检索结果-内蒙古大学图书馆

Stability-Based Generalization Analysis of Distributed Learning Algorithms for Big Data

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systems 2020年第3期31卷 801-812页

作者： Wu, Xinxing Zhang, Junping Wang, Fei-Yue Shanghai Tech Inst Elect & Informat Dept Commun & Informat Engn Shanghai 201411 Peoples R China Fudan Univ Sch Comp Sci Shanghai Key Lab Intelligent Informat Proc Shanghai 200433 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Macau Univ Sci & Technol Inst Syst Engn Macau 999078 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

As one of the efficient approaches to deal with big data, divide-and-conquer distributed algorithms, such as the distributed kernel regression, bootstrap, structured perception training algorithms, and so on, are proposed and broadly used in learning systems. Some learning theories have been built to analyze the feasibility, approximation, and convergence bounds of these distributed learning algorithms. However, less work has been studied on the stability of these distributed learning algorithms. In this paper, we discuss the generalization bounds of distributed learning algorithms from the view of algorithmic stability. First, we introduce a definition of uniform distributed stability for distributed algorithms and study the distributed algorithms' generalization risk bounds. Then, we analyze the stability properties and generalization risk bounds of a kind of regularization-based distributed algorithms. Two generalization distributed risks obtained show that the generalization distributed risk bounds for the difference between their generalization distributed and empirical distributed/leave-one-computer-out risks are closely related to the size of samples n and the amount of working computers m mathcal O(m/n(1/2)). Furthermore, the results in this paper indicate that, for a good generalization regularized distributed kernel algorithm, the regularization parameter lambda should be adjusted with the change of the term m/n(1/2). These theoretic discoveries provide the useful guidance when deploying the distributed algorithms on practical big data platforms. We explore our theoretic analyses through two simulation experiments. Finally, we discuss some problems about the sufficient amount of working computers, nonequivalence, and generalization for distributed learning. We show that the rules for the computation on one single computer may not always hold for distributed learning.

关键词： Big data distributed learning algorithms distributed simulations generalization

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Brain-Computer Interfaces: A Systematic Review

arXiv

引用

arXiv 2024年

作者： Xia, Kun Duch, Wlodzislaw Sun, Yu Xu, Kedi Fang, Weili Luo, Hanbin Zhang, Yi Sang, Dong Xu, Xiaodong Wang, Fei-Yue Wu, Dongrui The Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Zhejiang Lab Hangzhou311121 China The Department of Informatics School of Physics Astronomy and Informatics Neurocognitive Laboratory Center for Modern Interdisciplinary Technologies Nicolaus Copernicus University Torun Poland The Ministry of Education Key Laboratory for Biomedical Engineering Zhejiang University Hangzhou China The Zhejiang University School of Medicine National Clinical Research Center for Child Health Hangzhou China Department of Biomedical Engineering Zhejiang University Hangzhou China The School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan430074 China The College of Public Administration Huazhong University of Science and Technology Wuhan430074 China The NetsUnion Clearing Corporation Beijing100045 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100049 China

A brain-computer interface (BCI) establishes a direct communication pathway between the human brain and a computer. It has been widely used in medical diagnosis, rehabilitation, education, entertainment, etc. Most research so far focuses on making BCIs more accurate and reliable, but much less attention has been paid to their privacy. Developing a commercial BCI system usually requires close collab.rations among multiple organizations, e.g., hospitals, universities, and/or companies. Input data in BCIs, e.g., electroencephalogram (EEG), contain rich privacy information, and the developed machine learning model is usually proprietary. Data and model transmission among different parties may incur significant privacy threats, and hence privacy protection in BCIs must be considered. Unfortunately, there does not exist any contemporary and comprehensive review on privacy-preserving BCIs. This paper fills this gap, by describing potential privacy threats and protection strategies in BCIs. It also points out several challenges and future research directions in developing privacy-preserving BCIs. © 2024, CC BY.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Social Manufacturing Pattern in the intelligent Reform of the Shoes and Clothing Industry

Social Manufacturing Pattern in the Intelligent Reform of th...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Yansong Cao Yutong Wang Juwu Dai Xihao Zhu Fei-Yue Wang Macau Institute of Systems Engineering Macau University of Science and Technology Macau China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Ningbo Sanbody Intelligent Technology co. LTD Ningbo China Faculty of Science and Engineering University of Nottingham Ningbo China

Along with economic globalization, the shoes and clothing market is undergoing huge changes and is facing increasing individualized demands. To realize personalized customization, we propose a social manufacturing pattern for the shoes and clothing industry. On the customer side, we collect costumer information with the help of 3D scanning and virtual fitting. On the production side, we replace human lab.r with intelligent production equipment. On the enterprise management side, we construct a cloud platform to realize source maximization. Through this social manufacturing pattern, we expect to accelerate the intelligent reform of the shoes and clothing industry.

关键词： Product customization Cloud computing Three-dimensional displays Social networking (online) Production equipment Footwear Clothing industry

来源：评论

学校读者我要写书评

暂无评论

Bitcoin Fee Decisions in Transaction Confirmation Queueing Games under Limited Multi-Priority Rule

Bitcoin Fee Decisions in Transaction Confirmation Queueing G...

引用

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Li, Juanjuan Yuan, Yong Wang, Fei-Yue State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China

ISBN: (纸本)9781728128535

In the Bitcoin system, transaction fees serve not only as the fundamental economic incentive to stimulate miners, but also as an important tuner for the Bitcoin system to define the priorities in the transaction confirmation process. In this paper, we aim to study the priority rules for queueing transactions based on their associated fees, and in turn users' decision-making in formulating their fees in the transaction confirmation queueing game. Based on the queueing theory, we first analyzed the waiting time of users under non-preemptive limited multi-priority (LMP) rule, which is formulated to adjust users' waiting time over different priorities. We then established a game-theoretical model, and analyze users' equilibrium fee decisions. Towards the end, we conducted computational experiments to validate the theoretical analysis. Our research findings can not only help understand users' fee decisions under the LMP rule, but also offer useful managerial insights in optimizing the queueing rules of Bitcoin transactions. © 2019 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting

arXiv

引用

arXiv 2022年

作者： Gao, Jiaqi Huang, Zhizhong Lei, Yiming Shan, Hongming Wang, James Z. Wang, Fei-Yue Zhang, Junping The Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China The Institute of Science and Technology for Brain-inspired Intelligence MOE Frontiers Center for Brain Science Fudan University Shanghai200433 China The Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai201210 China The College of Information Sciences and Technology The Pennsylvania State University University ParkPA16802 United States The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The Institute of Systems Engineering Macau University of Science and Technology China Qingdao Academy of Intelligent Industries Qingdao266109 China

Most conventional crowd counting methods utilize a fully-supervised learning framework to establish a mapping between scene images and crowd density maps. They usually rely on a large quantity of costly and time-intensive pixel-level annotations for training supervision. One way to mitigate the intensive lab.ling effort and improve counting accuracy is to leverage large amounts of unlab.led images. This is attributed to the inherent self-structural information and rank consistency within a single image, offering additional qualitative relation supervision during training. Contrary to earlier methods that utilized the rank relations at the original image level, we explore such rank-consistency relation within the latent feature spaces. This approach enables the incorporation of numerous pyramid partial orders, strengthening the model representation capability. A notable advantage is that it can also increase the utilization ratio of unlab.led samples. Specifically, we propose a Deep Rank-consistEnt pyrAmid Model (DREAM), which makes full use of rank consistency across coarse-to-fine pyramid features in latent spaces for enhanced crowd counting with massive unlab.led images. In addition, we have collected a new unlab.led crowd counting dataset, FUDAN-UCC, comprising 4,000 images for training purposes. Extensive experiments on four benchmark datasets, namely UCF-QNRF, ShanghaiTech PartA and PartB, and UCF-CC-50, show the effectiveness of our method compared with previous semi-supervised methods. The codes are availab.e at https://***/bridgeqiqi/DREAM. Copyright © 2022, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Kernel Regularized Nonlinear Dictionary Learning for Sparse Coding

引用

IEEE TRANSACTIONS ON systems MAN CYBERNETICS-systems 2019年第4期49卷 766-775页

作者： Liu, Huaping Liu, He Sun, Fuchun Fang, Bin Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China Tsinghua Univ State Key Lab Intelligent Technol & Syst TNLIST Beijing 100084 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

For most sparse coding methods, data samples are first encoded as hand-crafted features, followed by another separate learning step that generates dictionary and sparse codes. However, such feature representations may not be optimally compatible with the learning process, thus producing suboptimal results. In this paper, we propose a new architecture for non-linear dictionary learning with sparse coding, in which samples are mapped into sparse codes via carefully designed stacked auto-encoder (SAE) networks. We jointly learn a low-dimensional embedding of the data samples by means of an SAE and a dictionary in the low-dimensional space. Further, to leverage the prior knowledge, we develop a kernel regularized nonlinear dictionary learning method, which effectively incorporates the knowledge provided by the hand-crafted kernel. An iterative algorithm is developed to jointly search the solutions of the associated optimization problem and extensive experimental validations are performed to show that the proposed kernel regularized dictionary learning method achieves satisfactory performance.

关键词： Kernel dictionary learning kernel sparse coding stacked auto-encoder (SAE)

来源：评论

学校读者我要写书评

暂无评论

Social Intelligence: The Way We Interact, The Way We Go

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL systems 2019年第6期6卷 1139-1146页

作者： Wang, Fei-Yue Ye, Peijun Li, Juanjuan State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China Qingdao Acad Intelligent Ind Qingdao 266109 Shandong Peoples R China

Welcome to the last issue of the IEEE Transactions on Computational Social systems (TCSS) of this year, with a special focus on “blockchainbased secure and trusted computing for IoT.” Here, we have 18 regular articles and a brief discussion on social intelligence. I would like to take this opportunity to thank and congratulate everyone, especially our editorial board for a great job well done. Looking forward to working with you all in 2020!

关键词：

来源：评论

学校读者我要写书评

暂无评论

Face Image Based Automatic Diagnosis by Deep Neural Networks 16

Face Image Based Automatic Diagnosis by Deep Neural Networks

引用

16th IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Niu, Lulu Xiong, Gang Shen, Zhen Pan, Zhouxian Chen, Shi Dong, Xisong Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Chinese Acad Sci Beijing Engn Res Ctr Intelligent Syst & Technol Inst Automat Beijing Peoples R China Chinese Acad Sci Guangdong Engn Res Ctr 3D Printing & Intelligent Cloud Comp Ctr Dongguan Peoples R China Qingdao Acad Intelligent Ind Qingdao Peoples R China Chinese Acad Med Sci & Peking Union Med Coll CAMS Peking Union Med Coll Hosp PUMCH Dept Allergy Beijing Peoples R China CAMS & PUMC Dept Endocrinol PUMCH Endocrine Key LabMinist Hlth Beijing Peoples R China

ISBN: (纸本)9781665422482

In this paper, we use ResNet based networks for the automatic diagnosis of the Turner Syndrome (TS) by facial images. The TS is a common sex chromosomal disorder, which is due to the total or partial absence or structural abnormality of the X chromosome. Nowadays, the diagnosis of the TS mainly depends on peripheral blood lymphocyte chromosome karyotype analysis, which is time consuming. For inexperienced doctors, it is difficult to diagnose the TS only based on facial features, and there may be missed and inaccurate diagnosis. In order to help the TS patients to get timely diagnosis, we design and train ResNet-based networks to recognize patients' facial features, and build an intelligent system for automatic diagnosis. We evaluate the performance of the ResNet-based networks by sensitivity, specificity, and accuracy. We increase the average sensitivity from 67.6% to 91.54%, average specificity from 87.9% to 9852%, compared with the AdaBoost method with local features. In the future, we aim to set up the intelligent system on a smart-phone to achieve fast and convenient screening of the TS at an early stage.

关键词： Deep Neural Networks (DNNs) Turner Syndrome (TS) facial images automatic diagnosis ResNet

来源：评论

学校读者我要写书评

暂无评论

A Heuristic Algorithm for the Fabric Spreading and Cutting Problem in Apparel Factories

引用

IEEE/CAA Journal of Automatica Sinica 2019年第4期6卷 961-968页

作者： Xiuqin Shang Dayong Shen Fei-Yue Wang Timo R. Nyberg the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of Sciences (CAS)Beijing 100190China the Qingdao Academy of Intelligent Industries Qingdao 266109China IEEE the Beijing Enineering Research Center of Intelligent Systems and Technology Institute of AutomationCASBeijing 100190China the Cloud Computing Center CASDongguan 523808China the School of Science at Aalto University AaltoFinland

We study the fabric spreading and cutting problem in apparel *** the sake of saving the material costs,the cutting requirement should be met exactly without producing additional garment *** reducing the production costs,the number of lays that corresponds to the frequency of using the cutting beds should be *** propose an iterated greedy algorithm for solving the fabric spreading and cutting *** algorithm contains a constructive procedure and an improving *** the constructive procedure creates a set of lays in sequence,and then the improving loop tries to pick each lay from the lay set and rearrange the remaining lays into a smaller lay *** improving loop will run until it cannot obtain any smaller lay set or the time limit is *** experiment results on 500 cases show that the proposed algorithm is effective and efficient.

关键词： Construction and improvement cutting and packing fabric spreading and cutting heuristic algorithm

来源：评论

学校读者我要写书评

暂无评论

Pay attention to doctor-patient dialogues: Multi-modal knowledge graph attention image-text embedding for COVID-19 diagnosis

引用

INFORMATION FUSION 2021年 75卷 168-185页

作者： Zheng, Wenbo Yan, Lan Gou, Chao Zhang, Zhi-Cheng Zhang, Jun Jason Hu, Ming Wang, Fei-Yue Xi An Jiao Tong Univ Sch Software Engn Xian 710049 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100190 Peoples R China Sun Yat Sen Univ Sch Intelligent Syst Engn Guangzhou 510275 Peoples R China Gen Hosp Peoples Liberat Army Med Ctr 7 Beijing 100700 Peoples R China Wuhan Univ Sch Elect Engn & Automat Wuhan 430072 Peoples R China Wuhan Pulm Hosp Intens Care Unit Wuhan 430030 Peoples R China

The sudden increase in coronavirus disease 2019 (COVID-19) cases puts high pressure on healthcare services worldwide. At this stage, fast, accurate, and early clinical assessment of the disease severity is vital. In general, there are two issues to overcome: (1) Current deep learning-based works suffer from multimodal data adequacy issues;(2) In this scenario, multimodal (e.g., text, image) information should be taken into account together to make accurate inferences. To address these challenges, we propose a multi-modal knowledge graph attention embedding for COVID-19 diagnosis. Our method not only learns the relational embedding from nodes in a constituted knowledge graph but also has access to medical knowledge, aiming at improving the performance of the classifier through the mechanism of medical knowledge attention. The experimental results show that our approach significantly improves classification performance compared to other state-of-the-art techniques and possesses robustness for each modality from multi-modal data. Moreover, we construct a new COVID-19 multi-modal dataset based on text mining, consisting of 1393 doctor-patient dialogues and their 3706 images (347 X-ray + 2598 CT + 761 ultrasound) about COVID-19 patients and 607 non-COVID-19 patient dialogues and their 10754 images (9658 X-ray + 494 CT + 761 ultrasound), and the fine-grained lab.ls of all. We hope this work can provide insights to the researchers working in this area to shift the attention from only medical images to the doctor-patient dialogue and its corresponding medical images.

关键词： COVID-19 diagnose Knowledge attention mechanism Knowledge-based representation learning Knowledge embedding

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：