检索结果-内蒙古大学图书馆

9th International Symposium on Neural Networks, ISNN 2012

作者： Wang, Jing He, Haibo Cao, Yuan Xu, Jin Zhao, Dongbin Department of Electrical Computer and Biomedical Engineering University of Rhode Island Kingston RI 02881 United States MathWorks Inc. Natick MA 01760 United States Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ 07030 United States State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9783642313455

In this paper, a hierarchical neural network with cascading architecture is proposed and its application to classification is analyzed. This cascading architecture consists of multiple levels of neural network structure, in which the outputs of the hidden neurons in the higher hierarchical level are treated as an equivalent input data to the input neurons at the lower hierarchical level. The final predictive result is obtained through a modified weighted majority vote scheme. In this way, it is hoped that new patterns could be learned from hidden layers at each level and thus the combination result could significantly improve the learning performance of the whole system. In simulation, a comparison experiment is carried out among our approach and two popular ensemble learning approaches, bagging and AdaBoost. Various simulation results based on synthetic data and real data demonstrate this approach can improve the classification performance. © 2012 Springer-Verlag.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Mobile robots' wall-following controller based on probabilistic spiking neuron model

Mobile robots' wall-following controller based on probabilis...

引用

2012 International Conference on Advances in Mechanics Engineering, ICAME 2012

作者： Wang, Xiuqing Hou, Zeng-Guang Tan, Min Wang, Yongji Xie, Fei Hebei Normal University Shijiazhuang 050031 China State Key Laboratory of Complex Systems and Intelligence Science Institute of Automation The Chinese Academy of Sciences Beijing 100090 China Laboratory for Internet Technologies Institute of Software The Chinese Academy of Sciences South Fourth Street Zhong Guan Cun Beijing 100190 China State Key Laboratory of Computer Science Institute of Software The Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9783037855287

This paper focuses on the third generation of neural networks- Spiking neural networks (SNNs), the novel Spiking neuron model- probabilistic Spiking neuron model (pSNM), and their applications. pSNM is used in mobile robots' behavior control, and a novel mobile robots' wall-following controller based on pSNM is proposed. In the pSNM controller, Spiking time-delayed coding is used for the sensory neurons of the input layer and pSNM is used for the motor neurons in the output layer. Thorpe and Hebbian learning rules are used in the controller. The experimental results show that the controller can control the mobile robots to follow the wall clockwise and counterclockwise successfully. The structure of the controller is simple, and the controller can study online. © (2012) Trans Tech Publications, Switzerland.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

A NoSQL based cached storage solution of GIS Web service

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content Technology and its Applications 2012年第20期6卷 268-276页

作者： Liu, Jin Wu, Yangping Zhuo, Dan Hu, Qiping Wang, Yan Zhang, Wensheng State Key Lab of Software Engineering Computer School Wuhan University China International School of Software Wuhan University China State Key Lab of Management and Control for Complex Systems Institute of Automation Chinese Academy of Science China

One of challenges in GIS Web service is mass GIS data storage and processing. There are at least three obstacles that oppose dealing with this challenge: the mismatch between the frequent requirement of concurrent tasks for accessing data in GIS Web service and the poor performance of conventional storage mechanism such as relational databases;the insufficiency of relational databases to manage complex data types in GIS Web service;the horizontal scalability of storage for non-stop GIS Web service evolution. This paper proposes a distributed cached storage solution, as the mixture of MongoDB storage and Memcached cache, for GIS Web service. Both techniques are closely related to NoSQL that is a class of database management system identified by its non-adherence to the widely used relational database management system (RDBMS) model. A concise case that facilitates a better understanding of this work indicates its feasibility.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Identifying Important Users in Sina Microblog

Identifying Important Users in Sina Microblog

引用

International Conference on Multimedia Information Networking and Security (MINES)

作者： Jiaqi Liu Zhidong Cao Kainan Cui Feng Xie State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Department of Automation Tsinghua University Tsinghua National Lab for Information Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9781467330930

Important users are high-status vertices in social networks. They are everywhere in most fields of society and have big impact on those around them. Although a lot of effort has been made on identifying important users, the efficient methods still need to be developed, especially for the web users from Sina microblog, which is the most popular social networking sites in China and has unique characteristics. In this paper, a machine learning-based method which only uses several attributes on Naive Bayes Classifiers (NBC) and Back Propagation Neural Network (BPNN) was proposed to identify important users. Initial experiments indicate that our method is effective. The result of "high" category has more than 55% accuracy rate. We find the NBC can identify more important users while BPNN has higher accuracy rate. What's more, the numbers of follower and followings in Sina microblog is independent.

关键词： Social network services Training Neural networks Accuracy Security Learning systems Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Learning control of dynamical systems based on Markov decision processes: Research frontiers and outlooks

引用

Zidonghua Xuebao/Acta Automatica Sinica 2012年第5期38卷 673-687页

作者： Xu, Xin Shen, Dong Gao, Yan-Qing Wang, Kai Institute of Automation College of Mechatronic Engineering and Automation National University of Defense Technology Changsha 410073 China Institute of Automation Chinese Academy of Sciences Beijing 100190 China State Key Laboratory of Management and Control for Complex Systems Beijing 100190 China Department of Systems and Industrial Engineering University of Arizona Tucson AZ85721-0020 United States Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology Changsha 410073 China

Learning control of dynamical systems based on Markov decision processes (MDPs) is an interdisciplinary research area of machine learning, control theory, and operations research. The main objective in this research area is to realize data-driven multi-stage optimal control for complex or uncertain dynamical systems. This paper presents a comprehensive survey on the theory, algorithms, and applications of MDP-based learning control of dynamical systems. Emphases are put on recent advances in the theory and methods of reinforcement learning (RL) and adaptive/approximate dynamic programming (ADP), including temporal-difference learning theory, value function approximation for continuous state and action spaces, direct policy search, approximate policy iteration, and adaptive critic designs. Applications and the trends for future research and developments in related fields are also discussed. Copyright © 2012 Acta Automatica Sinica. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

The analysis of a scheduling strategy with energy balance for linear wireless sensor networks

The analysis of a scheduling strategy with energy balance fo...

引用

31st Chinese control Conference, CCC 2012

作者： Wang, Zhengjie Zhao, Xiaoguang Qian, Xu Shandong University of Science and Technology Qingdao 266590 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China Beijing 100083 China

ISBN: (纸本)9789881563811

Considering the linear wireless sensor network application scenarios, such as road, bridge, tunnel and metro where linear network and multi-hop traffic pattern make the energy consumption unbalanced. The nodes near the base station are required to forward the large amount of traffic for other nodes, which exhausts their energy and results in the failure of network monitoring. In order to solve this problem, a linear wireless sensor network and uniform deployment strategy are considered and an optimal scheduling strategy based on the nonlinear programming is presented. The constraint is formed by the energy model and the requirement of balanced energy consumption. The network lifetime can be extended by adjusting the proportion of traffic and the distance to next hop. The factors affecting the energy efficiency are analyzed and simulation is presented. Simulation results show that energy balance can be achieved by adjusting the communication distance and traffic and network lifetime can be extended. © 2012 Chinese Assoc of Automati.

关键词： Energy balance

来源：评论

学校读者我要写书评

暂无评论

A new B2B platform based on cloud computing

A new B2B platform based on cloud computing

引用

2012 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2012

作者： Xiong, Gang Hou, Jiachen Dong, Xisong Nyberg, Timo R. State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China Dongguan Research Institute of CASIA Cloud Computing Center Chinese Academy of Sciences Songshan Lake Dongguan 523808 China Jiang Su China Sciences Intelligent Engineering Co. Ltd. Enterprise Academician Workstation 215000 China BIT Research Centre Aalto University Finland

ISBN: (纸本)9781467324007

With the fast development of Internet and its data scale, B2B (Business to Business), whose speed and high availability advantage is based on Internet, is eroding more and more market share of traditional business. In recent years, the new data processing technologies, such as cloud computing, assure the enhancement of computer's computing capacity;it has become possible for researchers to process and analyze the massive business data, including large scale customer data, and large scale commodity information. A new B2B platform frame, based on cloud computing with less running time and better response efficiency, is proposed here to promote transaction handle efficiency. By adoption of complex network theory and cloud computing technology, the new platform has been evaluated to decrease transaction handle time, and make more benefits. © 2012 IEEE.

关键词： complex networks

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Multi-Winding Power Current Transformer for Power Transmission Lines Inspection Robot

引用

Procedia Engineering 2012年 29卷 2187-2193页

作者： Mingbo Yang Zize Liang Hanbo Qian En Li Guodong Yang State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 P. R. China The Center of Coordination&Support of SASTIND Beijing 100081 P. R. China

Special current transformer (CT) is designed to induct power from the power transmission lines for an inspection robot. Equivalent circuit is used for calculating and modelling the parameters of the current transformer. Air gap analysis is given aiming at adapting dynamic range of bar current, and calculation of the effect of air gap is provided in detail. Ratio change of current transformer is introduced by which the secondary current could be adaptive to the bus current. Simulation results show that dynamic control of length of air gap and turns of the coils could make the current transformer be adaptive to the variable bus current and be more convenient for inducing power for the power transmission lines inspection robot.

关键词： current transformer induction charging inspection robot

来源：评论

学校读者我要写书评

暂无评论

Bottleneck Prediction Method Based on Improved Adaptive Network-based Fuzzy Inference System (ANFIS) in Semiconductor Manufacturing System

引用

Chinese Journal of Chemical Engineering 2012年第6期20卷 1081-1088页

作者：曹政才邓积杰刘民王永吉 College of Information Science and Technology Beijing University of Chemical Technology Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSoutheast University Tsinghua National Laboratory for Information Science and Technology State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China

Semiconductor manufacturing (SM) system is one of the most complicated hybrid processes involved continuously variable dynamical systems and discrete event dynamical systems. The optimization and scheduling of semiconductor fabrication has long been a hot research direction in automation. Bottleneck is the key factor to a SM system, which seriously influences the throughput rate, cycle time, time-delivery rate, etc. Efficient prediction for the bottleneck of a SM system provides the best support for the consequent scheduling. Because categorical data (product types, releasing strategies) and numerical data (work in process, processing time, utilization rate, buffer length, etc.) have significant effect on bottleneck, an improved adaptive network-based fuzzy inference system (ANFIS) was adopted in this study to predict bottleneck since conventional neural network-based methods accommodate only numerical inputs. In this improved ANFIS, the contribution of categorical inputs to firing strength is reflected through a transformation matrix. In order to tackle high-dimensional inputs, reduce the number of fuzzy rules and obtain high prediction accuracy, a fuzzy c-means method combining binary tree linear division method was applied to identify the initial structure of fuzzy inference system. According to the experimental results, the main-bottleneck and sub-bottleneck of SM system can be predicted accurately with the proposed method.

关键词： semiconductor manufacturing system bottleneck prediction adaptive network-based fuzzy inference system

来源：评论

学校读者我要写书评

暂无评论

Low frequency positive real control for delta operator systems

引用

Automatica 2012年第8期48卷 1791-1795页

作者： Hongjiu Yang Yuanqing Xia School of Automation Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing 100081 China Institute of Electrical Engineering Yanshan University Qinhuangdao 066004 China

A strictly positive real control problem for delta operator systems in a low frequency range is presented by using the generalized Kalman–Yakubovic˘–Popov lemma. The objective of the strictly positive real control problem is to design a controller such that the transfer function is strictly positive real and the resulting closed-loop system is stable. Sufficient conditions for the low frequency strictly positive real controller of the closed-loop delta operator systems are presented in terms of solutions to a set of linear matrix inequalities. A numerical example is given to illustrate the effectiveness and potential for the developed techniques.

关键词：

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：