检索结果-内蒙古大学图书馆

Unknown input observer-based consensus control of uncertain multi-agent systems under intermittent communication

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS 2024年第18期361卷

作者： Luo, Miaohong An, Qing Su, Housheng Chen, Yin Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Educ Minist China Wuhan 430074 Peoples R China Wuchang Univ Technol Artificial Intelligence Sch Wuhan 430223 Peoples R China Univ Strathclyde Dept Elect & Elect Engn Glasgow City G1 1XW Scotland

This paper investigates the leader-follower consensus problem of uncertain multi-agent systems under directed graph, where the uncertainties arise from unknown disturbance inputs and initial states. The primary approach to addressing the consensus problem in this paper unfolds in two main steps. Firstly, an unknown input observer, composed of an unknown input reconstruction and a Luenberger-like state observer, is constructed to asymptotically estimate the state and the unknown disturbance input of each follower. Secondly, building on the proposed unknown input observer, a distributed control protocol under intermittent communication is introduced to enable each follower to track the leader's trajectory. This control protocol incorporates unknown input reconstruction to mitigate the impact of disturbances. This paper further extends the approach to the case with multiple leaders. Ultimately, through two simulation examples, the validity of the results presented in this paper are verified.

关键词： Interval observer Unknown input observer Multi-agent systems Uncertainty Leader-follower consensus

来源：评论

学校读者我要写书评

暂无评论

Quasisynchronization of Memristive Neural Networks With Communication Delays via Event-Triggered Impulsive control

引用

IEEE TRANSACTIONS ON CYBERNETICS 2022年第8期52卷 7682-7693页

作者： Zhou, Yufeng Zhang, Hao Zeng, Zhigang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430070 Peoples R China Huazhong Univ Sci & Technol Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

This article considers the quasisynchronization of memristive neural networks (MNNs) with communication delays via event-triggered impulsive control (ETIC). In view of the limited communication and bandwidth, we adopt a novel switching event-triggered mechanism (ETM) that not only decreases the times of controller update and the amount of data sent out but also eliminates the Zeno behavior. By using an appropriate Lyapunov function, several algebraic conditions are given for quasisynchronization of MNNs with communication delays. More important, there is no restriction on the derivation of the Lyapunov function, even if it is an increasing function over a period of time. Then, we further propose a switching ETM depending on communication delays and aperiodic sampling, which is more economical and practical and can directly avoid Zeno behavior. Finally, two simulations are presented to validate the effectiveness of the proposed results.

关键词： Delays Switches Synchronization Lyapunov methods Memristors Biological neural networks Stability analysis Communication delays event-triggered impulsive control (ETIC) memristive neural networks (MNNs) quasisynchronization

来源：评论

学校读者我要写书评

暂无评论

Feature Transductive Distribution Optimization for Few-Shot image Classification

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第3期35卷 2230-2243页

作者： Liu, Qing Tang, Xianlun Wang, Ying Li, Xingchen Jiang, Xinyan Li, Weisheng Chongqing Univ Posts & Telecommun Sch Comp Sci & Technol Chongqing 400065 Peoples R China Chongqing Univ Posts & Telecommun Chongqing Key Lab Complex Syst & Bion Control Chongqing 400065 Peoples R China Chongqing Vocat Inst Engn Big Data & Internet Things Sch Chongqing 402260 Peoples R China Chongqing Univ Posts & Telecommun Chongqing Key Lab Image Cognit Minist Educ Chongqing 400065 Peoples R China Chongqing Univ Posts & Telecommun Key Lab Cyberspace Big Data Intelligent Secur Minist Educ Chongqing 400065 Peoples R China

Few-shot learning (FSL) requires vision models to quickly adapt to brand-new classification tasks with changing task distributions in the presence of limited annotated samples. However, the learned model is susceptible to overfitting and may fail to identify effective classification boundaries due to the biased distribution resulting from a limited number of training samples. Moreover, if the support samples from different classes in the new task are in close proximity, this may lead to fuzzy or even biased class decision boundaries. To address the issues, we propose a generation-based Feature Transductive Distribution Optimization (FTDO) in our research. Specifically, we calibrate the distribution of novel classes by utilizing high-confidence unlabeled query samples from these novel classes, together with the statistics of similar base classes, to generate a sufficient number of virtual training samples. In addition, we introduce a task commonality removal and discriminability enhancement module, which eliminates commonality from all features in the task along the task-commonality direction, and reinforces the retained discriminative features through a channel transformation function. Our method can be implemented using off-the-shelf pre-trained feature extractors and classification models, without requiring additional parameters. Experiments conducted on four few-shot classification datasets substantiate the superiority of our proposed method.

关键词： Few-shot learning distribution calibration image classification image classification image classification

来源：评论

学校读者我要写书评

暂无评论

Bipartite leader-following synchronization of delayed incommensurate fractional-order memristor-based neural networks under signed digraph via adaptive strategy

引用

NEUROCOMPUTING 2022年第0期505卷 413-432页

作者： Jia, Jia Wang, Fei Zeng, Zhigang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Qufu Normal Univ Sch Math Sci Qufu 273165 Shandong Peoples R China

In this work, an adaptive controller, formulated as linear feedback controls plus nonlinear parts, is synthesized to achieve bipartite leader-following synchronization of delayed incommensurate fractionalorder memristor-based neural networks (FMNNs), in which follower FMNNs are linearly coupled under a signed digraph. The salient features of this research lie in two aspects: (1) the assumption on timevarying delays is very weak, since it neither requires boundedness of delays nor restricts the differentiation of time delay functions;(2) the adaptive controller contains no delay term, and it is feasible for both bounded and unbounded activation functions. As the preparatory work for stability analysis of the controlled synchronization error system, the ready-made results on delayed incommensurate fractionalorder linear positive systems, especially stability condition and comparison principle, are perfected by relaxing premises of time-varying delays. Besides, a group of differential inclusion inequalities are established as a powerful aid in scaling the bipartite synchronization error system. More relevantly, an algebraic synchronization criterion, formulated in terms of coupling strength, inner coupling matrix, Laplacian matrix and FMNN system parameters, is proved with the benefit of vector Lyapunov function and positive system theory. With the controller utilized, linear feedback controls can be exerted merely on partial neurons of some selected FMNNs, which is exemplified by numerical simulations.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Fractional-order memristor-based neural networks Incommensurate orders Bipartite synchronization Signed digraph Adaptive strategy

来源：评论

学校读者我要写书评

暂无评论

Consensus-Based Distributed Reduced-Order Observer Design for LTI Systems

引用

IEEE TRANSACTIONS ON CYBERNETICS 2022年第7期52卷 6331-6341页

作者： Wang, Xiaoling Jiang, Guo-Ping Su, Housheng Zeng, Zhigang Nanjing Univ Posts & Telecommun Coll Automat Coll Artificial Intelligence Jiangsu Engn Lab IoT Intelligent Robots Nanjing 210023 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Image Proc & Intelligent Control Key Lab Educ Minist China Wuhan 430074 Peoples R China

In this article, we refocus on the distributed observer construction of a continuous-time linear time-invariant (LTI) system, which is called the target system, by using a network of observers to measure the output of the target system. Each observer can access only a part of the component information of the output of the target system, but the consensus-based communication among them can make it possible for each observer to estimate the full state vector of the target system asymptotically. The main objective of this article is to simplify the distributed reduced-order observer design for the LTI system on the basis of the consensus communication pattern. For observers interacting on a directed graph, we first address the problem of the distributed reduced-order observer design for the detectable target system and provide sufficient conditions involving the topology information to guarantee the existence of the distributed reduced-order observer. Then, the dependence on the topology information in the sufficient conditions will be eliminated by using the adaptive strategy and so that a completely distributed reduced-order observer can be designed for the target system. Finally, some numerical simulations are proposed to verify the theoretical results.

关键词： Observers Linear systems Directed graphs Topology Adaptive systems Consensus protocol Adaptive strategy consensus linear time-invariant (LTI) system reduced-order observer

来源：评论

学校读者我要写书评

暂无评论

Imbalanced regression for intensity series of pain expression from videos by regularizing spatio-temporal face nets

引用

PATTERN RECOGNITION LETTERS 2022年 163卷 152-158页

作者： Xiang, Xiang Wang, Feng Tan, Yuwen Yuille, Alan L. Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automation Key Lab Image Proc & Intelligent Control Educ Minist China Wuhan Peoples R China Johns Hopkins Univ Dept Comp Sci Baltimore MD 21218 USA

Obtaining accurate patient-reported pain intensity is essential for effective pain management. An auto-matic pain recognition system can simplify the pain reporting process and reduce the strain on manual effort s. Limited and imbalanced labeled data are available for the research of estimating the intensity of pain based on facial expressions. However, the ability to train deep networks for automated pain assess-ment is limited by small datasets with imbalanced labels of patient-reported pain levels. Fortunately, fine-tuning from a data-extensive pre-trained domain, such as face verification or recognition, can alleviate this problem to some extent. In this paper, we propose a network which fine-tunes a face verification or recognition network using a regularized regression loss and additional data with pain-intensity labels. The expression intensity regression task can benefit from the rich feature representations trained on a large number of data for face analysis tasks. In order to explore the temporal information between frames, we combine CNN with LSTM to obtain a better prediction result of each frame in videos. A weighted evalua-tion metric and re-sampling technique are also proposed to address the imbalance issue of different pain levels. The proposed regularized deep regressor is applied to estimate the pain expression intensity and verified on the widely-used UNBC-McMaster Shoulder-Pain dataset and BioVid Heat Pain dataset, achiev-ing the state-of-the-art performance. As pain detection is a form of micro facial expression recognition, we also apply the transferred deep regressor to estimate the intensity of facial action units, obtaining high quality performance.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Facial expression LSTM Fine-tuning Regularization

来源：评论

学校读者我要写书评

暂无评论

Distributed Adaptive Output Feedback Consensus of Parabolic PDE Agents on Undirected Networks

引用

IEEE TRANSACTIONS ON CYBERNETICS 2022年第8期52卷 7742-7752页

作者： Qiu, Qian Su, Housheng Zeng, Zhigang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

In this article, we investigate the distributed adaptive consensus problem of parabolic partial differential equation (PDE) agents by output feedback on undirected communication networks, in which two cases of no leader and leader-follower with a leader are taken into account. For the leaderless case, a novel distributed adaptive protocol, namely, the vertex-based protocol, is designed to achieve consensus by taking advantage of the relative output information of itself and its neighbors for any given undirected connected communication graph. For the case of leader-follower, a distributed continuous adaptive controller is put forward to converge the tracking error to a bounded domain by using the Lyapunov function, graph theory, and PDE theory. Furthermore, a corollary that the tracking error tends to zero by replacing the continuous controller with the discontinuous controller is given. Finally, the relevant simulation results are further demonstrated to demonstrate the theoretical results obtained.

关键词： Output feedback Adaptive systems Symmetric matrices Eigenvalues and eigenfunctions Couplings Adaptive control Network topology Adaptive control consensus output feedback undirected networks

来源：评论

学校读者我要写书评

暂无评论

Single image based 3D human pose estimation via uncertainty learning

引用

PATTERN RECOGNITION 2022年 132卷

作者： Han, Chuchu Yu, Xin Gao, Changxin Sang, Nong Yang, Yi Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automation Key Lab Minist Educ Image Proc & Intelligent Control Wuhan 430074 Peoples R China Univ Technol Sydney Ctr Artificial Intelligence Ultimo NSW 2007 Australia

In monocular image scenes, 3D human pose estimation exhibits inherent ambiguity due to the loss of depth information and occlusions. Simply regressing body joints with high uncertainties will lead to model overfitting and poor generalization. In this paper, we propose an uncertainty-based framework to jointly learn 3D human poses and the uncertainty of each joint. Our proposed joint estimation framework aims to mitigate the adverse effects of training samples with high uncertainties and facilitate the training procedure. To be specific, we model each body joint as a Laplace distribution for uncertainty representation. Since visual joints often exhibit low uncertainties while occluded ones have high uncertainties, we develop an adaptive scaling factor, named the uncertainty-aware scaling factor, to ease the network optimization in accordance with the joint uncertainties. By doing so, our network is able to converge faster and significantly reduce the adverse effects caused by those ambiguous joints. Furthermore, we present an uncertainty-aware graph convolutional network by exploiting the learned joint uncertainties and the relationships among joints to refine the initial joint localization. Extensive experiments on single-person (Human3.6M) and multi-person (MuCo-3DHP & MuPoTS-3D) 3D human pose estimation datasets demonstrate the effectiveness of our method. (c) 2022 Elsevier Ltd. All rights reserved.

关键词： Uncertainty 3D pose estimation Graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

Synchronization of Timescale-Type Nonautonomous Neural Networks With Proportional Delays

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2022年第4期52卷 2167-2173页

作者： Xiao, Qiang Huang, Tingwen Zeng, Zhigang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Texas A&M Univ Qatar Sci Program Doha Qatar

Synchronization of a class of drive-response timescale-type nonautonomous proportional-delayed neural networks (TNPNNs) is addressed in this article. The key technique to cope with the proportional term is using comparison principle. By timescale theory, inequality technique, and comparison principle, criteria of synchronization are obtained. The method used in this article is effective to cope with TNPNNs and it is a direct approach as well by eliminating the conventional exponential transformation. The obtained results are verified with three examples.

关键词： Synchronization Neural networks Delays Switches control systems Stability criteria Dynamical systems Nonautonomous neural networks proportional delays synchronization time scale

来源：评论

学校读者我要写书评

暂无评论

Finite-Time Distributed H∞ Filtering in Sensor Networks With Switching Topology and Two-Channel Stochastic Attacks

引用

IEEE TRANSACTIONS ON AUTOMATIC control 2024年第6期69卷 4158-4165页

作者： Zhou, Xin Chen, Guici Zeng, Zhigang Hu, Junhao Wuhan Univ Sci & Technol Coll Sci Wuhan 430065 Peoples R China Huazhong Univ Sci & Technol Sch Automat Wuhan 430074 Peoples R China Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China South Cent Univ Nationalities Sch Math & Stat Wuhan 430074 Peoples R China

This article investigates the finite-time distributed H-infinity filtering problem in sensor networks with switching topology and two-channel stochastic attacks. The two-channel stochastic deception attacks are introduced, encompassing network attacks in the communication channel between the model and the sensor, as well as in the channel between the sensors, implemented through an independent Bernoulli process with uncertain probabilities. To address this problem, a novel distributed filter with two-channel stochastic attacks is designed, considering the switching topology and information transmission between sensors. The corresponding filtering error system is proposed. By utilizing the Lyapunov function technique and stochastic analysis method, some new sufficient conditions are established to demonstrate the stochastic finite-time boundability of the filtering error system and ensure satisfaction of the H-infinity performance index. Moreover, the optimal H-infinity performance index problem is solved to determine the distributed filter gains and establish the lower boundness of the average dwell time of the topology switching signals. Finally, the effectiveness of the proposed design method is validated through two simulation examples.

关键词： Switches Topology Network topology Stochastic processes Information filters Electronic mail Indexes H-infinity filter distributed filter finite-time network attacks sensor networks switching topology

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

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

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：