检索结果-内蒙古大学图书馆

Distributed algorithm for solving variational inequalities over time-varying unbalanced digraphs

control Theory and technology 2024年第3期22卷 431-441页

作者： Yichen Zhang Yutao Tang Zhipeng Tu Yiguang Hong School of Artificial Intelligence Beijing University of Posts and TelecommunicationsBeijing 100876China Network Technology Laboratory Huawei Technologies Co.Ltd.Beijing 100095China Department of Control Science and Engineering Tongji UniversityShanghai 200092China Shanghai Research Institute for Intelligent Autonomous Systems Tongji UniversityShanghai 200092China

In this paper,we study a distributed model to cooperatively compute variational inequalities over time-varying directed ***,each agent has access to a part of the full mapping and holds a local view of the global set *** virtue of an auxiliary vector to compensate the graph imbalance,we propose a consensus-based distributed projection algorithm relying on local computation and communication at each *** show the convergence of this algorithm over uniformly jointly strongly connected unbalanced digraphs with nonidentical local *** also provide a numerical example to illustrate the effectiveness of our algorithm.

关键词： Variational inequality Distributed computation Multi-agent system Weight-unbalanced graph

来源：评论

学校读者我要写书评

暂无评论

Robust H∞ Attitude Stabilization for the Cluster Takeover of Non-cooperative Flexible spacecraft 1

引用

29th International Conference on Computational and Experimental Engineering and sciences, ICCES 2023

作者： Yue, Xiaokui Yang, Ziyu Yu, Hongyu Huang, Panxing Liu, Yuan National Key Laboratory of Aerospace Flight Dynamics School of Astronautics Northwestern Polytechnical University Xi’an710072 China Science and Technology on Space Intelligent Control Laboratory Beijing Institute of Control Engineering Beijing100094 China Beijing Institute of Remote Sensing Information Beijing100011 China

ISBN: (数字)9783031449475

ISBN: (纸本)9783031449468

In this paper, a cooperative control scheme based on the small spacecraft cluster is proposed for the takeover control of the failed flexible spacecraft in space. In order to overcome external disturbance, inertia uncertainty and controller gain perturbation, the controller spacecraft calculates the control torque which can stabilize the combined spacecraft in theory, and generates the desired control signal according to the robust H∞ non-fragile control law set in advance. Based on the communication topology, the actuator spacecraft restores the control signal according to the distributed control torque allocation scheme considering the saturation state of all reaction wheels, and implements it to achieve the attitude stabilization and vibration suppression of the combined spacecraft. Simulation results show that the distributed control torque allocation scheme can implement the desired control signal with relatively small error. Under the condition that the external disturbance, controller gain perturbation and inertia uncertainty coexist, the angle and angular velocity of the combined spacecraft can be stabilized quickly. Moreover, the vibration of the flexible appendages can also be suppressed effectively. During the whole takeover control process, the dynamic allocation scheme can always ensure that all reaction wheels of each actuator spacecraft never reach saturation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Flexible spacecraft

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Residual Dense Shrinkage Network for ECG Denoising

引用

Computer Modeling in Engineering & sciences 2024年第3期138卷 2809-2824页

作者： Dengyong Zhang Minzhi Yuan Feng Li Lebing Zhang Yanqiang Sun Yiming Ling Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China School of Computer and Artificial Intelligence Huaihua UniversityHuaihua418000China School of Computer National University of Defense TechnologyChangsha410073China New Energy Centralized Control Center CHN Energy Hunan Power New Energy Co.Ltd.Changsha410000China

Electrocardiogram(ECG)signal is one of the noninvasive physiological measurement techniques commonly usedin cardiac ***,in real scenarios,the ECGsignal is susceptible to various noise erosion,which affectsthe subsequent pathological ***,the effective removal of the noise from ECG signals has becomea top priority in cardiac diagnostic *** at the problem of incomplete signal shape retention andlow signal-to-noise ratio(SNR)after denoising,a novel ECG denoising network,named attention-based residualdense shrinkage network(ARDSN),is proposed in this ***,the shallow ECG characteristics are extractedby a shallow feature extraction network(SFEN).Then,the residual dense shrinkage attention block(RDSAB)isused for adaptive noise ***,feature fusion representation(FFR)is performed on the hierarchicalfeatures extracted by a series of RDSABs to reconstruct the de-noised ECG *** on the MIT-BIHarrhythmia database and MIT-BIH noise stress test database indicate that the proposed scheme can effectively resistthe interference of different sources of noise on the ECG signal.

关键词： Electrocardiogram signal denoising signal-to-noise ratio attention-based residual dense shrinkage network MIT-BIH

来源：评论

学校读者我要写书评

暂无评论

Layer normalized OpenGAN framework for human intrusion activity recognition in a φ-OTDR optical fiber sensing system

引用

Optics Express 2025年第10期33卷 20272-20295页

作者： Zhou, Zhengxian Wang, Xiankun Xie, Tianchang Qu, Jun Shi, Jianping Zhang, Dawei Peng, Jiansheng Zhuang, Songlin Anhui Province Key Laboratory for Control and Applications of Optoelectronic Information Materials Anhui Normal University Wuhu241000 China School of Optical Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China School of Artificial Intelligence and Manufacturing Hechi University Guangxi546300 China

Distributed optical fiber vibration sensing systems (DVS) are widely employed in perimeter security for their high sensitivity, simplicity, and strong immunity to electromagnetic interference. However, these systems are facing with two serious challenges: accurately classifying closed-set signals (known events) and detecting open-set signals (unknown events). To address this, we propose an open-set recognition framework, ResEff-OpenGAN-LN. By integrating layer normalization into the OpenGAN architecture, this framework mitigates instability caused by input feature variations while leveraging ResEff for efficient feature extraction to enhance closed-set classification. Experimental results show that ResEff achieves 99.92% accuracy on closed-set tasks, and ResEff-OpenGAN-LN obtains an AUROC of 0.9900 with 96.63% overall accuracy on mixed datasets containing open-set and closed-set signals, validating its potential to improve intrusion detection and reduce false alarms. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Light interference

来源：评论

学校读者我要写书评

暂无评论

A Novel Radar Emitter Fingerprint for Multiple Path Propagation Environment

A Novel Radar Emitter Fingerprint for Multiple Path Propagat...

引用

IET International Radar Conference 2023, IRC 2023

作者： Wang, Xuefei Zhu, Mengtao Zhang, Ruibin Li, Yunjie School of Information and Electronics Beijing Institute of Technology Beijing China School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing China

ISBN: (纸本)9781839539954

Mining additional modulation information of signal propagation environment as a new fingerprint feature is more important for modern radar reconnaissance systems. This paper proposes a definition and processing method of a new radar emitter fingerprint from multiple path propagation environment, and demonstrates its application in an improved radar pulses deinterleaving task. For the fingerprint generation, the proposed method reconstructs a reference radar pulse by pulse description words (PDW) and correlate it to intercepted pulse sequence firstly. Then an adaptive threshold is utilized to pick out the main peaks belonging to the same radar. Next all the selected range profiles take a procedure of self-focusing and coherent accumulation among different pulses. Finally, propagation environment fingerprint (PEFP) is obtained after eliminating main-peak by CLEAN in the accumulated results. For the deinterleaving application, a sparse auto-encoder (AE) is used to extract high dimensional features from the generated PEFPs, then the features are combined into traditional PDW as extended features to implement an improved deinterleaving task. Simulation results verify the validity and effectiveness of the proposed fingerprint. The PEFP enhanced deinterleaving processing can improve the precision by 6% in non-cooperative conditions compared with traditional methods. © The Institution of Engineering & technology 2023.

关键词： Radar signal processing

来源：评论

学校读者我要写书评

暂无评论

Exposure-NeuS: Multi-View Head Reconstruction Using Exposure-Distorted Data

Exposure-NeuS: Multi-View Head Reconstruction Using Exposure...

引用

2024 International Annual Conference on Complex Systems and Intelligent science, CSIS-IAC 2024

作者： Cheng, Zhanliang Peng, Bo An, Ning School of Data Science University of Science and Technology of China Hefei China School of Mathematical Science University of Science and Technology of China Hefei China Research Institute of Mine Artificial Intelligence China Coal Research Institute Beijing100013 China State Key Laboratory of Intelligent Coal Mining and Strata Control Beijing100013 China

ISBN: (纸本)9798331504755

We propose Exposure-NeuS, a high fidelity human head reconstruction method from multi-view images, even from exposure-distorted images. Previous methods either did not reconstruct with sufficient accuracy, such as failing to reconstruct hair, or resulted in artifacts or holes in the reconstructed results due to exposure in the input data. To solve these challenging problems, we improve the original fine sampling of the model by using piecewise power function sampling to obtain sampling points closer to the real surface. And we develop a prior latent code to implicitly model factors such as environment and exposure. Experiments show that we eliminate or reduce the erroneous facial depressions and hair holes that occur in the baseline method during reconstruction. Released code is provided as follows:https://***/zhanliangOO/*** © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Secure Recursive State Estimation of Networked Systems Against Eavesdropping: A Partial-Encryption-Decryption Method

引用

IEEE Transactions on Automatic control 2024年第6期70卷 3681-3694页

作者： Zou, Lei Wang, Zidong Shen, Bo Dong, Hongli Donghua University College of Information Science and Technology Engineering Research Center of Digitalized Textile and Fashion Technology Ministry of Education Shanghai201620 China Brunel University London Department of Computer Science UxbridgeUB8 3PH United Kingdom Northeast Petroleum University Artificial Intelligence Energy Research Institute Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Daqing163318 China

This paper addresses the problem of secure recursive state estimation for a networked linear system, which may be vulnerable to interception of transmitted measurement data by eavesdroppers. To effectively protect information security, an encryption-decryption-based communication scheme can be used, but encrypting all the measurement data from sensors can result in significant computational costs. To address this issue, a partial-encryption-decryption (PED) mechanism is proposed to enhance information security with relatively low computational costs. In this mechanism, only part of the transmitted measurement signals are encrypted, and the remaining signals are transmitted directly to the estimator. A Jordan-canonical-form-based approach is developed to select the appropriate parameter for the PED mechanism, and recursive formulas for the state estimator are designed based on the principle of minimum mean squared error. Sufficient conditions are derived to guarantee the ultimate boundedness of the estimation error variance matrix. Finally, the proposed PED-based recursive state estimation scheme is evaluated through two simulation examples to demonstrate its effectiveness. © 1963-2012 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Energy management of solid oxide fuel cell/lithium battery hybrid system

引用

CSEE Journal of Power and Energy Systems 2022年 1-14页

作者： Li, Dong Zhong, Xiao Bo Xu, Yuan Wu Wei, Chong Yang Zhao, Song Jiang, Jianhua Deng, Zhonghua Fu, Xiaowei Li, Xi School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry Huazhong University of Science and Technology Hubei Wuhan430074 China College of Computer Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan430081 China

The research of fuel cell and lithium battery hybrid system has attracted more and more researchers because of its advantages of low emission. However, the lower efficiency of energy management has been a critical factor that obstruct the commercialization of hybrid system. In this work, based on finite element ideas, a solid oxide full cell node model is developed to accurately estimate the operating status of the fuel cell. As for lithium battery, previous energy management studies generally only focused on state of charge, however, state of health is also a key parameter for lithium battery. In this paper, considering the strong coupling between variables we use particle filter algorithm to jointly estimate the state of charge and state of health. To reasonably distribute and manage the energy in the hybrid system, a T-S fuzzy controller for the hybrid system is designed by controlling the state variables in the SOFC model and the state of lithium battery. Finally, our algorithm is verified by Dspace simulation platform. The result shows that the hybrid system with the energy management strategy not only meets the real-time sharply changing demand but also ensures the hybrid system working efficiently and safely. © 2022 China Electric Power Research Institute. All rights reserved.

关键词： Hybrid systems

来源：评论

学校读者我要写书评

暂无评论

STGSA:A Novel Spatial-Temporal Graph Synchronous Aggregation Model for Traffic Prediction

引用

IEEE/CAA Journal of Automatica Sinica 2023年第1期10卷 226-238页

作者： Zebing Wei Hongxia Zhao Zhishuai Li Xiaojie Bu Yuanyuan Chen Xiqiao Zhang Yisheng Lv Fei-Yue Wang the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China the Shandong Key Laboratory of Smart Transportation(Preparation) Shandong Jiao Tong UniversityShanghai 200240China the College of Science China University of PetroleumQingdao 266580China the Department of Transportation Engineering School of Transportation Science and TechnologyHarbin Institute of TechnologyHarbin 150090China IEEE

The success of intelligent transportation systems relies heavily on accurate traffic prediction,in which how to model the underlying spatial-temporal information from traffic data has come under the *** existing frameworks typically utilize separate modules for spatial and temporal correlations ***,this stepwise pattern may limit the effectiveness and efficiency in spatial-temporal feature extraction and cause the overlook of important information in some ***,it is lacking sufficient guidance from prior information while modeling based on a given spatial adjacency graph(e.g.,deriving from the geodesic distance or approximate connectivity),and may not reflect the actual interaction between *** overcome those limitations,our paper proposes a spatial-temporal graph synchronous aggregation(STGSA)model to extract the localized and long-term spatial-temporal dependencies ***,a tailored graph aggregation method in the vertex domain is designed to extract spatial and temporal features in one graph convolution *** each STGSA block,we devise a directed temporal correlation graph to represent the localized and long-term dependencies between nodes,and the potential temporal dependence is further fine-tuned by an adaptive weighting ***,we construct an elaborated spatial adjacency matrix to represent the road sensor graph by considering both physical distance and node similarity in a datadriven ***,inspired by the multi-head attention mechanism which can jointly emphasize information from different r epresentation subspaces,we construct a multi-stream module based on the STGSA blocks to capture global *** projects the embedding input repeatedly with multiple different ***,the predicted values are generated by stacking several multi-stream *** experiments are constructed on six real-world datasets,and numerical results show that the proposed STGSA

关键词： Deep learning graph neural network(GNN) multistream spatial-temporal feature extraction temporal graph traffic prediction

来源：评论

学校读者我要写书评

暂无评论

Vision-Based PM2.5 Concentration Estimation with Natural Scene Statistical Analysis

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial intelligence 2024年第6期5卷 2805-2815页

作者： Wang, Guangcheng Shi, Quan Wang, Han Gu, Ke Wei, Mengting Wong, Lai Kuan Wang, Mingxing Nantong University School of Transportation and Civil Engineering Nantong226019 China Beijing University of Technology Faculty of Information Technology Engineering Research Center of Intelligence Perception and Autonomous Control Ministry of Education Beijing Laboratory of Smart Environmental Protection Beijing Artificial Intelligence Institute Beijing100124 China Chinese Academy of Sciences Institute of Software Beijing100045 China Multimedia University Faculty of Computing and Informatics Cyberjaya63100 Malaysia Environmental Science and Technology Company Ltd. Beijing102100 China

As the primary pollutant in China's urban atmosphere, particulate matter (PM)2.5 poses a great threat to the health of residents and ecological stability. An efficient and effective PM2.5 concentration monitoring is essential. Nonetheless, the popular devices for PM2.5 monitoring are developed based on two standards: the microoscillation balance method and the β-ray method, which have high purchase and maintenance costs and slow calculation rates. To this end, we put forward a real-time and reliable vision-based estimation algorithm of PM2.5 concentration. To be specific, the proposed method first develops two natural scene statistical analysis-based visual priors to measure saturation and structural information losses caused by the 'haze' formed by PM2.5. Moreover, we develop a lightweight deep belief network-deep neural network-based PM2.5 concentration estimation model, which learns the mapping from the designed visual priors to PM2.5 concentrations. Experiments confirm the superiority of our vision-based PM2.5 concentration estimation method by comparison with state-of-the-art photo-based PM2.5 monitoring methods. © 2020 IEEE.

关键词： Entropy

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：