检索结果-内蒙古大学图书馆

Application of multi-gene genetic programming based on separable functional network for landslide displacement prediction

引用

Neural Computing and Applications 2015年第6期27卷 1771-1784页

作者： Chen, Jiejie Zeng, Zhigang Jiang, Ping Tang, Huiming School of Automation Huazhong University of Science and Technology Wuhan China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan China Faculty of Engineering China University of Geosciences Wuhan China

Complexity of analysis of landslide hazard is due to uncertainty. In this study, a novel approach multi-gene genetic programming based on separable functional network (MGGPSFN) is presented for predicting landslide displacement. Moreover, Pearson's cross-correlation coefficients and mutual information are adopted to look for the potential input variables for a forecast model in the paper. The performance of new model is verified through one case study in Baishuihe landslide in the Three Gorges Reservoir in China. In addition, we compared it with two methods, back-propagation neural network and radial basis function, and MGGPSFN got the best results in the same measurements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

New results on anti-synchronization of switched neural networks with time-varying delays and lag signals

引用

Neural networks : the official journal of the International Neural Network Society 2016年 81卷 52-8页

作者： Yuting Cao Shiping Wen Michael Z Q Chen Tingwen Huang Zhigang Zeng 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. Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan 430074 China. Electronic address: wenshiping226@***. The Department of Mechanical Engineering The University of Hong Kong Hong Kong. Texas A & M University at Qatar Doha 5825 Qatar.

This paper investigates the problem of global exponential anti-synchronization of a class of switched neural networks with time-varying delays and lag signals. Considering the packed circuits, the controller is dependent on the output of the system as the inner states are very hard to measure. Therefore, it is necessary to investigate the controller based on the output of the neuron cell. Through theoretical analysis, it is obvious that the obtained ones improve and generalize the results derived in the previous literature. To illustrate the effectiveness, a simulation example with applications in image encryptions is also presented in the paper.

关键词： Anti-synchronization Exponential stability Switched neural networks

来源：评论

学校读者我要写书评

暂无评论

Observer-Based Robust Coordinated Tracking of Multi-Agent Systems with Input Saturation

Observer-Based Robust Coordinated Tracking of Multi-Agent Sy...

引用

IEEE Annual Conference on Decision and control

作者： Xiaoling Wang Housheng Su Xiaofan Wang Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China Department of Control Science and Engineering Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781479978878

This paper addresses the robust semi-global coordinated tracking problem of multiple-input multiple-output (MIMO) multi-agent systems with input saturation and communication noise. A distributed observer-based coordinated tracking protocol is constructed by combining a novel parameterized low-and-high feedback technique with the high-gain observers design approach. It is shown that, under the assumptions that each agent is asymptotically null-controllable with bounded controls and the network is connected, semi-global consensus tracking or semi-global swarm tracking can be attained for left-invertible and minimal-phase systems.

关键词： noise(communication) bounded control tracking high gain Agents

来源：评论

学校读者我要写书评

暂无评论

A novel model and behavior analysis for a swarm of multi-agent systems with finite velocity

引用

Chinese Physics B 2014年第9期23卷 590-593页

作者：王良顺吴治海 Key Laboratory of Image Processing and Intelligent Control of the Ministry of Education School of AutomationHuazhong University of Science and Technology Key Laboratory for Advanced Process Control of Light Industry of the Ministry of Education School of Internet of Things EngineeringJiangnan University

Inspired by the fact that in most existing swarm models of multi-agent systems the velocity of an agent can be infinite, which is not in accordance with the real applications, we propose a novel swarm model of multi-agent systems where the velocity of an agent is finite. The Lyapunov function method and LaSalle＇s invariance principle are employed to show that by using the proposed model all of the agents eventually enter into a bounded region around the swarm center and finally tend to a stationary state. Numerical simulations are provided to demonstrate the effectiveness of the theoretical results.

关键词： multi-agent systems swarm finite velocity attraction and repulsion

来源：评论

学校读者我要写书评

暂无评论

A heuristically accelerated multi-agent reinforcement learning algorithm applied to flow line maintenance scheduling

引用

Journal of Computational Information Systems 2015年第6期11卷 2245-2255页

作者： Wang, Xiao Wang, Hongwei Qi, Chao Wang, Xu School of Safety Engineering Shenyang Aerospace University Shenyang China Institute of Systems Engineering/State Key Laboratory of Education Ministry for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China

This paper investigates the maintenance scheduling problem in a flow line system consisting of two series machines with a finite buffer in between. The machines deteriorate with age and have multiple deteriorating quality states represented by multiple decreasing yield levels. The maintenance problem of both machines is modeled as semi-Markov decision processes. A heuristically accelerated multi-agent reinforcement learning algorithm with a feature of incorporating heuristic function for action selection is developed to produce a reasonable maintenance scheduling. A comparison with a Ε-greedy search based exploration algorithm, a simulated annealing search based exploration algorithm, a tabu search based exploration algorithm and a neighborhood search based exploration algorithm in reinforcement learning is presented. The results indicate that the proposed heuristically accelerated multi-agent reinforcement learning algorithm is competitive and has a certain advantage for larger problems. Copyright © 2015 Binary Information Press.

关键词： Tabu search

来源：评论

学校读者我要写书评

暂无评论

A new crossbar architecture based on two serial memristors with threshold

A new crossbar architecture based on two serial memristors w...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiaoping Wang Min Chen Yi Shen Xiaoya Hu Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China School of Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781479919611

This paper presents a memory crossbar based on two serial memristors with threshold characteristic to eliminate the effect of sneak paths, which is a key issue in crossbar memory system leading to great degradation in their performance and power efficiency. At first, we analyze the threshold characteristic of memristor and propose a memristor model with threshold. Based on this model, the paper presents the design and simulation of a non-volatile memory system utilizing two serial memristors with different polarities as a memory cell. This scheme solves the sneak-path problem by taking advantage of the threshold characteristic and the performance with having always high resistance state in all the memory cells, which is validated by simulation results. The scheme also possesses the superior properties of remarkable compatibility and high density.

关键词： Memristors Nonvolatile memory

来源：评论

学校读者我要写书评

暂无评论

Semi-global containment control of multi-agent systems with intermittent input saturation

引用

Journal of the Franklin Institute 2015年第9期352卷 3504-3525页

作者： Housheng Su Gui Jia Michael Z.Q. Chen School of Automation Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Luoyu Road 1037 Wuhan 430074 China Department of Mechanical Engineering The University of Hong Kong Hong Kong

This paper investigates containment control of multi-agent systems with intermittent communications and input saturation on fixed undirected networks . Under the assumption that each agent is asymptotically null controllable with bounded controls and there exists at least one leader that has directed path to each followers, both state feedback and output feedback control protocols are designed by utilizing the algebraic Riccati equation . For any a priori given bounded set , semi-global state feedback and output feedback containment control of multi-agent systems with intermittent communication can be attained. Numerical simulations are provided to ensure the effectiveness of results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A new automatic mass detection method for breast cancer with false positive reduction

引用

Neurocomputing 2015年 152卷 388-402页

作者： Xiaoming Liu Zhigang Zeng 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 College of Computer Science and Technology Wuhan University of Science and Technology Wuhan 430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan 430081 China

Mass localization is a crucial problem in computer-aided detection (CAD) system for the diagnosis of suspicious regions in mammograms. In this paper, a new automatic mass detection method for breast cancer in mammographic images is proposed. Firstly, suspicious regions are located with an adaptive region growing method, named multiple concentric layers (MCL) approach. Prior knowledge is utilized by tuning parameters with training data set during the MCL step. Then, the initial regions are further refined with narrow band based active contour (NBAC), which can improve the segmentation accuracy of masses. Texture features and geometry features are extracted from the regions of interest (ROI) containing the segmented suspicious regions and the boundaries of the segmentation. The texture features are computed from gray level co-occurrence matrix (GLCM) and completed local binary pattern (CLBP). Finally, the ROIs are classified by means of support vector machine (SVM), with supervision provided by the radiologist׳s diagnosis. To deal with the imbalance problem regarding the number of non-masses and masses, supersampling and downsampling are incorporated. The method was evaluated on a dataset with 429 craniocaudal (CC) view images, containing 504 masses. Among them, 219 images containing 260 masses are used to optimize the parameters during MCL step, and are used to train SVM. The remaining 210 images (with 244 masses) are used to test the performance. Masses are detected with 82.4% sensitivity with 5.3 false positives per image (FPsI) with MCL, and after active contour refinement, feature analysis and classification, it obtained 1.48 FPsI at the sensitivity 78.2%. Testing on 164 normal mammographic images showed 5.18 FPsI with MCL and 1.51 FPsI after classification. Experiments on mediolateral oblique (MLO) images have also been performed, the proposed method achieved a sensitivity 75.6% at 1.38 FPsI. The method is also analyzed with free response operating characteristi

关键词： Mass detection Breast cancer Level set Local binary pattern Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Impulsive positive observers and dynamic output feedback stabilization of positive linear continuous systems

引用

International Journal of Robust and Nonlinear control 2016年第13期27卷

作者： Jiang-Wen Xiao Meng-Jie Hu Yan-Wu Wang Wu-Hua Chen 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 China College of Mathematics and Information Science Guangxi University Nanning 530004 China

This paper is concerned with the design and the synthesis of the impulsive positive observer (IPO) for positive linear continuous systems. The IPO can estimate the states for positive systems even when the measured output is only available at discrete-time instants. In this paper, a time-varying weighted copositive Lyapunov function is constructed, and the upper and lower bounds of impulsive intervals method combined with the convex combination technique are used to establish sufficient conditions for the existence of the IPO. Furthermore, the design of the dynamic output feedback controller based on the IPO is addressed to positively stabilize positive linear systems. Algorithms are given to design the IPO and the controller, respectively. Finally, two numerical examples are provided to show the effectiveness of the theoretical results. Copyright © 2016 John Wiley & Sons, Ltd.

关键词： impulsive positive observer dynamic output feedback controller time-varying weighted copositive Lyapunov function positive system upper and lower bounds of impulsive intervals method convex combination technique

来源：评论

学校读者我要写书评

暂无评论

Multistability analysis of a general class of recurrent neural networks with non-monotonic activation functions and time-varying delays

引用

Neural networks : the official journal of the International Neural Network Society 2016年 79卷 117-27页

作者： Peng Liu Zhigang Zeng Jun Wang 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. Electronic address: liupengjz@***. Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan 430074 China. Electronic address: hustzgzeng@***. Department of Computer Science College of Science and Engineering City University of Hong Kong Kowloon Tong Hong Kong. Electronic address: jwang.cs@cityu.edu.hk.

This paper addresses the multistability for a general class of recurrent neural networks with time-varying delays. Without assuming the linearity or monotonicity of the activation functions, several new sufficient conditions are obtained to ensure the existence of (2K+1)(n) equilibrium points and the exponential stability of (K+1)(n) equilibrium points among them for n-neuron neural networks, where K is a positive integer and determined by the type of activation functions and the parameters of neural network jointly. The obtained results generalize and improve the earlier publications. Furthermore, the attraction basins of these exponentially stable equilibrium points are estimated. It is revealed that the attraction basins of these exponentially stable equilibrium points can be larger than their originally partitioned subsets. Finally, three illustrative numerical examples show the effectiveness of theoretical results.

关键词： Cohen–Grossberg neural networks Multistability Non-monotonic activation functions Time-varying delays

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：