检索结果-内蒙古大学图书馆

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

Learning binary codes with Bagging PCA

Learning binary codes with Bagging PCA

引用

European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2014

作者： Leng, Cong Cheng, Jian Yuan, Ting Bai, Xiao Lu, Hanqing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9783662448502

For the eigendecomposition based hashing approaches, the information caught in different dimensions is unbalanced and most of them is typically contained in the top eigenvectors. This often leads to an unexpected phenomenon that longer code does not necessarily yield better performance. This paper attempts to leverage the bootstrap sampling idea and integrate it with PCA, resulting in a new projection method called Bagging PCA, in order to learn effective binary codes. Specifically, a small fraction of the training data is randomly sampled to learn the PCA directions each time and only the top eigenvectors are kept to generate one piece of short code. This process is repeated several times and the obtained short codes are concatenated into one piece of long code. By considering each piece of short code as a "super-bit", the whole process is closely connected with the core idea of LSH. Both theoretical and experimental analyses demonstrate the effectiveness of the proposed method. © 2014 Springer-Verlag.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Research in video detection of lane curve and its application in speed alert system

引用

Research Journal of Applied sciences, engineering and Technology 2014年第5期7卷 957-962页

作者： Song, Maliang Liu, Xiaoyan Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Province 650500 China Yunnan Provincial Key Laboratory of Computer Application Technology Yunnan Province 650500 China

That vehicles travel on a curve with excessive speed tends to skid or roll over. This study presents research in video recognition technology of lane and its application in traffic early safety alert system, which improves traffic safety. In our study, we use a monocular camera to acquire the image of the road ahead. Techniques such as gray-scale transformation, filtering, edge detection and curve fitting are used for the recognition of the lane line and curve fitting. Then radius of curvature of the road ahead will be extracted and then the maximum safe speed, which is to be compared with the speed of the vehicle in safety alert system. Experiments show that this method can accurately calculate the radius of the curve ahead and timely give alert message when the vehicle's speed exceeds safe speed. © Maxwell Scientific Organization, 2014.

关键词： computer image processing Coordinate transform Monocular vision Speed alert

来源：评论

学校读者我要写书评

暂无评论

Passivity-based global stabilization of a class of switched nonlinear systems by backstepping 33

Passivity-based global stabilization of a class of switched ...

引用

第三十三届中国控制会议

作者： Pang Hongbo Zhao Jun Dimrovski Georgi M. State Key Laboratory of Synthetical Automation of Process Industries College of Information Science and EngineeringNortheastern University College of Science Liaoning University of Technology Department of Computer Engineering Dogus UniversityKadikoyIstanbul TR-34722Turkey

ISBN: (纸本)9781479947249

This paper considers the global stabilization problem for a class of switched nonlinear ***-based global stabilization controller and a state-dependent switching law of switched nonlinear systems with any relative degree are designed with the help of the recursive feedback passification design ***,a numerical example is presented to illustrate the effectiveness of our results.

关键词： Switched nonlinear system,Recursive feedback passification,Multiple storage functions,Passsivity-based stabiliz-ation.

来源：评论

学校读者我要写书评

暂无评论

Robust remote tracking control with partly quantized information and packed-dropout 33

Robust remote tracking control with partly quantized informa...

引用

第三十三届中国控制会议

作者： GE Yang WANG Jingcheng LI Kang Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China School of Electronics Electrical Engineering and Computer ScienceQueen’s University Belfast

ISBN: (纸本)9781479947249

This paper mainly discusses the remote tracking problem with partly quantized information and packet-dropout. Since the network exists between the remote plant and the local plant, any information transmitted between each other will experience the quantization errors and may be lost. In this situation, the controller of the local system needs to consider both the exact local information and the inaccurate remote information. A state feedback controller is adopted and the theorems to design such controller are given in terms of bilinear matrix inequalities(BMIs). Moreover, an algorithm is proposed and these BMIs are converted into a convex optimization problem. Finally, the efficiency of the proposed method is demonstrated by a simulation example.

关键词： Networked control systems,robust control,quantized,remote tracking,packet-dropout

来源：评论

学校读者我要写书评

暂无评论

Robust Fault Tolerant Control on Distributed Networked Control Systems with Quantized Outputs 33

Robust Fault Tolerant Control on Distributed Networked Contr...

引用

第三十三届中国控制会议

ISBN: (纸本)9781479947249

In this paper, we consider the robust fault tolerant control of the distributed networked control systems(DNCSs). In DNCSs, sub-systems are connected with each other through a communication network. Each sub-system has its own sensor, controller, actuator and quantizer. The output of each sub-system will be transmitted to all other sub-systems through the network. As a result, quantization errors and packet-dropouts cannot be avoided. We also consider the actuator faults situations, including outage, loss of effectiveness and impulse which is modeled by a Markov chain in this paper. A mode-based static output feedback controller is proposed to stable the DNCSs and to meet the robust H-inf performance. Finally, a simulation example is given to illustrate the effectiveness of the proposed method.

关键词： Distributed networked control systems,robust control,fault tolerant,quantized

来源：评论

学校读者我要写书评

暂无评论

A Novel Online Model for Furnace Exit Gas Temperature of Coal-fired Boiler 33

A Novel Online Model for Furnace Exit Gas Temperature of Coa...

引用

第三十三届中国控制会议

作者： Liu Zhengfeng Wang Jingcheng Shi Yuanhao Zhang Langwen Li Kang Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information ProcessingMinistry of Education of China School of Electronics Electrical Engineering and Computer Science Queen's University Belfast

ISBN: (纸本)9781479947249

Furnace exit gas temperature(FEGT) is the key parameter in the furnace ash fouling monitoring system. Since the standard least squares support vector machine(LSSVM) is not suitable for online identification and control of FEGT,a novel CM-LSSVM-PLS method is proposed to predict FEGT in this paper. In the process of CM-LSSVM-PLS method, c-means cluster(CM) algorithm is used to partition the training data into several different subsets by considering the characteristics of operational data. Submodels are subsequently developed in the individual subsets based on LSSVM method. Partial least squares algorithm(PLS) is employed as the combination strategy. The online updating algorithm is then applied to the CM-LSSVM-PLS model. The proposed online model is verified through operation data of a 300 MW generating unit. The simulation results show that the proposed online updating model is effective for online FEGT forecasting.

关键词： Coal-fired boiler Furnace exit gas temperature C-means cluster Least squares support vector machine Partial least squares Online updating

来源：评论

学校读者我要写书评

暂无评论

Online Chinese-Vietnamese bilingual topic detection based on RCRP algorithm with event elements 3

Online Chinese-Vietnamese bilingual topic detection based on...

引用

3rd CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2014

作者： Long, Wen-Xu Gao, Ji-xun Yu, Zheng-tao Gao, Sheng-xiang Hong, Xu-dong School of Information Engineering and Automation Kunming University of Science and Technology Kunming650051 China The Intelligent Information Processing Key Laboratory Kunming University of Science and Technology Kunming650051 China School of Computer Science Henan Institute of Engineering Zhengzhou451191 China

ISBN: (纸本)9783662459232

On account of the characteristics of online Chinese-Vietnamese topic detection, we propose a Chinese-Vietnamese bilingual topic model based on the Recurrent Chinese Restaurant Process and integrated with event elements. First, the event elements, including the characters, the place and the time, will be extracted from the new dynamic bilingual news texts. Then the word pairs are tagged and aligned from the bilingual news and comments. Both the event elements and the aligned words are integrated into RCRP algorithm to construct the proposed bilingual topic detection model. Finally, we use the model to determine if the new documents will be grouped into a new category or classified into the existing categories, as a result, to detect a topic. Through the contrast experiment, the proposed model achieves a good effect on topic detection. © Springer-Verlag Berlin Heidelberg 2014.

关键词： computers

来源：评论

学校读者我要写书评

暂无评论

Exemplar-based linear discriminant analysis for robust object tracking

Exemplar-based linear discriminant analysis for robust objec...

引用

作者： Gao, Changxin Chen, Feifei Yu, Jin-Gang Huang, Rui Sang, Nong National Key Laboratory of Science and Technology on Multispectral Information Processing School of Automation Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science and Engineering University of Nebraska-Lincoln LincolnNE68503 United States

ISBN: (纸本)9781479957514

Tracking-by-detection has become an attractive tracking technique, which treats tracking as a category detection problem. However, the task in tracking is to search for a specific object, rather than an object category as in detection. In this paper, we propose a novel tracking framework based on exemplar detector rather than category detector. The proposed tracker is an ensemble of exemplar-based linear discriminant analysis (ELDA) detectors. Each detector is quite specific and discriminative, because it is trained by a single object instance and massive negatives. To improve its adaptivity, we update both object and background models. Experimental results on several challenging video sequences demonstrate the effectiveness and robustness of our tracking algorithm. © 2014 IEEE.

关键词： Discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Analysis of oxygen saturation detection method on intelligent mobile devices

引用

Ruan Jian Xue Bao/Journal of Software 2015年 26卷 165-176页

作者： Chen, Yi-Neng Deng, Xiao-Ming He, Yue Lu, Lu Tian, Feng Wang, Feng Dai, Guo-Zhong Wang, Hong-An Beijing Key Laboratory of Human-Computer Interaction nstitute of Software The Chinese Academy of Sciences Beijing100190 China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing100049 China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650093 China

With the fast development of mobile devices and great concern on health surveillance, it is becoming increasingly popular to collect, analyze, and interpret people's health-related data by using intelligent mobile devices in their daily life. Oxygen saturation is an important physiological parameter referring to the concentration of oxygen in the blood, and prolonged low oxygen levels may lead to respiratory or cardiac arrest. Previous oxygen saturation detection methods require infrared light, however most of the off-the-shelf mobile devices lack such infrared light transmitter and receiver modules. This paper presents a novel oxygen saturation estimation method emplying a RGB camera and visible light in most of mobile devices. By applying of traditional optical oxygen saturation estimation model to mobile devices, and analyzing its problem for those devices, this study proposes a new oxygen saturation estimation model on intelligent mobile devices and offers an approach to solve the baseline drift problem in mobile cameras. Experiments demonstrate the effectiveness of the proposed method and its potentials in many oxygen saturation based researches such as daily-activity based healthcare with mobile devices. © Copyright 2015, Institute of Software, the Chinese Academy of sciences. All rights reserved.

关键词： Cameras

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：