our best model is competitive with the existing ensemble-based method. Copyright © 2018. Published by Elsevier B.V.

tf_unet: Generic convolutional neural network U-Net implementation in Tensorflow

NASA Astrophysics Data System (ADS)

Akeret, Joel; Chang, Chihway; Lucchi, Aurelien; Refregier, Alexandre

2016-11-01

tf_unet mitigates radio frequency interference (RFI) signals in radio data using a special type of Convolutional Neural Network, the U-Net, that enables the classification of clean signal and RFI signatures in 2D time-ordered data acquired from a radio telescope. The code is not tied to a specific segmentation and can be used, for example, to detect radio frequency interference (RFI) in radio astronomy or galaxies and stars in widefield imaging data. This U-Net implementation can outperform classical RFI mitigation algorithms.

PIV-DCNN: cascaded deep convolutional neural networks for particle image velocimetry

NASA Astrophysics Data System (ADS)

Lee, Yong; Yang, Hua; Yin, Zhouping

2017-12-01

Velocity estimation (extracting the displacement vector information) from the particle image pairs is of critical importance for particle image velocimetry. This problem is mostly transformed into finding the sub-pixel peak in a correlation map. To address the original displacement extraction problem, we propose a different evaluation scheme (PIV-DCNN) with four-level regression deep convolutional neural networks. At each level, the networks are trained to predict a vector from two input image patches. The low-level network is skilled at large displacement estimation and the high- level networks are devoted to improving the accuracy. Outlier replacement and symmetric window offset operation glue the well- functioning networks in a cascaded manner. Through comparison with the standard PIV methods (one-pass cross-correlation method, three-pass window deformation), the practicability of the proposed PIV-DCNN is verified by the application to a diversity of synthetic and experimental PIV images.

Dual Temporal Scale Convolutional Neural Network for Micro-Expression Recognition.

PubMed

Peng, Min; Wang, Chongyang; Chen, Tong; Liu, Guangyuan; Fu, Xiaolan

2017-01-01

Facial micro-expression is a brief involuntary facial movement and can reveal the genuine emotion that people try to conceal. Traditional methods of spontaneous micro-expression recognition rely excessively on sophisticated hand-crafted feature design and the recognition rate is not high enough for its practical application. In this paper, we proposed a Dual Temporal Scale Convolutional Neural Network (DTSCNN) for spontaneous micro-expressions recognition. The DTSCNN is a two-stream network. Different of stream of DTSCNN is used to adapt to different frame rate of micro-expression video clips. Each stream of DSTCNN consists of independent shallow network for avoiding the overfitting problem. Meanwhile, we fed the networks with optical-flow sequences to ensure that the shallow networks can further acquire higher-level features. Experimental results on spontaneous micro-expression databases (CASME I/II) showed that our method can achieve a recognition rate almost 10% higher than what some state-of-the-art method can achieve.

Deep learning classifier with optical coherence tomography images for early dental caries detection

NASA Astrophysics Data System (ADS)

Karimian, Nima; Salehi, Hassan S.; Mahdian, Mina; Alnajjar, Hisham; Tadinada, Aditya

2018-02-01

Dental caries is a microbial disease that results in localized dissolution of the mineral content of dental tissue. Despite considerable decline in the incidence of dental caries, it remains a major health problem in many societies. Early detection of incipient lesions at initial stages of demineralization can result in the implementation of non-surgical preventive approaches to reverse the demineralization process. In this paper, we present a novel approach combining deep convolutional neural networks (CNN) and optical coherence tomography (OCT) imaging modality for classification of human oral tissues to detect early dental caries. OCT images of oral tissues with various densities were input to a CNN classifier to determine variations in tissue densities resembling the demineralization process. The CNN automatically learns a hierarchy of increasingly complex features and a related classifier directly from training data sets. The initial CNN layer parameters were randomly selected. The training set is split into minibatches, with 10 OCT images per batch. Given a batch of training patches, the CNN employs two convolutional and pooling layers to extract features and then classify each patch based on the probabilities from the SoftMax classification layer (output-layer). Afterward, the CNN calculates the error between the classification result and the reference label, and then utilizes the backpropagation process to fine-tune all the layer parameters to minimize this error using batch gradient descent algorithm. We validated our proposed technique on ex-vivo OCT images of human oral tissues (enamel, cortical-bone, trabecular-bone, muscular-tissue, and fatty-tissue), which attested to effectiveness of our proposed method.

Deformable image registration using convolutional neural networks

NASA Astrophysics Data System (ADS)

Eppenhof, Koen A. J.; Lafarge, Maxime W.; Moeskops, Pim; Veta, Mitko; Pluim, Josien P. W.

2018-03-01

Deformable image registration can be time-consuming and often needs extensive parameterization to perform well on a specific application. We present a step towards a registration framework based on a three-dimensional convolutional neural network. The network directly learns transformations between pairs of three-dimensional images. The outputs of the network are three maps for the x, y, and z components of a thin plate spline transformation grid. The network is trained on synthetic random transformations, which are applied to a small set of representative images for the desired application. Training therefore does not require manually annotated ground truth deformation information. The methodology is demonstrated on public data sets of inspiration-expiration lung CT image pairs, which come with annotated corresponding landmarks for evaluation of the registration accuracy. Advantages of this methodology are its fast registration times and its minimal parameterization.

Training strategy for convolutional neural networks in pedestrian gender classification

NASA Astrophysics Data System (ADS)

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.

Going Deeper With Contextual CNN for Hyperspectral Image Classification.

PubMed

Lee, Hyungtae; Kwon, Heesung

2017-10-01

In this paper, we describe a novel deep convolutional neural network (CNN) that is deeper and wider than other existing deep networks for hyperspectral image classification. Unlike current state-of-the-art approaches in CNN-based hyperspectral image classification, the proposed network, called contextual deep CNN, can optimally explore local contextual interactions by jointly exploiting local spatio-spectral relationships of neighboring individual pixel vectors. The joint exploitation of the spatio-spectral information is achieved by a multi-scale convolutional filter bank used as an initial component of the proposed CNN pipeline. The initial spatial and spectral feature maps obtained from the multi-scale filter bank are then combined together to form a joint spatio-spectral feature map. The joint feature map representing rich spectral and spatial properties of the hyperspectral image is then fed through a fully convolutional network that eventually predicts the corresponding label of each pixel vector. The proposed approach is tested on three benchmark data sets: the Indian Pines data set, the Salinas data set, and the University of Pavia data set. Performance comparison shows enhanced classification performance of the proposed approach over the current state-of-the-art on the three data sets.

Convolutional Neural Network for Histopathological Analysis of Osteosarcoma.

PubMed

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.

Multi-Level and Multi-Scale Feature Aggregation Using Pretrained Convolutional Neural Networks for Music Auto-Tagging

NASA Astrophysics Data System (ADS)

Lee, Jongpil; Nam, Juhan

2017-08-01

Music auto-tagging is often handled in a similar manner to image classification by regarding the 2D audio spectrogram as image data. However, music auto-tagging is distinguished from image classification in that the tags are highly diverse and have different levels of abstractions. Considering this issue, we propose a convolutional neural networks (CNN)-based architecture that embraces multi-level and multi-scaled features. The architecture is trained in three steps. First, we conduct supervised feature learning to capture local audio features using a set of CNNs with different input sizes. Second, we extract audio features from each layer of the pre-trained convolutional networks separately and aggregate them altogether given a long audio clip. Finally, we put them into fully-connected networks and make final predictions of the tags. Our experiments show that using the combination of multi-level and multi-scale features is highly effective in music auto-tagging and the proposed method outperforms previous state-of-the-arts on the MagnaTagATune dataset and the Million Song Dataset. We further show that the proposed architecture is useful in transfer learning.

Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition.

PubMed

Ordóñez, Francisco Javier; Roggen, Daniel

2016-01-18

Human activity recognition (HAR) tasks have traditionally been solved using engineered features obtained by heuristic processes. Current research suggests that deep convolutional neural networks are suited to automate feature extraction from raw sensor inputs. However, human activities are made of complex sequences of motor movements, and capturing this temporal dynamics is fundamental for successful HAR. Based on the recent success of recurrent neural networks for time series domains, we propose a generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which: (i) is suitable for multimodal wearable sensors; (ii) can perform sensor fusion naturally; (iii) does not require expert knowledge in designing features; and (iv) explicitly models the temporal dynamics of feature activations. We evaluate our framework on two datasets, one of which has been used in a public activity recognition challenge. Our results show that our framework outperforms competing deep non-recurrent networks on the challenge dataset by 4% on average; outperforming some of the previous reported results by up to 9%. Our results show that the framework can be applied to homogeneous sensor modalities, but can also fuse multimodal sensors to improve performance. We characterise key architectural hyperparameters' influence on performance to provide insights about their optimisation.

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

NASA Astrophysics Data System (ADS)

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

2018-01-01

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

Single-shot T2 mapping using overlapping-echo detachment planar imaging and a deep convolutional neural network.

PubMed

Cai, Congbo; Wang, Chao; Zeng, Yiqing; Cai, Shuhui; Liang, Dong; Wu, Yawen; Chen, Zhong; Ding, Xinghao; Zhong, Jianhui

2018-04-24

An end-to-end deep convolutional neural network (CNN) based on deep residual network (ResNet) was proposed to efficiently reconstruct reliable T 2 mapping from single-shot overlapping-echo detachment (OLED) planar imaging. The training dataset was obtained from simulations that were carried out on SPROM (Simulation with PRoduct Operator Matrix) software developed by our group. The relationship between the original OLED image containing two echo signals and the corresponding T 2 mapping was learned by ResNet training. After the ResNet was trained, it was applied to reconstruct the T 2 mapping from simulation and in vivo human brain data. Although the ResNet was trained entirely on simulated data, the trained network was generalized well to real human brain data. The results from simulation and in vivo human brain experiments show that the proposed method significantly outperforms the echo-detachment-based method. Reliable T 2 mapping with higher accuracy is achieved within 30 ms after the network has been trained, while the echo-detachment-based OLED reconstruction method took approximately 2 min. The proposed method will facilitate real-time dynamic and quantitative MR imaging via OLED sequence, and deep convolutional neural network has the potential to reconstruct maps from complex MRI sequences efficiently. © 2018 International Society for Magnetic Resonance in Medicine.

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

NASA Astrophysics Data System (ADS)

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.

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

NASA Astrophysics Data System (ADS)

Guo, Dongwei; Wang, Zhe

2018-05-01

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

A method to correct sampling ghosts in historic near-infrared Fourier transform spectrometer (FTS) measurements

NASA Astrophysics Data System (ADS)

Dohe, S.; Sherlock, V.; Hase, F.; Gisi, M.; Robinson, J.; Sepúlveda, E.; Schneider, M.; Blumenstock, T.

2013-08-01

The Total Carbon Column Observing Network (TCCON) has been established to provide ground-based remote sensing measurements of the column-averaged dry air mole fractions (DMF) of key greenhouse gases. To ensure network-wide consistency, biases between Fourier transform spectrometers at different sites have to be well controlled. Errors in interferogram sampling can introduce significant biases in retrievals. In this study we investigate a two-step scheme to correct these errors. In the first step the laser sampling error (LSE) is estimated by determining the sampling shift which minimises the magnitude of the signal intensity in selected, fully absorbed regions of the solar spectrum. The LSE is estimated for every day with measurements which meet certain selection criteria to derive the site-specific time series of the LSEs. In the second step, this sequence of LSEs is used to resample all the interferograms acquired at the site, and hence correct the sampling errors. Measurements acquired at the Izaña and Lauder TCCON sites are used to demonstrate the method. At both sites the sampling error histories show changes in LSE due to instrument interventions (e.g. realignment). Estimated LSEs are in good agreement with sampling errors inferred from the ratio of primary and ghost spectral signatures in optically bandpass-limited tungsten lamp spectra acquired at Lauder. The original time series of Xair and XCO2 (XY: column-averaged DMF of the target gas Y) at both sites show discrepancies of 0.2-0.5% due to changes in the LSE associated with instrument interventions or changes in the measurement sample rate. After resampling, discrepancies are reduced to 0.1% or less at Lauder and 0.2% at Izaña. In the latter case, coincident changes in interferometer alignment may also have contributed to the residual difference. In the future the proposed method will be used to correct historical spectra at all TCCON sites.

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

PubMed

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

2017-01-01

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

Dermoscopic Image Segmentation via Multistage Fully Convolutional Networks.

PubMed

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.

Artificial neural network implementation of a near-ideal error prediction controller

NASA Technical Reports Server (NTRS)

Mcvey, Eugene S.; Taylor, Lynore Denise

1992-01-01

A theory has been developed at the University of Virginia which explains the effects of including an ideal predictor in the forward loop of a linear error-sampled system. It has been shown that the presence of this ideal predictor tends to stabilize the class of systems considered. A prediction controller is merely a system which anticipates a signal or part of a signal before it actually occurs. It is understood that an exact prediction controller is physically unrealizable. However, in systems where the input tends to be repetitive or limited, (i.e., not random) near ideal prediction is possible. In order for the controller to act as a stability compensator, the predictor must be designed in a way that allows it to learn the expected error response of the system. In this way, an unstable system will become stable by including the predicted error in the system transfer function. Previous and current prediction controller include pattern recognition developments and fast-time simulation which are applicable to the analysis of linear sampled data type systems. The use of pattern recognition techniques, along with a template matching scheme, has been proposed as one realizable type of near-ideal prediction. Since many, if not most, systems are repeatedly subjected to similar inputs, it was proposed that an adaptive mechanism be used to 'learn' the correct predicted error response. Once the system has learned the response of all the expected inputs, it is necessary only to recognize the type of input with a template matching mechanism and then to use the correct predicted error to drive the system. Suggested here is an alternate approach to the realization of a near-ideal error prediction controller, one designed using Neural Networks. Neural Networks are good at recognizing patterns such as system responses, and the back-propagation architecture makes use of a template matching scheme. In using this type of error prediction, it is assumed that the system error responses be known for a particular input and modeled plant. These responses are used in the error prediction controller. An analysis was done on the general dynamic behavior that results from including a digital error predictor in a control loop and these were compared to those including the near-ideal Neural Network error predictor. This analysis was done for a second and third order system.

Chromatin accessibility prediction via convolutional long short-term memory networks with k-mer embedding.

PubMed

Min, Xu; Zeng, Wanwen; Chen, Ning; Chen, Ting; Jiang, Rui

2017-07-15

Experimental techniques for measuring chromatin accessibility are expensive and time consuming, appealing for the development of computational approaches to predict open chromatin regions from DNA sequences. Along this direction, existing methods fall into two classes: one based on handcrafted k -mer features and the other based on convolutional neural networks. Although both categories have shown good performance in specific applications thus far, there still lacks a comprehensive framework to integrate useful k -mer co-occurrence information with recent advances in deep learning. We fill this gap by addressing the problem of chromatin accessibility prediction with a convolutional Long Short-Term Memory (LSTM) network with k -mer embedding. We first split DNA sequences into k -mers and pre-train k -mer embedding vectors based on the co-occurrence matrix of k -mers by using an unsupervised representation learning approach. We then construct a supervised deep learning architecture comprised of an embedding layer, three convolutional layers and a Bidirectional LSTM (BLSTM) layer for feature learning and classification. We demonstrate that our method gains high-quality fixed-length features from variable-length sequences and consistently outperforms baseline methods. We show that k -mer embedding can effectively enhance model performance by exploring different embedding strategies. We also prove the efficacy of both the convolution and the BLSTM layers by comparing two variations of the network architecture. We confirm the robustness of our model to hyper-parameters by performing sensitivity analysis. We hope our method can eventually reinforce our understanding of employing deep learning in genomic studies and shed light on research regarding mechanisms of chromatin accessibility. The source code can be downloaded from https://github.com/minxueric/ismb2017_lstm . tingchen@tsinghua.edu.cn or ruijiang@tsinghua.edu.cn. Supplementary materials are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

Chromatin accessibility prediction via convolutional long short-term memory networks with k-mer embedding

PubMed Central

Min, Xu; Zeng, Wanwen; Chen, Ning; Chen, Ting; Jiang, Rui

2017-01-01

Abstract Motivation: Experimental techniques for measuring chromatin accessibility are expensive and time consuming, appealing for the development of computational approaches to predict open chromatin regions from DNA sequences. Along this direction, existing methods fall into two classes: one based on handcrafted k-mer features and the other based on convolutional neural networks. Although both categories have shown good performance in specific applications thus far, there still lacks a comprehensive framework to integrate useful k-mer co-occurrence information with recent advances in deep learning. Results: We fill this gap by addressing the problem of chromatin accessibility prediction with a convolutional Long Short-Term Memory (LSTM) network with k-mer embedding. We first split DNA sequences into k-mers and pre-train k-mer embedding vectors based on the co-occurrence matrix of k-mers by using an unsupervised representation learning approach. We then construct a supervised deep learning architecture comprised of an embedding layer, three convolutional layers and a Bidirectional LSTM (BLSTM) layer for feature learning and classification. We demonstrate that our method gains high-quality fixed-length features from variable-length sequences and consistently outperforms baseline methods. We show that k-mer embedding can effectively enhance model performance by exploring different embedding strategies. We also prove the efficacy of both the convolution and the BLSTM layers by comparing two variations of the network architecture. We confirm the robustness of our model to hyper-parameters by performing sensitivity analysis. We hope our method can eventually reinforce our understanding of employing deep learning in genomic studies and shed light on research regarding mechanisms of chromatin accessibility. Availability and implementation: The source code can be downloaded from https://github.com/minxueric/ismb2017_lstm. Contact: tingchen@tsinghua.edu.cn or ruijiang@tsinghua.edu.cn Supplementary information: Supplementary materials are available at Bioinformatics online. PMID:28881969

Fabric defect detection based on faster R-CNN

NASA Astrophysics Data System (ADS)

Liu, Zhoufeng; Liu, Xianghui; Li, Chunlei; Li, Bicao; Wang, Baorui

2018-04-01

In order to effectively detect the defects for fabric image with complex texture, this paper proposed a novel detection algorithm based on an end-to-end convolutional neural network. First, the proposal regions are generated by RPN (regional proposal Network). Then, Fast Region-based Convolutional Network method (Fast R-CNN) is adopted to determine whether the proposal regions extracted by RPN is a defect or not. Finally, Soft-NMS (non-maximum suppression) and data augmentation strategies are utilized to improve the detection precision. Experimental results demonstrate that the proposed method can locate the fabric defect region with higher accuracy compared with the state-of- art, and has better adaptability to all kinds of the fabric image.

SU-E-T-371: Evaluating the Convolution Algorithm of a Commercially Available Radiosurgery Irradiator Using a Novel Phantom

DOE Office of Scientific and Technical Information (OSTI.GOV)

Cates, J; Drzymala, R

2015-06-15

Purpose: The purpose of this study was to develop and use a novel phantom to evaluate the accuracy and usefulness of the Leskell Gamma Plan convolution-based dose calculation algorithm compared with the current TMR10 algorithm. Methods: A novel phantom was designed to fit the Leskell Gamma Knife G Frame which could accommodate various materials in the form of one inch diameter, cylindrical plugs. The plugs were split axially to allow EBT2 film placement. Film measurements were made during two experiments. The first utilized plans generated on a homogeneous acrylic phantom setup using the TMR10 algorithm, with various materials inserted intomore » the phantom during film irradiation to assess the effect on delivered dose due to unplanned heterogeneities upstream in the beam path. The second experiment utilized plans made on CT scans of different heterogeneous setups, with one plan using the TMR10 dose calculation algorithm and the second using the convolution-based algorithm. Materials used to introduce heterogeneities included air, LDPE, polystyrene, Delrin, Teflon, and aluminum. Results: The data shows that, as would be expected, having heterogeneities in the beam path does induce dose delivery error when using the TMR10 algorithm, with the largest errors being due to the heterogeneities with electron densities most different from that of water, i.e. air, Teflon, and aluminum. Additionally, the Convolution algorithm did account for the heterogeneous material and provided a more accurate predicted dose, in extreme cases up to a 7–12% improvement over the TMR10 algorithm. The convolution algorithm expected dose was accurate to within 3% in all cases. Conclusion: This study proves that the convolution algorithm is an improvement over the TMR10 algorithm when heterogeneities are present. More work is needed to determine what the heterogeneity size/volume limits are where this improvement exists, and in what clinical and/or research cases this would be relevant.« less

Compression of digital images over local area networks. Appendix 1: Item 3. M.S. Thesis

NASA Technical Reports Server (NTRS)

Gorjala, Bhargavi

1991-01-01

Differential Pulse Code Modulation (DPCM) has been used with speech for many years. It has not been as successful for images because of poor edge performance. The only corruption in DPC is quantizer error but this corruption becomes quite large in the region of an edge because of the abrupt changes in the statistics of the signal. We introduce two improved DPCM schemes; Edge correcting DPCM and Edge Preservation Differential Coding. These two coding schemes will detect the edges and take action to correct them. In an Edge Correcting scheme, the quantizer error for an edge is encoded using a recursive quantizer with entropy coding and sent to the receiver as side information. In an Edge Preserving scheme, when the quantizer input falls in the overload region, the quantizer error is encoded and sent to the receiver repeatedly until the quantizer input falls in the inner levels. Therefore these coding schemes increase the bit rate in the region of an edge and require variable rate channels. We implement these two variable rate coding schemes on a token wing network. Timed token protocol supports two classes of messages; asynchronous and synchronous. The synchronous class provides a pre-allocated bandwidth and guaranteed response time. The remaining bandwidth is dynamically allocated to the asynchronous class. The Edge Correcting DPCM is simulated by considering the edge information under the asynchronous class. For the simulation of the Edge Preserving scheme, the amount of information sent each time is fixed, but the length of the packet or the bit rate for that packet is chosen depending on the availability capacity. The performance of the network, and the performance of the image coding algorithms, is studied.

Cascaded Segmentation-Detection Networks for Word-Level Text Spotting.

PubMed

Qin, Siyang; Manduchi, Roberto

2017-11-01

We introduce an algorithm for word-level text spotting that is able to accurately and reliably determine the bounding regions of individual words of text "in the wild". Our system is formed by the cascade of two convolutional neural networks. The first network is fully convolutional and is in charge of detecting areas containing text. This results in a very reliable but possibly inaccurate segmentation of the input image. The second network (inspired by the popular YOLO architecture) analyzes each segment produced in the first stage, and predicts oriented rectangular regions containing individual words. No post-processing (e.g. text line grouping) is necessary. With execution time of 450 ms for a 1000 × 560 image on a Titan X GPU, our system achieves good performance on the ICDAR 2013, 2015 benchmarks [2], [1].

Minimal entropy reconstructions of thermal images for emissivity correction

NASA Astrophysics Data System (ADS)

Allred, Lloyd G.

1999-03-01

Low emissivity with corresponding low thermal emission is a problem which has long afflicted infrared thermography. The problem is aggravated by reflected thermal energy which increases as the emissivity decreases, thus reducing the net signal-to-noise ratio, which degrades the resulting temperature reconstructions. Additional errors are introduced from the traditional emissivity-correction approaches, wherein one attempts to correct for emissivity either using thermocouples or using one or more baseline images, collected at known temperatures. These corrections are numerically equivalent to image differencing. Errors in the baseline images are therefore additive, causing the resulting measurement error to either double or triple. The practical application of thermal imagery usually entails coating the objective surface to increase the emissivity to a uniform and repeatable value. While the author recommends that the thermographer still adhere to this practice, he has devised a minimal entropy reconstructions which not only correct for emissivity variations, but also corrects for variations in sensor response, using the baseline images at known temperatures to correct for these values. The minimal energy reconstruction is actually based on a modified Hopfield neural network which finds the resulting image which best explains the observed data and baseline data, having minimal entropy change between adjacent pixels. The autocorrelation of temperatures between adjacent pixels is a feature of most close-up thermal images. A surprising result from transient heating data indicates that the resulting corrected thermal images have less measurement error and are closer to the situational truth than the original data.

Automatic sleep stage classification of single-channel EEG by using complex-valued convolutional neural network.

PubMed

Zhang, Junming; Wu, Yan

2018-03-28

Many systems are developed for automatic sleep stage classification. However, nearly all models are based on handcrafted features. Because of the large feature space, there are so many features that feature selection should be used. Meanwhile, designing handcrafted features is a difficult and time-consuming task because the feature designing needs domain knowledge of experienced experts. Results vary when different sets of features are chosen to identify sleep stages. Additionally, many features that we may be unaware of exist. However, these features may be important for sleep stage classification. Therefore, a new sleep stage classification system, which is based on the complex-valued convolutional neural network (CCNN), is proposed in this study. Unlike the existing sleep stage methods, our method can automatically extract features from raw electroencephalography data and then classify sleep stage based on the learned features. Additionally, we also prove that the decision boundaries for the real and imaginary parts of a complex-valued convolutional neuron intersect orthogonally. The classification performances of handcrafted features are compared with those of learned features via CCNN. Experimental results show that the proposed method is comparable to the existing methods. CCNN obtains a better classification performance and considerably faster convergence speed than convolutional neural network. Experimental results also show that the proposed method is a useful decision-support tool for automatic sleep stage classification.

A model of traffic signs recognition with convolutional neural network

NASA Astrophysics Data System (ADS)

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.

Recurrent Convolutional Neural Networks: A Better Model of Biological Object Recognition.

PubMed

Spoerer, Courtney J; McClure, Patrick; Kriegeskorte, Nikolaus

2017-01-01

Feedforward neural networks provide the dominant model of how the brain performs visual object recognition. However, these networks lack the lateral and feedback connections, and the resulting recurrent neuronal dynamics, of the ventral visual pathway in the human and non-human primate brain. Here we investigate recurrent convolutional neural networks with bottom-up (B), lateral (L), and top-down (T) connections. Combining these types of connections yields four architectures (B, BT, BL, and BLT), which we systematically test and compare. We hypothesized that recurrent dynamics might improve recognition performance in the challenging scenario of partial occlusion. We introduce two novel occluded object recognition tasks to test the efficacy of the models, digit clutter (where multiple target digits occlude one another) and digit debris (where target digits are occluded by digit fragments). We find that recurrent neural networks outperform feedforward control models (approximately matched in parametric complexity) at recognizing objects, both in the absence of occlusion and in all occlusion conditions. Recurrent networks were also found to be more robust to the inclusion of additive Gaussian noise. Recurrent neural networks are better in two respects: (1) they are more neurobiologically realistic than their feedforward counterparts; (2) they are better in terms of their ability to recognize objects, especially under challenging conditions. This work shows that computer vision can benefit from using recurrent convolutional architectures and suggests that the ubiquitous recurrent connections in biological brains are essential for task performance.

Air Temperature Error Correction Based on Solar Radiation in an Economical Meteorological Wireless Sensor Network

PubMed Central

Sun, Xingming; Yan, Shuangshuang; Wang, Baowei; Xia, Li; Liu, Qi; Zhang, Hui

2015-01-01

Air temperature (AT) is an extremely vital factor in meteorology, agriculture, military, etc., being used for the prediction of weather disasters, such as drought, flood, frost, etc. Many efforts have been made to monitor the temperature of the atmosphere, like automatic weather stations (AWS). Nevertheless, due to the high cost of specialized AT sensors, they cannot be deployed within a large spatial density. A novel method named the meteorology wireless sensor network relying on a sensing node has been proposed for the purpose of reducing the cost of AT monitoring. However, the temperature sensor on the sensing node can be easily influenced by environmental factors. Previous research has confirmed that there is a close relation between AT and solar radiation (SR). Therefore, this paper presents a method to decrease the error of sensed AT, taking SR into consideration. In this work, we analyzed all of the collected data of AT and SR in May 2014 and found the numerical correspondence between AT error (ATE) and SR. This corresponding relation was used to calculate real-time ATE according to real-time SR and to correct the error of AT in other months. PMID:26213941

Air Temperature Error Correction Based on Solar Radiation in an Economical Meteorological Wireless Sensor Network.

PubMed

Sun, Xingming; Yan, Shuangshuang; Wang, Baowei; Xia, Li; Liu, Qi; Zhang, Hui

2015-07-24

Air temperature (AT) is an extremely vital factor in meteorology, agriculture, military, etc., being used for the prediction of weather disasters, such as drought, flood, frost, etc. Many efforts have been made to monitor the temperature of the atmosphere, like automatic weather stations (AWS). Nevertheless, due to the high cost of specialized AT sensors, they cannot be deployed within a large spatial density. A novel method named the meteorology wireless sensor network relying on a sensing node has been proposed for the purpose of reducing the cost of AT monitoring. However, the temperature sensor on the sensing node can be easily influenced by environmental factors. Previous research has confirmed that there is a close relation between AT and solar radiation (SR). Therefore, this paper presents a method to decrease the error of sensed AT, taking SR into consideration. In this work, we analyzed all of the collected data of AT and SR in May 2014 and found the numerical correspondence between AT error (ATE) and SR. This corresponding relation was used to calculate real-time ATE according to real-time SR and to correct the error of AT in other months.

Deep feature representation with stacked sparse auto-encoder and convolutional neural network for hyperspectral imaging-based detection of cucumber defects

USDA-ARS?s Scientific Manuscript database

It is challenging to achieve rapid and accurate processing of large amounts of hyperspectral image data. This research was aimed to develop a novel classification method by employing deep feature representation with the stacked sparse auto-encoder (SSAE) and the SSAE combined with convolutional neur...

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

PubMed

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

2017-04-10

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

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

PubMed Central

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

2017-01-01

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks. PMID:28394270

The discriminatory cost of ICD-10-CM transition between clinical specialties: metrics, case study, and mitigating tools

PubMed Central

Boyd, Andrew D; Li, Jianrong ‘John’; Burton, Mike D; Jonen, Michael; Gardeux, Vincent; Achour, Ikbel; Luo, Roger Q; Zenku, Ilir; Bahroos, Neil; Brown, Stephen B; Vanden Hoek, Terry; Lussier, Yves A

2013-01-01

Objective Applying the science of networks to quantify the discriminatory impact of the ICD-9-CM to ICD-10-CM transition between clinical specialties. Materials and Methods Datasets were the Center for Medicaid and Medicare Services ICD-9-CM to ICD-10-CM mapping files, general equivalence mappings, and statewide Medicaid emergency department billing. Diagnoses were represented as nodes and their mappings as directional relationships. The complex network was synthesized as an aggregate of simpler motifs and tabulation per clinical specialty. Results We identified five mapping motif categories: identity, class-to-subclass, subclass-to-class, convoluted, and no mapping. Convoluted mappings indicate that multiple ICD-9-CM and ICD-10-CM codes share complex, entangled, and non-reciprocal mappings. The proportions of convoluted diagnoses mappings (36% overall) range from 5% (hematology) to 60% (obstetrics and injuries). In a case study of 24 008 patient visits in 217 emergency departments, 27% of the costs are associated with convoluted diagnoses, with ‘abdominal pain’ and ‘gastroenteritis’ accounting for approximately 3.5%. Discussion Previous qualitative studies report that administrators and clinicians are likely to be challenged in understanding and managing their practice because of the ICD-10-CM transition. We substantiate the complexity of this transition with a thorough quantitative summary per clinical specialty, a case study, and the tools to apply this methodology easily to any clinical practice in the form of a web portal and analytic tables. Conclusions Post-transition, successful management of frequent diseases with convoluted mapping network patterns is critical. The http://lussierlab.org/transition-to-ICD10CM web portal provides insight in linking onerous diseases to the ICD-10 transition. PMID:23645552

Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition

PubMed Central

Kheradpisheh, Saeed Reza; Ghodrati, Masoud; Ganjtabesh, Mohammad; Masquelier, Timothée

2016-01-01

Deep convolutional neural networks (DCNNs) have attracted much attention recently, and have shown to be able to recognize thousands of object categories in natural image databases. Their architecture is somewhat similar to that of the human visual system: both use restricted receptive fields, and a hierarchy of layers which progressively extract more and more abstracted features. Yet it is unknown whether DCNNs match human performance at the task of view-invariant object recognition, whether they make similar errors and use similar representations for this task, and whether the answers depend on the magnitude of the viewpoint variations. To investigate these issues, we benchmarked eight state-of-the-art DCNNs, the HMAX model, and a baseline shallow model and compared their results to those of humans with backward masking. Unlike in all previous DCNN studies, we carefully controlled the magnitude of the viewpoint variations to demonstrate that shallow nets can outperform deep nets and humans when variations are weak. When facing larger variations, however, more layers were needed to match human performance and error distributions, and to have representations that are consistent with human behavior. A very deep net with 18 layers even outperformed humans at the highest variation level, using the most human-like representations. PMID:27601096

Weed Growth Stage Estimator Using Deep Convolutional Neural Networks.

PubMed

Teimouri, Nima; Dyrmann, Mads; Nielsen, Per Rydahl; Mathiassen, Solvejg Kopp; Somerville, Gayle J; Jørgensen, Rasmus Nyholm

2018-05-16

This study outlines a new method of automatically estimating weed species and growth stages (from cotyledon until eight leaves are visible) of in situ images covering 18 weed species or families. Images of weeds growing within a variety of crops were gathered across variable environmental conditions with regards to soil types, resolution and light settings. Then, 9649 of these images were used for training the computer, which automatically divided the weeds into nine growth classes. The performance of this proposed convolutional neural network approach was evaluated on a further set of 2516 images, which also varied in term of crop, soil type, image resolution and light conditions. The overall performance of this approach achieved a maximum accuracy of 78% for identifying Polygonum spp. and a minimum accuracy of 46% for blackgrass. In addition, it achieved an average 70% accuracy rate in estimating the number of leaves and 96% accuracy when accepting a deviation of two leaves. These results show that this new method of using deep convolutional neural networks has a relatively high ability to estimate early growth stages across a wide variety of weed species.

Tooth labeling in cone-beam CT using deep convolutional neural network for forensic identification

NASA Astrophysics Data System (ADS)

Miki, Yuma; Muramatsu, Chisako; Hayashi, Tatsuro; Zhou, Xiangrong; Hara, Takeshi; Katsumata, Akitoshi; Fujita, Hiroshi

2017-03-01

In large disasters, dental record plays an important role in forensic identification. However, filing dental charts for corpses is not an easy task for general dentists. Moreover, it is laborious and time-consuming work in cases of large scale disasters. We have been investigating a tooth labeling method on dental cone-beam CT images for the purpose of automatic filing of dental charts. In our method, individual tooth in CT images are detected and classified into seven tooth types using deep convolutional neural network. We employed the fully convolutional network using AlexNet architecture for detecting each tooth and applied our previous method using regular AlexNet for classifying the detected teeth into 7 tooth types. From 52 CT volumes obtained by two imaging systems, five images each were randomly selected as test data, and the remaining 42 cases were used as training data. The result showed the tooth detection accuracy of 77.4% with the average false detection of 5.8 per image. The result indicates the potential utility of the proposed method for automatic recording of dental information.

Virus Particle Detection by Convolutional Neural Network in Transmission Electron Microscopy Images.

PubMed

Ito, Eisuke; Sato, Takaaki; Sano, Daisuke; Utagawa, Etsuko; Kato, Tsuyoshi

2018-06-01

A new computational method for the detection of virus particles in transmission electron microscopy (TEM) images is presented. Our approach is to use a convolutional neural network that transforms a TEM image to a probabilistic map that indicates where virus particles exist in the image. Our proposed approach automatically and simultaneously learns both discriminative features and classifier for virus particle detection by machine learning, in contrast to existing methods that are based on handcrafted features that yield many false positives and require several postprocessing steps. The detection performance of the proposed method was assessed against a dataset of TEM images containing feline calicivirus particles and compared with several existing detection methods, and the state-of-the-art performance of the developed method for detecting virus was demonstrated. Since our method is based on supervised learning that requires both the input images and their corresponding annotations, it is basically used for detection of already-known viruses. However, the method is highly flexible, and the convolutional networks can adapt themselves to any virus particles by learning automatically from an annotated dataset.

Classification of stroke disease using convolutional neural network

NASA Astrophysics Data System (ADS)

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.

Yarn-dyed fabric defect classification based on convolutional neural network

NASA Astrophysics Data System (ADS)

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

2017-09-01

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

Yarn-dyed fabric defect classification based on convolutional neural network

NASA Astrophysics Data System (ADS)

Jing, Junfeng; Dong, Amei; Li, Pengfei

2017-07-01

Considering that the manual inspection of the yarn-dyed fabric can be time consuming and less efficient, a convolutional neural network (CNN) solution based on the modified AlexNet structure for the classification of the yarn-dyed fabric defect is proposed. CNN has powerful ability of feature extraction and feature fusion which can simulate the learning mechanism of the human brain. In order to enhance computational efficiency and detection accuracy, the local response normalization (LRN) layers in AlexNet are replaced by the batch normalization (BN) layers. In the process of the network training, through several convolution operations, the characteristics of the image are extracted step by step, and the essential features of the image can be obtained from the edge features. And the max pooling layers, the dropout layers, the fully connected layers are also employed in the classification model to reduce the computation cost and acquire more precise features of fabric defect. Finally, the results of the defect classification are predicted by the softmax function. The experimental results show the capability of defect classification via the modified Alexnet model and indicate its robustness.

CNNdel: Calling Structural Variations on Low Coverage Data Based on Convolutional Neural Networks

PubMed Central

2017-01-01

Many structural variations (SVs) detection methods have been proposed due to the popularization of next-generation sequencing (NGS). These SV calling methods use different SV-property-dependent features; however, they all suffer from poor accuracy when running on low coverage sequences. The union of results from these tools achieves fairly high sensitivity but still produces low accuracy on low coverage sequence data. That is, these methods contain many false positives. In this paper, we present CNNdel, an approach for calling deletions from paired-end reads. CNNdel gathers SV candidates reported by multiple tools and then extracts features from aligned BAM files at the positions of candidates. With labeled feature-expressed candidates as a training set, CNNdel trains convolutional neural networks (CNNs) to distinguish true unlabeled candidates from false ones. Results show that CNNdel works well with NGS reads from 26 low coverage genomes of the 1000 Genomes Project. The paper demonstrates that convolutional neural networks can automatically assign the priority of SV features and reduce the false positives efficaciously. PMID:28630866

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

PubMed

Valdes, Gilmer; Interian, Yannet

2018-03-15

The application of machine learning (ML) presents tremendous opportunities for the field of oncology, thus we read 'Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study' with great interest. In this article, the authors used state of the art techniques: a pre-trained convolutional neural network (VGG-16 CNN), transfer learning, data augmentation, drop out and early stopping, all of which are directly responsible for the success and the excitement that these algorithms have created in other fields. We believe that the use of these techniques can offer tremendous opportunities in the field of Medical Physics and as such we would like to praise the authors for their pioneering application to the field of Radiation Oncology. That being said, given that the field of Medical Physics has unique characteristics that differentiate us from those fields where these techniques have been applied successfully, we would like to raise some points for future discussion and follow up studies that could help the community understand the limitations and nuances of deep learning techniques.

Fully convolutional networks with double-label for esophageal cancer image segmentation by self-transfer learning

NASA Astrophysics Data System (ADS)

Xue, Di-Xiu; Zhang, Rong; Zhao, Yuan-Yuan; Xu, Jian-Ming; Wang, Ya-Lei

2017-07-01

Cancer recognition is the prerequisite to determine appropriate treatment. This paper focuses on the semantic segmentation task of microvascular morphological types on narrowband images to aid clinical examination of esophageal cancer. The most challenge for semantic segmentation is incomplete-labeling. Our key insight is to build fully convolutional networks (FCNs) with double-label to make pixel-wise predictions. The roi-label indicating ROIs (region of interest) is introduced as extra constraint to guild feature learning. Trained end-to-end, the FCN model with two target jointly optimizes both segmentation of sem-label (semantic label) and segmentation of roi-label within the framework of self-transfer learning based on multi-task learning theory. The learning representation ability of shared convolutional networks for sem-label is improved with support of roi-label via achieving a better understanding of information outside the ROIs. Our best FCN model gives satisfactory segmentation result with mean IU up to 77.8% (pixel accuracy > 90%). The results show that the proposed approach is able to assist clinical diagnosis to a certain extent.

A brain MRI bias field correction method created in the Gaussian multi-scale space

NASA Astrophysics Data System (ADS)

Chen, Mingsheng; Qin, Mingxin

2017-07-01

A pre-processing step is needed to correct for the bias field signal before submitting corrupted MR images to such image-processing algorithms. This study presents a new bias field correction method. The method creates a Gaussian multi-scale space by the convolution of the inhomogeneous MR image with a two-dimensional Gaussian function. In the multi-Gaussian space, the method retrieves the image details from the differentiation of the original image and convolution image. Then, it obtains an image whose inhomogeneity is eliminated by the weighted sum of image details in each layer in the space. Next, the bias field-corrected MR image is retrieved after the Υ correction, which enhances the contrast and brightness of the inhomogeneity-eliminated MR image. We have tested the approach on T1 MRI and T2 MRI with varying bias field levels and have achieved satisfactory results. Comparison experiments with popular software have demonstrated superior performance of the proposed method in terms of quantitative indices, especially an improvement in subsequent image segmentation.

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

NASA Astrophysics Data System (ADS)

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.

LensFlow: A Convolutional Neural Network in Search of Strong Gravitational Lenses

NASA Astrophysics Data System (ADS)

Pourrahmani, Milad; Nayyeri, Hooshang; Cooray, Asantha

2018-03-01

In this work, we present our machine learning classification algorithm for identifying strong gravitational lenses from wide-area surveys using convolutional neural networks; LENSFLOW. We train and test the algorithm using a wide variety of strong gravitational lens configurations from simulations of lensing events. Images are processed through multiple convolutional layers that extract feature maps necessary to assign a lens probability to each image. LENSFLOW provides a ranking scheme for all sources that could be used to identify potential gravitational lens candidates by significantly reducing the number of images that have to be visually inspected. We apply our algorithm to the HST/ACS i-band observations of the COSMOS field and present our sample of identified lensing candidates. The developed machine learning algorithm is more computationally efficient and complimentary to classical lens identification algorithms and is ideal for discovering such events across wide areas from current and future surveys such as LSST and WFIRST.

Finessing filter scarcity problem in face recognition via multi-fold filter convolution

NASA Astrophysics Data System (ADS)

Low, Cheng-Yaw; Teoh, Andrew Beng-Jin

2017-06-01

The deep convolutional neural networks for face recognition, from DeepFace to the recent FaceNet, demand a sufficiently large volume of filters for feature extraction, in addition to being deep. The shallow filter-bank approaches, e.g., principal component analysis network (PCANet), binarized statistical image features (BSIF), and other analogous variants, endure the filter scarcity problem that not all PCA and ICA filters available are discriminative to abstract noise-free features. This paper extends our previous work on multi-fold filter convolution (ℳ-FFC), where the pre-learned PCA and ICA filter sets are exponentially diversified by ℳ folds to instantiate PCA, ICA, and PCA-ICA offspring. The experimental results unveil that the 2-FFC operation solves the filter scarcity state. The 2-FFC descriptors are also evidenced to be superior to that of PCANet, BSIF, and other face descriptors, in terms of rank-1 identification rate (%).

Spectral-spatial classification of hyperspectral image using three-dimensional convolution network

NASA Astrophysics Data System (ADS)

Liu, Bing; Yu, Xuchu; Zhang, Pengqiang; Tan, Xiong; Wang, Ruirui; Zhi, Lu

2018-01-01

Recently, hyperspectral image (HSI) classification has become a focus of research. However, the complex structure of an HSI makes feature extraction difficult to achieve. Most current methods build classifiers based on complex handcrafted features computed from the raw inputs. The design of an improved 3-D convolutional neural network (3D-CNN) model for HSI classification is described. This model extracts features from both the spectral and spatial dimensions through the application of 3-D convolutions, thereby capturing the important discrimination information encoded in multiple adjacent bands. The designed model views the HSI cube data altogether without relying on any pre- or postprocessing. In addition, the model is trained in an end-to-end fashion without any handcrafted features. The designed model was applied to three widely used HSI datasets. The experimental results demonstrate that the 3D-CNN-based method outperforms conventional methods even with limited labeled training samples.

Automated general temperature correction method for dielectric soil moisture sensors

NASA Astrophysics Data System (ADS)

Kapilaratne, R. G. C. Jeewantinie; Lu, Minjiao

2017-08-01

An effective temperature correction method for dielectric sensors is important to ensure the accuracy of soil water content (SWC) measurements of local to regional-scale soil moisture monitoring networks. These networks are extensively using highly temperature sensitive dielectric sensors due to their low cost, ease of use and less power consumption. Yet there is no general temperature correction method for dielectric sensors, instead sensor or site dependent correction algorithms are employed. Such methods become ineffective at soil moisture monitoring networks with different sensor setups and those that cover diverse climatic conditions and soil types. This study attempted to develop a general temperature correction method for dielectric sensors which can be commonly used regardless of the differences in sensor type, climatic conditions and soil type without rainfall data. In this work an automated general temperature correction method was developed by adopting previously developed temperature correction algorithms using time domain reflectometry (TDR) measurements to ThetaProbe ML2X, Stevens Hydra probe II and Decagon Devices EC-TM sensor measurements. The rainy day effects removal procedure from SWC data was automated by incorporating a statistical inference technique with temperature correction algorithms. The temperature correction method was evaluated using 34 stations from the International Soil Moisture Monitoring Network and another nine stations from a local soil moisture monitoring network in Mongolia. Soil moisture monitoring networks used in this study cover four major climates and six major soil types. Results indicated that the automated temperature correction algorithms developed in this study can eliminate temperature effects from dielectric sensor measurements successfully even without on-site rainfall data. Furthermore, it has been found that actual daily average of SWC has been changed due to temperature effects of dielectric sensors with a significant error factor comparable to ±1% manufacturer's accuracy.

A Fast Numerical Method for Max-Convolution and the Application to Efficient Max-Product Inference in Bayesian Networks.

PubMed

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.

Topology reduction in deep convolutional feature extraction networks

NASA Astrophysics Data System (ADS)

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.

Performance of convolutionally encoded noncoherent MFSK modem in fading channels

NASA Technical Reports Server (NTRS)

Modestino, J. W.; Mui, S. Y.

1976-01-01

The performance of a convolutionally encoded noncoherent multiple-frequency shift-keyed (MFSK) modem utilizing Viterbi maximum-likelihood decoding and operating on a fading channel is described. Both the lognormal and classical Rician fading channels are considered for both slow and time-varying channel conditions. Primary interest is in the resulting bit error rate as a function of the ratio between the energy per transmitted information bit and noise spectral density, parameterized by both the fading channel and code parameters. Fairly general upper bounds on bit error probability are provided and compared with simulation results in the two extremes of zero and infinite channel memory. The efficacy of simple block interleaving in combatting channel memory effects are thoroughly explored. Both quantized and unquantized receiver outputs are considered.

Optimal information transfer in enzymatic networks: A field theoretic formulation

NASA Astrophysics Data System (ADS)

Samanta, Himadri S.; Hinczewski, Michael; Thirumalai, D.

2017-07-01

Signaling in enzymatic networks is typically triggered by environmental fluctuations, resulting in a series of stochastic chemical reactions, leading to corruption of the signal by noise. For example, information flow is initiated by binding of extracellular ligands to receptors, which is transmitted through a cascade involving kinase-phosphatase stochastic chemical reactions. For a class of such networks, we develop a general field-theoretic approach to calculate the error in signal transmission as a function of an appropriate control variable. Application of the theory to a simple push-pull network, a module in the kinase-phosphatase cascade, recovers the exact results for error in signal transmission previously obtained using umbral calculus [Hinczewski and Thirumalai, Phys. Rev. X 4, 041017 (2014), 10.1103/PhysRevX.4.041017]. We illustrate the generality of the theory by studying the minimal errors in noise reduction in a reaction cascade with two connected push-pull modules. Such a cascade behaves as an effective three-species network with a pseudointermediate. In this case, optimal information transfer, resulting in the smallest square of the error between the input and output, occurs with a time delay, which is given by the inverse of the decay rate of the pseudointermediate. Surprisingly, in these examples the minimum error computed using simulations that take nonlinearities and discrete nature of molecules into account coincides with the predictions of a linear theory. In contrast, there are substantial deviations between simulations and predictions of the linear theory in error in signal propagation in an enzymatic push-pull network for a certain range of parameters. Inclusion of second-order perturbative corrections shows that differences between simulations and theoretical predictions are minimized. Our study establishes that a field theoretic formulation of stochastic biological signaling offers a systematic way to understand error propagation in networks of arbitrary complexity.

Decoder synchronization for deep space missions

NASA Technical Reports Server (NTRS)

Statman, J. I.; Cheung, K.-M.; Chauvin, T. H.; Rabkin, J.; Belongie, M. L.

1994-01-01

The Consultative Committee for Space Data Standards (CCSDS) recommends that space communication links employ a concatenated, error-correcting, channel-coding system in which the inner code is a convolutional (7,1/2) code and the outer code is a (255,223) Reed-Solomon code. The traditional implementation is to perform the node synchronization for the Viterbi decoder and the frame synchronization for the Reed-Solomon decoder as separate, sequential operations. This article discusses a unified synchronization technique that is required for deep space missions that have data rates and signal-to-noise ratios (SNR's) that are extremely low. This technique combines frame synchronization in the bit and symbol domains and traditional accumulated-metric growth techniques to establish a joint frame and node synchronization. A variation on this technique is used for the Galileo spacecraft on its Jupiter-bound mission.

Transfer Error and Correction Approach in Mobile Network

NASA Astrophysics Data System (ADS)

Xiao-kai, Wu; Yong-jin, Shi; Da-jin, Chen; Bing-he, Ma; Qi-li, Zhou

With the development of information technology and social progress, human demand for information has become increasingly diverse, wherever and whenever people want to be able to easily, quickly and flexibly via voice, data, images and video and other means to communicate. Visual information to the people direct and vivid image, image / video transmission also been widespread attention. Although the third generation mobile communication systems and the emergence and rapid development of IP networks, making video communications is becoming the main business of the wireless communications, however, the actual wireless and IP channel will lead to error generation, such as: wireless channel multi- fading channels generated error and blocking IP packet loss and so on. Due to channel bandwidth limitations, the video communication compression coding of data is often beyond the data, and compress data after the error is very sensitive to error conditions caused a serious decline in image quality.

On the inversion of geodetic integrals defined over the sphere using 1-D FFT

NASA Astrophysics Data System (ADS)

García, R. V.; Alejo, C. A.

2005-08-01

An iterative method is presented which performs inversion of integrals defined over the sphere. The method is based on one-dimensional fast Fourier transform (1-D FFT) inversion and is implemented with the projected Landweber technique, which is used to solve constrained least-squares problems reducing the associated 1-D cyclic-convolution error. The results obtained are as precise as the direct matrix inversion approach, but with better computational efficiency. A case study uses the inversion of Hotine’s integral to obtain gravity disturbances from geoid undulations. Numerical convergence is also analyzed and comparisons with respect to the direct matrix inversion method using conjugate gradient (CG) iteration are presented. Like the CG method, the number of iterations needed to get the optimum (i.e., small) error decreases as the measurement noise increases. Nevertheless, for discrete data given over a whole parallel band, the method can be applied directly without implementing the projected Landweber method, since no cyclic convolution error exists.

A Very Efficient Transfer Function Bounding Technique on Bit Error Rate for Viterbi Decoded, Rate 1/N Convolutional Codes

NASA Technical Reports Server (NTRS)

Lee, P. J.

1984-01-01

For rate 1/N convolutional codes, a recursive algorithm for finding the transfer function bound on bit error rate (BER) at the output of a Viterbi decoder is described. This technique is very fast and requires very little storage since all the unnecessary operations are eliminated. Using this technique, we find and plot bounds on the BER performance of known codes of rate 1/2 with K 18, rate 1/3 with K 14. When more than one reported code with the same parameter is known, we select the code that minimizes the required signal to noise ratio for a desired bit error rate of 0.000001. This criterion of determining goodness of a code had previously been found to be more useful than the maximum free distance criterion and was used in the code search procedures of very short constraint length codes. This very efficient technique can also be used for searches of longer constraint length codes.

Multiscale Rotation-Invariant Convolutional Neural Networks for Lung Texture Classification.

PubMed

Wang, Qiangchang; Zheng, Yuanjie; Yang, Gongping; Jin, Weidong; Chen, Xinjian; Yin, Yilong

2018-01-01

We propose a new multiscale rotation-invariant convolutional neural network (MRCNN) model for classifying various lung tissue types on high-resolution computed tomography. MRCNN employs Gabor-local binary pattern that introduces a good property in image analysis-invariance to image scales and rotations. In addition, we offer an approach to deal with the problems caused by imbalanced number of samples between different classes in most of the existing works, accomplished by changing the overlapping size between the adjacent patches. Experimental results on a public interstitial lung disease database show a superior performance of the proposed method to state of the art.