检索结果-内蒙古大学图书馆

N-Docker: A NVM-HDD Hybrid Docker Storage Framework to Improve Docker Performance 16th

学校读者我要写书评

暂无评论

N-Docker: A NVM-HDD Hybrid Docker Storage Framework to Impro...

16th IFIP WG 10.3 International Conference on Network and Parallel computing, NPC 2019

作者： Gu, Lin Tang, Qizhi Wu, Song Jin, Hai Zhang, Yingxi Shi, Guoqiang Lin, Tingyu Rao, Jia National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China State Key Laboratory of Intelligent Manufacturing System Technology Beijing100854 China The University of Texas at Arlington ArlingtonTX76019 United States

ISBN: (纸本)9783030307080

Docker has been widely adopted in production environment, but unfortunately deployment and cold-start of container are limited by the low speed of disk. The emerging non-volatile memory (NVM) technology, which has high speed and can store data permanently, brings a new chance to accelerate the deployment and cold-start of container. However, it is expensive to replace the whole hard disk driver (HDD) with NVM. To achieve the fastest deployment and cold-start with lowest cost, we conduct in-depth analysis on the Top-134 images in Docker Hub and obtain two main insights as: (1) the storing latency of layered image has become the bottleneck of container deployment;(2) only a few image layers are required for container cold-start. Based on these two findings, we propose a NVM-HDD hybrid docker storage framework as N-Docker. It can effectively accelerate container cold-start by detecting the bottleneck layers as well as cold-start required layers and storing them into NVM for faster container startup with limited NVM capacity. Experimental results show that N-Docker can accelerate the container deployment by 1.21X and cold-start by 2.96X. Compared to NVM-Docker, which stores all images into NVM, N-Docker achieves the same performance improvements while reducing the usage of NVM by 88.22%. © 2019, IFIP International Federation for Information Processing.

关键词： Containers

DLEDNet: A deep learning-based image encryption and decryption network for internet of medical things

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ding, Yi Wu, Guozheng Chen, Dajiang Zhang, Ning Gong, Linpeng Cao, Mingsheng Qin, Zhiguang Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu Sichuan610054 China Institute of Electronic and Information Engineering of UESTC in Guangdong Dongwan Guangdong China Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu Sichuan610054 China National Natural Science Foundation of China Beijing China Department of Computing Science Texas A&M University-Corpus Christi Corpus ChristiTX78412 United States

With the rapid development of Internet of Medical Things (IoMT) technology, many medical imaging equipments are connected to the medical information network to facilitate the process of diagnosing and treating for doctors. As medical image contains sensitive information, it is of importance yet very challenging to encrypt the medical image to safeguard the privacy or security of the patient. In this work, a deep learning based encryption and decryption network (DLEDNet) is proposed to fulfill the process of encrypting and decrypting the medical image. Specifically, in DLEDNet, the Cycle-GAN network is employed as the main learning network to transfer the medical image from its original domain to the target domain. Target domain is regarded as a "Hidden Factors" to guide the learning model to realize the encryption process. The encrypted image is restored to the original (plaintext) image through a reconstruction network to achieve an image decryption process. In order to realize the data mining process direct from the privacy-protected environment, a ROI (Region of interest)-mining-network is proposed to extract the interested object directly from the encrypted image. The proposed DLEDNet is evaluated on the chest X-ray dataset. Extensive experimental results show that the proposed method can achieve a high level of security with a good performance in efficiency. Copyright © 2020, The Authors. All rights reserved.

关键词： Image segmentation

Crosslink-net: Double-branch encoder segmentation network via fusing vertical and horizontal convolutions

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yu, Qian Qi, Lei Zhou, Luping Wang, Lei Yin, Yilong Shi, Yinghuan Wang, Wuzhang Gao, Yang School of Data and Computer Science Shandong Women's University Jinan250300 China The State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Science and Engineering Southeast University Nanjing211189 China The School of Electrical and Information Engineering University of Sydney NSW2006 Australia The School of Computing and Information Technology University of Wollongong WollongongNSW2522 Australia The School of Soft Shandong University Jinan250100 China Department of Respiratory and Critical Care Medicine Shandong Chest Hospital Jinan250013 China

Accurate image segmentation plays a crucial role in medical image analysis, yet it faces great challenges of various shapes, diverse sizes, and blurry boundaries. To address these difficulties, square kernel-based encoder-decoder architecture has been proposed and widely used, but its performance remains still unsatisfactory. To further cope with these challenges, we present a novel double-branch encoder architecture. Our architecture is inspired by two observations: 1) Since the discrimination of features learned via square convolutional kernels needs to be further improved, we propose to utilize non-square vertical and horizontal convolutional kernels in the double-branch encoder, so features learned by the two branches can be expected to complement each other. 2) Considering that spatial attention can help models to better focus on the target region in a large-sized image, we develop an attention loss to further emphasize the segmentation on small-sized targets. Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net. The experiments validate the effectiveness of our model on four datasets. The code is released at https://***/Qianyu1226/*** Codes 68T07 Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

A reinforcement-learning-based energy-efficient framework for multi-task video analytics pipeline

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhao, Yingying Dong, Mingzhi Wang, Yujiang Feng, Da Lv, Qin Dick, Robert P. Li, Dongsheng Lu, Tun Gu, Ning Shang, Li School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Data Science Fudan University Shanghai China Shanghai Institute of Intelligent Electronics & Systems Shanghai China Department of Computing Imperial College London London United Kingdom Software Service Company Limited Beijing China University of Colorado Boulder BoulderCO United States Department of Electrical Engineering and Computer Science College of Engineering University of Michigan Ann ArborMI United States Microsoft Research Asia Shanghai China School of Computer Science Fudan University Shanghai China

Deep-learning-based video processing has yielded transformative results in recent years. However, the video analytics pipeline is energy-intensive due to high data rates and reliance on complex inference algorithms, which limits its adoption in energy-constrained applications. Motivated by the observation of high and variable spatial redundancy and temporal dynamics in video data streams, we design and evaluate an adaptive-resolution optimization framework to minimize the energy use of multitask video analytics pipelines. Instead of heuristically tuning the input data resolution of individual tasks, our framework utilizes deep reinforcement learning to dynamically govern the input resolution and computation of the entire video analytics pipeline. By monitoring the impact of varying resolution on the quality of high-dimensional video analytics features, hence the accuracy of video analytics results, the proposed end-to-end optimization framework learns the best non-myopic policy for dynamically controlling the resolution of input video streams to globally optimize energy efficiency. Governed by reinforcement learning, optical flow is incorporated into the framework to minimize unnecessary spatio-temporal redundancy that leads to re-computation, while preserving accuracy. The proposed framework is applied to video instance segmentation which is one of the most challenging computer vision tasks, and achieves better energy efficiency than all baseline methods of similar accuracy on the YouTube-VIS dataset. Copyright © 2021, The Authors. All rights reserved.

关键词： Energy efficiency

How does the primate brain combine generative and discriminative computations in vision?

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Peters, Benjamin DiCarlo, James J. Gureckis, Todd Haefner, Ralf Isik, Leyla Tenenbaum, Joshua Konkle, Talia Naselaris, Thomas Stachenfeld, Kimberly Tavares, Zenna Tsao, Doris Yildirim, Ilker Kriegeskorte, Nikolaus Zuckerman Mind Brain Behavior Institute Columbia University United States School of Psychology & Neuroscience University of Glasgow United Kingdom Department of Brain and Cognitive Sciences MIT United States McGovern Institute for Brain Research MIT United States NSF Center for Brains Minds and Machines MIT United States Quest for Intelligence Schwarzman College of Computing MIT United States Department of Psychology New York University United States Brain and Cognitive Sciences University of Rochester United States Center for Visual Science University of Rochester United States Department of Cognitive Science Johns Hopkins University United States Computer Science and Artificial Intelligence Laboratory MIT United States Department of Psychology Harvard University United States Center for Brain Science Harvard University United States Kempner Institute for Natural and Artificial Intelligence Harvard University United States Department of Neuroscience University of Minnesota United States DeepMind United Kingdom Data Science Institute Columbia University United States Dept of Molecular & Cell Biology University of California Berkeley United States Howard Hughes Medical Institute United States Department of Psychology Yale University United States Department of Statistics and Data Science Yale University United States Department of Psychology Columbia University United States Department of Neuroscience Columbia University United States Department of Electrical Engineering Columbia University United States

Vision is widely understood as an inference problem. However, two contrasting conceptions of the inference process have each been influential in research on biological vision as well as the engineering of machine vision. The first emphasizes bottom-up signal flow, describing vision as a largely feedforward, discriminative inference process that filters and transforms the visual information to remove irrelevant variation and represent behaviorally relevant information in a format suitable for downstream functions of cognition and behavioral control. In this conception, vision is driven by the sensory data, and perception is direct because the processing proceeds from the data to the latent variables of interest. The notion of "inference" in this conception is that of the engineering literature on neural networks, where feedforward convolutional neural networks processing images are said to perform inference. The alternative conception is that of vision as an inference process in Helmholtz's sense, where the sensory evidence is evaluated in the context of a generative model of the causal processes that give rise to it. In this conception, vision inverts a generative model through an interrogation of the sensory evidence in a process often thought to involve top-down predictions of sensory data to evaluate the likelihood of alternative hypotheses. The authors include scientists rooted in roughly equal numbers in each of the conceptions and motivated to overcome what might be a false dichotomy between them and engage the other perspective in the realm of theory and experiment. The primate brain employs an unknown algorithm that may combine the advantages of both conceptions. We explain and clarify the terminology, review the key empirical evidence, and propose an empirical research program that transcends the dichotomy and sets the stage for revealing the mysterious hybrid algorithm of primate vision. © 2024, CC BY.

关键词： Feedforward neural networks

REFUGE2 CHALLENGE: A TREASURE TROVE FOR MULTI-DIMENSION ANALYSIS AND EVALUATION IN GLAUCOMA SCREENING

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fang, Huihui Li, Fei Wu, Junde Fu, Huazhu Sun, Xu Son, Jaemin Yu, Shuang Zhang, Menglu Yuan, Chenglang Bian, Cheng Lei, Baiying Zhao, Benjian Xu, Xinxing Li, Shaohua Fumero, Francisco Sigut, José Almubarak, Haidar Bazi, Yakoub Guo, Yuanhao Zhou, Yating Baid, Ujjwal Innani, Shubham Guo, Tianjiao Yang, Jie Orlando, José Ignacio Bogunović, Hrvoje Zhang, Xiulan Xu, Yanwu The REFUGE2 Challenge Australia State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center Sun Yat-Sen University Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science Guangzhou China Intelligent Healthcare Unit Baidu Inc. Beijing China The Institute of High Performance Computing Agency for Science Technology and Research Singapore Yatiris Group PLADEMA Institute CONICET UNICEN Tandil Argentina Christian Doppler Lab for Artificial Intelligence in Retina Department of Ophthalmology and Optometry Medical University of Vienna Vienna Austria VUNO Inc Seoul Korea Republic of Tencent HealthCare Tencent Shenzhen China Computer Vision Institute College of Computer Science and Software Engineering of Shenzhen University Shenzhen China School of Biomedical Engineering Health Science Center Shenzhen University China Xiaohe Healthcare ByteDance Guangdong Guangzhou510000 China School of Biomedical Engineering Shenzhen University China College of Computer Science & Software Engineering Shenzhen University China Department of Computer Science and Systems Engineering Universidad de La Laguna Spain Saudi Electronic University Saudi Arabia King Saud University Saudi Arabia Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China SGGS Institute of Engineering and Technology India Institute of Medical Robotics Shanghai Jiao Tong University China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

With the rapid development of artificial intelligence (AI) in medical image processing, deep learning in color fundus photography (CFP) analysis is also evolving. Although there are some open-source, labeled datasets of CFPs in the ophthalmology community, large-scale datasets for screening only have labels of disease categories, and datasets with annotations of fundus structures are usually small in size. In addition, labeling standards are not uniform across datasets, and there is no clear information on the acquisition device. Here we release a multi-annotation, multi-quality, and multi-device color fundus image dataset for glaucoma analysis on an original challenge-Retinal Fundus Glaucoma Challenge 2nd Edition (REFUGE2). The REFUGE2 dataset contains 2000 color fundus images with annotations of glaucoma classification, optic disc/cup segmentation, as well as fovea localization. Meanwhile, the REFUGE2 challenge sets three sub-tasks of automatic glaucoma diagnosis and fundus structure analysis and provides an online evaluation framework. Based on the characteristics of multi-device and multi-quality data, some methods with strong generalizations are provided in the challenge to make the predictions more robust. This shows that REFUGE2 brings attention to the characteristics of real-world multi-domain data, bridging the gap between scientific research and clinical application. © 2022, CC BY-NC-ND.

关键词： Color

Collaborative Three-Tier Architecture Non-contact Respiratory Rate Monitoring using Target Tracking and False Peaks Eliminating Algorithms

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Mo, Haimiao Ding, Shuai Yang, Shanlin Vasilakos, Athanasios V. Zheng, Xi The School of Management Hefei University of Technology Anhui Hefei23009 China The Key Laboratory of Process Optimization and Intelligent Decision-Making Ministry of Education China The National Engineering Laboratory of Big Data Distribution and Exchange Technologies China Grimstad Norway The College of Mathematics and Computer Science Fuzhou University Fuzhou350116 China The School of Computing Macquarie University Sydney Australia

Monitoring the respiratory rate is crucial for helping us identify respiratory disorders. Devices for conventional respiratory monitoring are inconvenient and scarcely available. Recent research has demonstrated the ability of non-contact technologies, such as photoplethysmography and infrared thermography, to gather respiratory signals from the face and monitor breathing. However, the current non-contact respiratory monitoring techniques have poor accuracy because they are sensitive to environmental influences like lighting and motion artifacts. Furthermore, frequent contact between users and the cloud in real-world medical application settings might cause service request delays and potentially the loss of personal data. We proposed a non-contact respiratory rate monitoring system with a cooperative three-layer design to increase the precision of respiratory monitoring and decrease data transmission latency. To reduce data transmission and network latency, our three-tier architecture layer-by-layer decomposes the computing tasks of respiration monitoring. Moreover, we improved the accuracy of respiratory monitoring by designing a target tracking algorithm and an algorithm for eliminating false peaks to extract high-quality respiratory signals. By gathering the data and choosing several regions of interest on the face, we were able to extract the respiration signal and investigate how different regions affected the monitoring of respiration. The results of the experiment indicate that when the nasal region is used to extract the respiratory signal, it performs experimentally best. Our approach performs better than rival approaches while transferring fewer data. © 2020, CC BY.

关键词： Edge computing

Multiview feature selection combining latent space and similarity structure learning

学校读者我要写书评

暂无评论

Pattern Recognition 2026年 169卷

作者： Zhuowen Li Hongmei Chen Tengyu Yin Zhong Yuan Chuan Luo Shi-Jinn Horng Tianrui Li School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu 611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu 611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu 611756 PR China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu 611756 PR China College of Computer Science Sichuan University Chengdu 610065 China Department of Computer Science and Information Engineering Asia University Taichung 41354 Taiwan Department of Medical Research China Medical University Hospital China Medical University Taichung 404327 Taiwan

Unsupervised multiview feature selection dependent on similar or clustering structures has dramatically progressed, but both ignore the mutually reinforcing relationship between structure learning. Firstly, the two methods of appeal ignore the possibility of shared joint learning, although they can learn coherent information. Secondly, they are inadequate for data structure learning and lack awareness of co-learning global and local structures. This paper proposes an unsupervised feature selection method (SCSF_FS) that integrates similarity and clustering structures learning to capture intrinsic information in data. Specifically, we use latent space learning to partition multiple data matrices into view-specific base matrices and clustering metrics. Structural learning is used to transform specific clustering metrics into coherent clustering structures. In addition, adaptive weights are used on each view’s similarity matrix to learn a consistent similarity structure, while laplacian graph learning is introduced to unify the similarity and clustering structures. Consequently, a unified framework is designed to unify multiview consistency learning, global structure, and local structure preservation. Moreover, an optimization iteration algorithm is designed to solve it. Comparison with eight algorithms shows the effectiveness of the proposed method.

关键词： Multiview feature selection Latent representation learning Similarity and clustering structures Consistency information

Hyperspectral Image Classification with Spatial Consistence Using Fully Convolutional Spatial Propagation Network

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Jiang, Yenan Li, Ying Zou, Shanrong Zhang, Haokui Bai, Yunpeng School of Computer Science National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech and Image Information Processing Northwestern Polytechnical University Xi’an710129 China School of Computer Science University of Adelaide AdelaideSA5005 Australia National Key Laboratory of Science and Technology on Space Microwave Xi’an710000 China School of Computing and Information Systems University of Melbourne MelbourneVIC3010 Australia

In recent years, deep convolutional neural networks (CNNs) have demonstrated impressive ability to represent hyperspectral images (HSIs) and achieved encouraging results in HSI classification. However, the existing CNN-based models operate at the patch-level, in which pixel is separately classified into classes using a patch of images around it. This patch-level classification will lead to a large number of repeated calculations, and it is hard to identify the appropriate patch size that is beneficial to classification accuracy. In addition, the conventional CNN models operate convolutions with local receptive fields, which cause the failure of contextual spatial information modeling. To overcome these aforementioned limitations, we propose a novel end-to-end, pixel-to-pixel fully convolutional spatial propagation network (FCSPN) for HSI classification. Our FCSPN consists of a 3D fully convolution network (3D-FCN) and a convolutional spatial propagation network (CSPN). Specifically, the 3D-FCN is firstly introduced for reliable preliminary classification, in which a novel dual separable residual (DSR) unit is proposed to effectively capture spectral and spatial information simultaneously with fewer parameters. Moreover, the channel-wise attention mechanism is adapted in the 3D-FCN to grasp the most informative channels from redundant channel information. Finally, the CSPN is introduced to capture the spatial correlations of HSI via learning a local linear spatial propagation, which allows maintaining the HSI spatial consistency and further refining the classification results. Experimental results on three HSI benchmark datasets demonstrate that the proposed FCSPN achieves state-of-the-art performance on HSI classification. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution