检索结果-内蒙古大学图书馆

IEEE Annual Conference on Decision and Control

作者： Xi Chen Zhiyong Chen Hai-Tao Zhang School of Electrical Engineering and Computer Science The University of Newcastle Callaghan NSW 2308 Australia Key Laboratory of Image Processing and Intelligent Control School of Automation and the State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan 430074 P.R. China

ISBN: (纸本)9781467360890

The conventional output regulation problem aims to achieve reference tracking and disturbance rejection while references and disturbances are generated by an autonomous exosystem. When the exosystem is perturbed by an external event, a novel robust perturbed output regulation problem is formulated and solved in this paper. The formulation arises from a kind of synchronization problem of multiple agents. Hence, the proposed solution leads to a decentralized control algorithm for synchronization of multiple agents with nonlinear heterogeneous dynamics.

关键词： Output Regulation decentralized control algorithm Disturbance rejection external events computer algorithms

来源：评论

学校读者我要写书评

暂无评论

Molecular model for information addressing and transporting based on DNA nanotechnology

Communications in Computer and Information Science

引用

Communications in computer and Information Science 2014年 472卷 29-34页

作者： Chen, Zhihua Qiang, Xiaoli Zhang, Kai Key Laboratory of Image Information Processing and Intelligent Control School of Automation Huazhong University of Science and Technology WuhanHubei430074 China College of Computer Science South-Central University for Nationalities WuhanHubei430074 China School of Computer Science Wuhan University of Science and Technology WuhanHubei430081 China

ISBN: (纸本)9783662450482

DNA-based information processing includes storage, addressing, transporting and error-correction, etc. Here we describe a feasible model that can extract and transport the information from specified sources to targeted destinations. This model is established based on the DNA nanotechnologies of hybridization, DNA strand displacement and nanoparticle aggregation reactions. By adding the extracting strands, the data strands of specified sources can be extracted, and then transported to the targets by the transporting strands. The result could be detected by observing the change of color through the naked eyes. Theoretical analysis indicates that thismodel could achieve the parallel information extracting and transporting from different specified sources to different targeted destination, which offers a realistic technology for the flexibility of managing information. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Performance of combined artificial neural networks for forecasting landslide displacement

Performance of combined artificial neural networks for forec...

引用

International Joint Conference on Neural Networks (IJCNN)

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

An efficient and accurate method for landslide displacement prediction is very important to reduce the casualties and property losses caused by this type of natural hazard. In recent years, many kinds of artificial neural networks (ANNs) have been widely applied to landslide displacement prediction. But we can't know which type of ANN is the best until we have calculated the prediction error. An improper choice of ANN may result in bad prediction results. In this paper, we use a neural networks combination prediction method based on the discounted MSFE (mean squared forecast error) to reduce the risk of selecting the types of ANNs. Four popular ANNs, radial basis function neural network (RBFNN), support vector regression (SVR), least squares support vector machine (LSSVM) and extreme learning machine (ELM), are selected as candidate neural networks. The performance of our model is verified through two case studies in Baishuihe landslide and Bazimen landslide. Experimental results reveal that the combining neural networks can improve the generalization abilities of ANNs.

关键词： Terrain factors Artificial neural networks Monitoring Predictive models Kernel Training

来源：评论

学校读者我要写书评

暂无评论

SEMI-SUPERVISED LEARNING IN TRAFFIC SCENE SURVEILLANCE BASED ON LABEL-PROPAGATION

SEMI-SUPERVISED LEARNING IN TRAFFIC SCENE SURVEILLANCE BASED...

引用

IEEE International Conference on image processing

作者： Meng Liang Zhaoxiang Zhang Yunhong Wang Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing 100191 China

ISBN: (纸本)9781479923427

Object classification in traffic scene surveillance has attracted much attention recent years. Traditional classification methods need lots of labeled samples to build a satisfying classifier. However, the acquisition of the labeled samples may cost lots of time and human labor. In this paper, we propose an label-propagation based semi-supervised learning method which uses the information of both labeled and unlabeled samples. Experiment results show that our method outperforms the traditional methods both in accuracy and robustness.

关键词： traffic scene surveillance object classification label propagation semi-supervised learning Semi-supervised Learning Traffic traffic monitoring Classification Methods

来源：评论

学校读者我要写书评

暂无评论

CROSS-VIEW ACTION RECOGNITION VIA TRANSDUCTIVE TRANSFER LEARNING

CROSS-VIEW ACTION RECOGNITION VIA TRANSDUCTIVE TRANSFER LEAR...

引用

IEEE International Conference on image processing

作者： Jie Qin Zhaoxiang Zhang Yunhong Wang Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing 100191 China

ISBN: (纸本)9781479923427

Human action recognition is a hot topic in computer vision field. Various applicable approaches have been proposed to recognize different types of actions. However, the recognition performance deteriorates rapidly when the viewpoint changes. Traditional approaches aim to address the problem by inductive transfer learning, in which target-view samples are manually labeled. In this paper, we present a novel approach for cross-view action recognition based on transduc-tive transfer learning. We address the problem by transferring instances across views. In our settings, both labels of examples from the target view and the corresponding relation between examples from pairwise views are dispensable. Experimental results on the IXMAS multi-view data set demonstrate the effectiveness of our approach, and are comparable to the state of the art.

关键词： action recognition transfer learning transductive SVM Transfer (Psychology) state of the art target view Recognition (Psychology) Learning

来源：评论

学校读者我要写书评

暂无评论

Small Universal Sequential Spiking Neural P Systems based on Minimum Spike Number

Small Universal Sequential Spiking Neural P Systems based on...

引用

The Second Asian Conference on Membrane Computing(ACMC2013)

作者： Keqin Jiang Yufang Huang Jinbang Xu Zhihua Chen Key Laboratory of Image Processing and Intelligent Control School of Automation Huazhong University of Science and Technology School of Computer and Information Anqing Normal University College of Mathematics Southwest Jiaotong University

Spiking neural P systems (SN P systems, for short) are a class of distributed parallel computing devices inspired from the way neurons communicate by means of spikes. Recently, a variant of SN P systems was considered: at each step the neuron with the minimum number of spikes among the neurons that can spike will fire. In previous literature, it was obtained that such systems can achieve Turing completeness when the computing result is realized through accumulation of spikes in the output neuron. In this work, we use a natural way to define the computing result of the systems, by means of determining the time interval between the first two spikes emitted by the output neuron. As devices of computing functions, we construct a universal sequential SN P system based on minimum spike number (without delay) by using 137 neurons;as generators of sets of numbers, a universal sequential SN P system based on minimum spike number (without delay) with 126 neurons is also obtained.

关键词： Membrane computing, Spiking neural P system, Sequentiality, Small universal system

来源：评论

学校读者我要写书评

暂无评论

Displacement prediction of landslide based on PSOGSA-ELM with mixed kernel

Displacement prediction of landslide based on PSOGSA-ELM wit...

引用

International Workshop on Advanced Computational Intelligence (IWACI)

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

The prediction of landslide displacement is essential for carrying out to improve the disaster warning system and reduce casualties and property losses. This study applies a novel neural network technique, extreme learning machine (ELM) with kernel function, to landslide displacement prediction problem. However, the generalization performance of ELM with kernel function depends closely on the kernel types and the kernel parameters. In this paper, we use a convex combination of Gaussian kernel function and polynomial kernel function in ELM, which may use these two types of kernel functions' advantages. In order to avoid blindness and inaccuracy in parameter selection, a novel hybrid optimization algorithm based on the combination of Particle Swarm Optimization (PSO) and Gravitational Search Algorithm (GSA) is used to optimize the regularization parameter C, the Gaussian kernel parameter γ, the polynomial kernel parameter q and the mixing weight coefficient η. The performance of our model is verified through two case studies in Baishuihe landslide and Yuhuangge landslide.

关键词： Kernel Terrain factors Optimization Hazards Reservoirs Training Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A uniform solution to the independent set problem through tissue P systems with cell separation

引用

Frontiers of computer Science 2012年第4期6卷 477-488页

作者： Xingyi ZHANG Xiangxiang ZENG Bin LUO Zheng ZHANG Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230039China Department of Computer Science Xiamen UniversityXiamen 361005China Key Laboratory of Image Processing and Intelligent Control Department of Control Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China

Membrane computing is an emergent branch of natural computing, which is inspired by the structure and the functioning of living cells, as well as the organization of cells in tissues, organs, and other higher order structures. Tissue P systems are a class of the most investigated computing mod- els in the framework of membrane computing, especially in the aspect of efficiency. To generate an exponential resource in a polynomial time, cell separation is incorporated into such systems, thus obtaining so called tissue P systems with cell separation. In this work, we exploit the computational efficiency of this model and construct a uniform family of such tissue P systems for solving the independent set problem, a well-known NP-complete problem, by which an efficient so- lution can be obtained in polynomial time.

关键词： membrane computing tissue P system cell sep- aration independent set problem

来源：评论

学校读者我要写书评

暂无评论

Degree of Spiking Neural P Systems Without Delay

引用

电子学报(英文版) 2012年第3期21卷 419-424页

作者： JIANG Keqin SHI Xiaolong Key Laboratory of Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan 430074 China School of Computer and Intormation Anqing Teachers College Anqing 246133 China

Spiking neural P systems are a class of dis- tributed parallel computing models inspired from the way neurons communicate with each other by means of electri- cal impulses (called "spikes"). In this paper, we continue the research of normal forms for spiking neural P systems. Specifically, we prove that the degree of spiking neural P systems without delay can be decreased to two without losing the computational completeness (both in the gener- ating and accepting modes).

关键词：电脉冲神经元膜系统并行计算模型延时分布式

来源：评论

学校读者我要写书评

暂无评论

Variable structure multiple model for articulated human motion tracking from monocular video sequences

引用

Science China(Information Sciences) 2012年第5期55卷 1138-1150页

作者： HAN Hong 1,TONG MingLei 2,CHEN ZhiChao 1 & FAN YouJian 1 1 key laboratory of intelligent Perception and image Understanding of Ministry of Education of China,Institute of intelligent Information processing,Xidian University,Xi'an 710071,China 2 School of computer and Information Engineering,Shanghai University of Electric Power,Shanghai 200090,China 1. Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi’an 710071 China2. School of Computer and Information Engineering Shanghai University of Electric Power Shanghai 200090 China

A new model-based human body tracking framework with learning-based theory is introduced in this *** propose a variable structure multiple model (VSMM) framework to address challenging problems such as uncertainty of motion styles,imprecise detection of feature points,and ambiguity of joint *** human joint points are detected automatically and the undetected points are estimated with Kalman *** motion models are learned from motion capture data using a ridge regression *** model set that covers the total motion set is designed on the basis of topological and compatibility relationships,while the VSMM algorithm is used to estimate quaternion vectors of joint *** using real image sequences and simulation videos demonstrate the high efficiency of our proposed human tracking framework.

关键词： human motion tracking ridge regression model groups design variable structure multiple model (VSMM) motion model group adaptation

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：