检索结果-内蒙古大学图书馆

16th ieee International symposium on Biomedical Imaging (ISBI)

作者： Daniels, Zachary A. Metaxas, Dimitris N. Rutgers State Univ Dept Comp Sci Piscataway NJ 08854 USA

ISBN: (纸本)9781538636411

Manual examination of chest x-rays is a time consuming process that involves significant effort by expert radiologists. Recent work attempts to alleviate tins problem by developing learning-based automated chest x-ray analysis systems that map images to multi-label diagnoses using deep neural networks. These methods are often treated as black boxes, or they output attention maps but don't explain why the attended areas are important. Given data consisting of a frontal-view x-ray, a set of natural language findings, and one or more diagnostic impressions, we propose a deep neural network model that during training simultaneously 1) constructs a topic model which clusters key terms from the findings into meaningful groups, 2) predicts the presence of each topic for a given input image based on learned visual features, and 3) uses an image's predicted topic encoding as features to predict one or more diagnoses. Since the net learns the topic model jointly with the classifier, it gives us a powerful tool for understanding which semantic concepts the net might be exploiting when making diagnoses, and since we constrain the net to predict topics based on expert-annotated reports, the net automatically encodes some higher-level expert knowledge about how to make diagnoses.

关键词： Chest X-Ray Analysis Multimedia Analysis Natural Language processing Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Many-level image Thresholding using a Center-Based Differential Evolution Algorithm

Many-level Image Thresholding using a Center-Based Different...

引用

Congress on Evolutionary Computation

作者： Seyed Jalaleddin Mousavirad Shahryar Rahnamayan Gerald Schaefer SMIEEE Nature-Inspired Computational Intelligence Lab Ontario Tech University Oshawa Canada Department of Computer Science Loughborough University Loughborough U.K.

ISBN: (数字)9781728169293

ISBN: (纸本)9781728169309

image thresholding is a crucial image processing task. Most of the time, it plays a pivotal role in an image processing chain, therefore, any error in image thresholding can propagate to other steps such as edge detection, area/volume estimation, or object recognition. Multi-level image thresholding is a popular method for image segmentation, dividing an image into homogeneous regions. Conventional algorithms are timeconsuming due to utilising an exhaustive search, especially when the number of threshold levels increases. On the other hand, population-based metaheuristic algorithms have been successfully applied to this problem. In this paper, we propose a center-based differential evolution (DE) algorithm for high-dimensional multilevel image thresholding (many-level image thresholding). While DE has been shown to yield satisfactory performance for various real-world optimisation problems, in our algorithm, DE is further boosted with a center-based sampling strategy. We evaluate our algorithm on a set of benchmark images on high-dimensional search spaces and with regards to an entropy-based objective function and peak signal-to-noise ratio (PSNR). The obtained results demonstrate that the proposed algorithm can improve upon the performance of other metaheuristic image thresholding techniques.

关键词： Thresholding (Imaging) Linear programming Optimization Sociology Histograms image segmentation

来源：评论

学校读者我要写书评

暂无评论

An End-To-End CNN-BiLSTM Attention Model for Gearbox Fault Diagnosis

An End-To-End CNN-BiLSTM Attention Model for Gearbox Fault D...

引用

symposium of image, signal processing, and Artificial Vision (STSIVA)

作者： Xiaoyang Zheng Jinliang Wu Zeyu Ye School of Artificial Intelligence Chongqing University of Technology Chongqing China

ISBN: (数字)9781728170862

ISBN: (纸本)9781728170879

Existing fault diagnosis methods based on Deep Learning require complicated and cumbersome preprocessing procedures heavily relying on signal processing and manual feature extraction techniques, which fails to maximize the superiority of the adaptive representation capability of Deep Learning. This paper proposes a novel end-to-end fault diagnosis approach combined convolutional neural network (CNN) with Bidirectional Long Short-Term Memory (BiLSTM) and Attention Mechanism. Specifically, one dimensional CNN is utilized to perform local feature extraction and dimension reduction on the input signal data. Then, the BiLSTM network is adopted to extract high-level features from the above results. The miscellaneous features extracted are filtered out by using Attention Mechanism. Finally, the learned features are implemented to train Softmax classifier for identifying fault types. To evaluate the effectiveness of the proposed model, experiments are carried out on two different datasets by using ten-fold cross validation approach. The results demonstrate that the proposed model is capable to learn features adaptively with fewer steps while ensuring higher accuracy compared with other state-of-art fault diagnosis methods.

关键词： Fault diagnosis Deep learning Vibrations Adaptation models Manuals signal processing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Apodizing Delay and Auto-Correlation Reconstruction Algorithm for High-Frame-Rate Ultrasound Imaging

Apodizing Delay and Auto-Correlation Reconstruction Algorith...

引用

ieee symposium (IUS) Ultrasonics

作者： Chunqi Li Harry R. Clegg Thomas M. Carpenter Luzhen Nie Steven Freear David M. J. Cowell James R. McLaughlan School of Electronic and Electrical Engineering University of Leeds UK Leeds Institute of Medical Research St James' University Hospital Leeds UK

ISBN: (数字)9781728154480

ISBN: (纸本)9781728154497

Delay and sum (DAS) beamforming is a common technique for ultrasound imaging, as it has a low computation complexity suitable for real-time imaging. However, the image quality of DAS is largely restricted by the imaging array configuration, such as the aperture size and the center frequency used. Adaptive beamforming techniques such as minimal variance (MV), which presents improved spatial resolution and contrast ratio, but with an significant increased computation requirements that can not generally be implemented with real-time monitoring. In this study, we developed an alternative nonlinear beamforming method for ultrasound imaging, termed an apodizing delay and auto-correlation reconstruction algorithm (ADAC). The computation complexity of ADAC is O(2N) which ensures a similar beamforming speed to DAS O(N), since both are on the same order of magnitude. We tested ADAC against DAS, on both Field II simulated data and experimental data acquired from imaging a standard CIRS calibration phantom. Results show that the ADAC beamformer compared with DAS that mitigated the self-nulling phenomenon of CIRS proximal targets and showed the weak-signal mapping ability up to an imaging depth of 65 mm. The image quality beamformed by ADAC from anechoic simulated data and interleaving B-mode showed an improved contrast ratio (CR), lateral, and axial resolution of 19 dB, 0.5 mm (lateral) and 0.3 mm mm (axial), respectively. All above demonstrate that the ADAC beamformer outperforms DAS with narrower main lobes and increased dynamic range whilst maintaining a similar computational complexity.

关键词： image quality Ultrasonic imaging Array signal processing Imaging Delays Spatial resolution computational complexity

来源：评论

学校读者我要写书评

暂无评论

Cognitive images for the Visual Analysis of the States of Complex Objects in Relation to the Space Industry

Cognitive Images for the Visual Analysis of the States of Co...

引用

symposium of image, signal processing, and Artificial Vision (STSIVA)

作者： Yulia Emelyanova Vyacheslav Khachumov Program Systems Institute of the Russian Academy of Sciences Pereslavl-Zalessky Russian Federation RUDN University Moscow Russian Federation Institute of Artificial Intelligence Problems Moscow Russian Federation

ISBN: (数字)9781728170862

ISBN: (纸本)9781728170879

The work is aimed at supporting the decision-making of ground station operators who monitor and diagnose spacecraft subsystems. The problem of automatic construction of color-bright cognitive symbols that contribute to an operational understanding of the current situation is solved. For the first time, a comprehensive formal assessment of the quality of cognitive symbols designed to observe the state of a complex real-time dynamic system was given.

关键词： Space vehicles Industries Visualization Real-time systems Informatics Dynamical systems Monitoring

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Based Layer-Wise Quantization For Lightweight Deep Neural Networks

Reinforcement Learning-Based Layer-Wise Quantization For Lig...

引用

ieee International Conference on image processing

作者： Juri Jung Jonghee Kim Youngeun Kim Changick Kim Korea Advanced Institute of Science and Technology (KAIST) Daejeon Korea

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

Network quantization has been widely studied to compress the deep neural network in mobile devices. Conventional methods quantize the network parameters of all layers with the same fixed precision, regardless of the number of parameters in each layer. However, quantizing the weights of the layer with many parameters is more effective in reducing the model size. Accordingly, in this paper, we propose a novel mixed-precision quantization method based on reinforcement learning. Specifically, we utilize the number of parameters at each layer as a prior for our framework. By using the accuracy and the bit-width as a reward, the proposed framework determines the optimal quantization policy for each layer. By applying this policy sequentially, we achieve weighted-average 2.97 bits for the VGG-16 model on the CIFAR-10 dataset with no degradation of the accuracy, compared with its full-precision baseline. We also show that our framework can provide an optimal quantization policy for the VGG-Net and the ResNet to minimize the storage while preserving the accuracy.

关键词： Quantization (signal) Neural networks Learning (artificial intelligence) computational modeling Training Mobile handsets Task analysis

来源：评论

学校读者我要写书评

暂无评论

Migrating Large Deep Learning Models to Serverless Architecture

Migrating Large Deep Learning Models to Serverless Architect...

引用

ieee International Conference on Software Reliability Engineering Workshops (ISSRE Wksp)

作者： Dheeraj Chahal Ravi Ojha Manju Ramesh Rekha Singhal TCS Research Mumbai India

ISBN: (数字)9781728177359

ISBN: (纸本)9781728177366

Serverless computing platform is emerging as a solution for event-driven artificial intelligence applications. Function-as-a-Service (FaaS) using serverless computing paradigm provides high performance and low cost solutions for deploying such applications on cloud while minimizing the operational logic. Using FaaS for efficient deployment of complex applications, such as natural language processing (NLP) and image processing, containing large deep learning models will be an advantage. However, constrained resources and stateless nature of FaaS offers numerous challenges while deploying such applications. In this work, we discuss the methodological suggestions and their implementation for deploying pre-trained large size machine learning and deep learning models on FaaS. We also evaluate the performance and deployment cost of an enterprise application, consisting of suite of deep vision preprocessing algorithms and models, on VM and FaaS platform. Our evaluation shows that migration from monolithic to FaaS platform significantly improves the performance of the application at a reduced cost.

关键词： FAA Optical character recognition software Biological system modeling Computer architecture Load modeling computational modeling Libraries

来源：评论

学校读者我要写书评

暂无评论

Partial Gated Feedback Recurrent Neural Network for Data Compression Type Classification

引用

ieee ACCESS 2020年 8卷 151426-151436页

作者： Song, Hyewon Kwon, Beom Yoo, Hoon Lee, Sanghoon Yonsei Univ Dept Elect & Elect Engn Seoul 03722 South Korea Sangmyung Univ Dept Elect Seoul 03016 South Korea

Owing to the widespread use of digital devices such as mobile phones and tablet PCs that are capable of easily viewing contents, the number of digital crimes committed using these digital devices has increased. One of the most common digital crimes is to hide the header information of the compressed data, which makes the user's data unusable. It is difficult to restore original data without the header because header contains the compression type. In this paper, we propose a Partial Gated Feedback Recurrent Neural Network (PGF-RNN) for the identification of lossless compression algorithms. We modify the gated recurrent units to improve the correlation of layers by grouping the fully-connected layers to effectively determine the characteristics of the compressed data. We emphasize on the temporal features, which consider a wide range of data, and spatial features from fully-connected layers to extract the feature vectors of each compression type. To improve the performance of the proposed PGF-RNN, we apply post-processing that considers the frequency of bit sequences on some compression types with similar compressed data. The proposed method is evaluated on 31 well-known lossless compression algorithms of the Association for computational Linguistics dataset. The average top 1 accuracy of the proposed method is 92.63%.

关键词： Feature extraction Compression algorithms Logic gates Recurrent neural networks Encoding Data mining image coding Compression type classification deep learning gated recurrent unit lossless compression partial gated feedback recurrent neural network recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

A study of fine-tuning CNN models based on thermal imaging for breast cancer classification

A study of fine-tuning CNN models based on thermal imaging f...

引用

2019 ieee International Conference on Cybernetics and computational intelligence, CYBERNETICSCOM 2019

作者： Roslidar, Roslidar Saddami, Khairun Arnia, Fitri Syukri, Maimun Munadi, Khairul Universitas Syiah Kuala Post Graduate Programme in Engineering Banda Aceh23111 Indonesia Post Graduate Programme in Engineering Universitas Syiah Kuala Department of Electrical and Computer Engineering Banda Aceh23111 Indonesia Medical Faculty Universitas Syiah Kuala Banda Aceh23111 Indonesia

ISBN: (纸本)9781728108674

This paper discusses the initial experiments on fine-tuning the convolutional neural network (CNN) models of ResNet101, DenseNet, MobileNetV2, and ShuffleNetV2 for breast cancer detection. These models have been tested using the imageNet database and shown their high performance on the image classification. Here, the dataset used to train the model are thermal breast images downloaded from the Database for Mastology Research (DMR). There are only two classification classes here, cancer and healthy. During the training, we used three epochs for the training iteration, 10, 20, and 30. For this preliminary study, we set the learning rate to 0.001, momentum to 0.9, learning rate factor for weight and bias each to 10, and minibatch size to 10. The training results showed that ResNet101 and DenseNet with deep networks have 100% accuracy only in 10 epochs. Whereas, MobileNetV2 and ShuffleNetV2 respectively need 20 epochs and 30 epochs of training to achieve 100% accuracy. Finally, we evaluated the performance of each pretrained model using testing results. The DenseNet was able to classify all the testing dataset correctly. ResNet101 and MobileNetV2 have the same performance, correctly classified static dataset while slightly missed in classifying dynamic dataset with 0.996 of accuracy. ShuffleNetV2 has a little lower performance with only 0.98 of accuracy. In term of training time, ShuffleNetV2 spent a short duration, but MobileNetV2 with competitive elapse time was able to show equal performance to ResNet101. © 2019 ieee.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Reservoir Computing for Jurkat T-cell Segmentation in High Resolution Live Cell Ca2+ Fluorescence Microscopy

Reservoir Computing for Jurkat T-cell Segmentation in High R...

引用

ieee International symposium on Biomedical Imaging

作者： Fatemeh Hadaeghi Björn-Philipp Diercks Insa M.A. Wolf René Werner

ISBN: (数字)9781538693308

ISBN: (纸本)9781538693315

The reservoir computing (RC) paradigm is exploited to detect Jurkat T cells and antibody-coated beads in fluorescence microscopy data. Recent progress in imaging of subcellular calcium (Ca 2 +) signaling offers a high spatial and temporal resolution to characterize early signaling events in T cells. However, data acquisition with dual-wavelength Ca 2 + indicators, the photo-bleaching at high acquisition rate, low signal-to-noise ratio, and temporal fluctuations of image intensity entail corporation of post-processing techniques into Ca 2 + imaging systems. Besides, although continuous recording enables real-time Ca 2 + signal tracking in T cells, reliable automated algorithms must be developed to characterize the cells, and to extract the relevant information for conducting further statistical analyses. Here, we present a robust two-channel segmentation algorithm to detect Jurkat T lymphocytes as well as antibody-coated beads that are utilized to mimic cell-cell interaction and to activate the T cells in microscopy data. Our algorithm uses the reservoir computing framework to learn and recognize the cells - taking the spatiotemporal correlations between pixels into account. A comparison of segmentation accuracy on testing data between our proposed method and the deep learning U-Net model confirms that the developed model provides accurate and computationally cheap solution to the cell segmentation problem.

关键词： Reservoirs image segmentation computational modeling Microscopy Computer architecture Microprocessors

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：