检索结果-内蒙古大学图书馆

Adaptive pinning cluster synchronization of fractional-order complex dynamical networks

Applied Mathematics and Computation 2014年 231卷 347-356页

作者： Guan-Sheng Wang Jiang-Wen Xiao Yan-Wu Wang Jing-Wen Yi School of Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan 430074 PR China

The problem about cluster synchronization of fractional-order CDNs is studied via a pinning adaptive approach in this paper. Based on the stability theory of fractional differential equations, some sufficient criteria for local and global cluster synchronization of fractional-order CDNs are derived. In this paper, the coupling configuration matrix can be asymmetric as well as reducible and the inner coupling matrix can also be asymmetric. Moreover, the number of pinning nodes in each cluster can be evaluated. Especially, when the coupling strength is large enough and the coupling configuration matrix is symmetric, cluster synchronization can be achieved via pinning a single node in each cluster. Finally, some typical examples are given to illustrate the correctness and effectiveness of our results, a surprising finding is that the synchronization performance will become better as the fractional order decreases in this simulation.

关键词： Complex dynamical networks Cluster synchronization Fractional-order Pinning adaptive control

来源：评论

学校读者我要写书评

暂无评论

DISCOVERING DISTINCTIVE ACTION PARTS FOR ACTION RECOGNITION

DISCOVERING DISTINCTIVE ACTION PARTS FOR ACTION RECOGNITION

引用

IEEE International Conference on image processing

作者： Feifei Chen Nong Sang Changxin Gao Xiaoqin Kuang Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Automation Huazhong University of Science and Technology

ISBN: (纸本)9781479957521

Recent methods based on mid-level visual concepts have shown promising capability in human action recognition field. Automatically discovering semantic entities such as parts for an action class remains challenging. In this paper, we focus on discovering distinctive action parts for recognition of human actions by learning and selecting a small number of discriminative part detectors directly from training videos. We initially train a large collection of candidate Exemplar-LDA detectors from clusters obtained by clustering spatiotemporal patches in whitened space. A novel Coverage-Entropy curve is proposed as a means of measuring the representative and discriminative capabilities of part detectors, and used to select a set of compact and meaningful detectors out of the vast candidates. By integrating these mined detectors into "bag of parts" representation, our approach demonstrates state-of-the-art performance on the UCF50 dataset.

关键词： Action recognition Action part Exemplar LDA

来源：评论

学校读者我要写书评

暂无评论

Multiple neural networks switched prediction for landslide displacement

引用

Engineering Geology 2014年 186卷 91-99页

作者： Lian, Cheng Zeng, Zhigang Yao, Wei Tang, Huiming School of Automation Huazhong University of Science and Technology Wuhan 430074 China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan 430074 China School of Computer Science South-Central University for Nationalities Wuhan 430074 China Faculty of Engineering China University of Geosciences Wuhan 430074 China

An accurate prediction of landslide displacement is challenging and of great interest to governments and researchers. In order to reduce the risk of selecting the types of influencing factors and artificial neural networks (ANNs), a multiple ANNs switched prediction method is proposed for landslide displacement forecasting. In the first stage, a set of individual neural networks are developed based on different environmental factors and/or different training algorithms. In the second stage, a switched prediction method is used to select the appropriate individual neural network for prediction purpose. For verification and testing, three typical landslides in Three Gorges Reservoir, namely Baishuihe landslide, Bazimen landslide and Shiliushubao landslide, are presented to test the effectiveness of our method. Application results demonstrate that the proposed method can significantly improve model generalization and perform similarly to, or better than, the best individual ANN predictor. © 2014 Elsevier B.V.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Connectivity Exploration after Stroke with Structural Equation Modeling

Connectivity Exploration after Stroke with Structural Equati...

引用

2012 Third International Conference on Theoretical and Mathematical Foundations of Computer Science(ICTMF 2012)

作者： Wei Li Hongtao Tan Xiaojun Wang Zhiqiao Yan Department of Control Science and Engineering Image Processing and Intelligent Control Key Laboratory of Education Ministry of ChinaHuazhong University of Science and Technology

Neuroplasticity has been demonstrated to play an important role in function recovery *** this paper,stroke patients and controls were subjected to functional magnetic resonance imaging(fMRI) study for *** group independent componentanalysis was used to get the time courses of the interested regions in *** investigate the reorganization of cerebral cortex after stroke,Structural Equation Modeling(SEM) was applied to construct a locomotor brain network *** results were analyzed to investigate thebrain activity changes involved in the cerebral motor cortex circuitry aroused by the hand *** contrast to healthy people,we found that the brain activity changes of the stroke patientscould not onlyshow the local changes around injured regions,but also the global transformation of brain related to *** the differences were examined in terms of changes in path coefficients between brain regions.

关键词： fMRI,ICA,SEM,Stroke,Neuroplasticity

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Fisher-Markov Selector via Manifold Regularization

Semi-supervised Fisher-Markov Selector via Manifold Regulari...

引用

2012 International Conference on Applied Informatics and Communication(ICAIC 2012)

作者： Dong Chen Lin Zhu JieYang Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China

Feature subset selection is an important approach to deal with high-dimensional data. But selecting the best subset of data is NP hard. So most of feature selection methods cannot handle high-dimensional data efficiently, or they can only obtain local optimum instead of global optimum. In these cases, when the data consist of both labeled and unlabeled data, semi-supervised feature selection can make full use of data information. In this paper, we introduce a novel semi-supervised feature selection algorithm, which is a filter method based on Fisher-Markov selector, thus ours can achieve global optimum and computational efficiency under certain kernels.

关键词： Feature selection, Dimensionality reduction, Manifold regularization, Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Implementation of Memristive Neural Networks with Spike-rate-dependent Plasticity Synapses

Implementation of Memristive Neural Networks with Spike-rate...

引用

International Joint Conference on Neural Networks

作者： Yide Zhang Zhigang Zeng Shiping Wen School of Automation Huazhong University of Science and Technology and Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China

ISBN: (纸本)9781479914821

The property of changing resistance according to applied currents of memristors makes them candidates for emulating synapses in artificial neural networks. In this paper, we introduce a memristive synapse design into neural network circuits. Combined with modified integrate-and-fire (I&F) complementary metal-oxide-semiconducter (CMOS) neurons, the memristive neural network shows similarities to its biological counterpart, in respect of biologically realistic, current-controlled spikes and adaptive synaptic plasticity. Then, the spike-rate-dependent plasticity (SRDP) of the synapse, an extended protocol of the Hebbian learning rule, is originally implemented by the circuit. And some advanced neural activities including learning, associative memory and forgetting are realized based on the SRDP rule. These activities are comprehensively validated on a neural network circuit inspired by famous Pavlov's dog-experiment with simulations and quantitative analyses.

关键词： Neurons Memristors Biological neural networks Biological system modeling Protocols Semiconductor device modeling Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

On the periodic dynamics of memristor-based neural networks with time-varying delays

引用

Information Sciences 2014年 279卷 358-373页

作者： Jiejie Chen Zhigang Zeng Ping Jiang School of Automation Huazhong University of Science and Technology Wuhan 430074 China Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education Wuhan 430074 China

In this paper, we study the existence, uniqueness and stability of periodic solution for a wide class of memristor-based neural networks with time-varying delays. By employing the topological degree theory in set-valued analysis, differential inclusions theory and a new Lyapunov function method, we prove that the neural network has a unique periodic solution, which is globally exponentially stable. Moreover, we prove the existence, uniqueness and global exponential stability of equilibrium point for time-varying delayed memristor-based neural networks with constant coefficients. The obtained results improve and extend previous works on memristor-based or usual neural network dynamical systems with continuous or discontinuous right-hand side. Finally, two numerical examples are provided to show the applicability and effectiveness of our main results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive synchronization of complex dynamical networks with time-varying delays

引用

Circuits, Systems, and Signal processing 2014年第4期33卷 1173-1188页

作者： Liu, Bo Wang, Xiaoling Su, Housheng Zhou, Hongtao Shi, Yuntao Li, Rong College of Science North China University of Technology Beijing 100144 China Department of Automation Shanghai Jiao Tong University Ministry of Education of China Shanghai 200240 China School of Automation Key Laboratory of Education Ministry for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China Key Laboratory of Beijing for Field-bus Technology and Automation North China University of Technology Beijing 100144 China Department of Applied Mathematical Sciences Shanghai Finance University Shanghai 201209 China

This paper addresses the problem of adaptive pinning synchronization of complex dynamical networks with nonlinear delayed intrinsic dynamics and time-varying delays. By introducing decentralized adaptive strategies to both the coupling strengths and the feedback gains, it is proved that the complex dynamical network can synchronize with the desired state for the bounded time-varying delays even when only one node is informed, without any global information of the underlying network. Finally, some numerical simulations are given to verify the main results and show the superiority of these self-designed adaptive strategies. © 2013 Springer Science+Business Media New York.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Flocking of partially-informed multi-agent systems avoiding obstacles with arbitrary shape

引用

Autonomous Agents and Multi-Agent Systems 2014年第5期29卷 943-972页

作者： Li, Jiaojie Zhang, Wei Su, Housheng Yang, Yupu Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Department of Measurement and Control Technology Shanghai Dian Ji University Shanghai China School of Automation Key Laboratory of Image Information Processing and Intelligent Control (Huazhong University of Science and Technology) Ministry of Education National Key Laboratory of Science and Technology on Multispectral Information Processing Huazhong University of Science and Technology Wuhan China

In this paper, we study the flocking problem of multi-agent systems with obstacle avoidance, in the situation when only a fraction of the agents have information on the obstacles. Obstacles of arbitrary shape are allowed, no matter if their boundary is smooth or non-smooth, and no matter it they are convex or non-convex. A novel geometry representation rule is proposed to transfer obstacles to a dense obstacle-agents lattice structure. Non-convex regions of the obstacles are detected and supplemented using a geometric rule. The uninformed agents can detect a section of the obstacles boundary using only a range position sensor. We prove that with the proposed protocol, uninformed agents which maintain a joint path with any informed agent can avoid obstacles that move uniformly and assemble around a point along with the informed agents. Eventually all the assembled agents reach consensus on their velocity. In the entire flocking process, no distinct pair of agents collide with each other, nor collide with obstacles. The assembled agents are guaranteed not to be lost in any non-convex region of the obstacles within a distance constraint. Numerical simulations demonstrate the flocking algorithm with obstacle avoidance both in 2D and 3D space. The situation when every agent is informed is considered as a special case.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A direct adaptive fuzzy sliding mode controller and its application

A direct adaptive fuzzy sliding mode controller and its appl...

引用

IEEE International Conference on Cyber Technology in Automation, control, and Intelligent Systems

作者： Song Hyok Ri Jian Huang Myong Ho Kim Ji Yong Kim Gwangmin Choe Chol Jun Rim School of Automation Huazhong University of Science and Technology Wuhan CHINA Department of Control Science University of Science Pyongyang D. P. R. of Korea (Democratic People's Republic of Korea) Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan CHINA Department of Control Science University of Science Pyongyang D.P.R. of Korea (Democratic People's Republic of Korea) School of Computer Science Kim II Sung university Pyongyang D. P. R. of Korea (Democratic People's Republic of Korea)

ISBN: (纸本)9781479987313

An approach of direct adaptive fuzzy sliding-mode control which combines the fuzzy control with the sliding-mode control, is proposed for the control of a class of unknown nonlinear dynamic systems. The control goal is to obtain a direct adaptive fuzzy sliding-mode control law and a constructive Lyapunov synthesis approach with respect to a class of nonlinear systems without the knowledge of uncertainties. For improving the approximate performance of the fuzzy system, the proposed approach in this study not only online updates the parameter values in the consequence fuzzy sets, but also updates the shape parameters of the membership functions of the prime fuzzy sets. The fuzzy control rules are updated through the online adaptive learning, which makes the output of fuzzy control to approximate to a sliding-mode equivalent control. The asymptotic stability of the overall system based on Lyapunov theory is proved. Some numerical simulation results show the efficiency of the proposed approach.

关键词： Adaptive systems Nonlinear dynamical systems Sliding mode control Fuzzy control Adaptation models

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：