检索结果-内蒙古大学图书馆

Real-time facial patterns mining and emotion tracking 3rd

3rd International Conference on Advances in Web-Age Information Management, WAIM 2002

作者： Xiang, Zhenggui Yao, Tianxiang Li, Jiang Yu, Keman State Key Laboratory of Intelligent Technology and Systems Dept of Computer Science and Tech Tsinghua University Beijing China Dept of Information System and Electrical Engineering Zhejiang University Zhejiang China Internet Media Group Microsoft Research Asia Beijing China

ISBN: (纸本)9783540440451

In this paper, we present a real-time method for mining the facial patterns and tracking the facial emotion. We first recognize the facial patterns based on a nonsupervised idea of pattern mining from video. To raise the mining speed, we adopt some simple and rapid filters called Gabor-like filters to mine individual feature patterns. To evaluate the facial patterns, we match deformable templates and analyze the histogram of local region. To track the mouth contour, we model dynamically the color distribution of lip and skin by EM algorithm and segment lip color by the Bayes classification rule. Finally, we represent the facial emotion with an avatar by transferring some parameters. Through experiments, our method can rapidly mine the facial patterns and track different facial expressions of different people whether they wear glasses or not. © Springer-Verlag Berlin Heidelberg 2002.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

A method of printing Tibetan character recognition

A method of printing Tibetan character recognition

引用

World Congress on Intelligent Control and Automation (WCICA)

作者： Shaoping Ma Yijiang Jin Zhe Jiang Yu Huang National Key Laboratory of Intelligence Technology and System Department of Computer Tsinghua University Beijing China Department of Computer North Communication University Beijing China

Due to the lack of research in the field of minority nationality character recognition, printing Tibetan character recognition was studied as an example in this paper. An experimental system was set up by applying fuzzy direction line features, which performs very effectively in the off-line Chinese character recognition, into printing Tibetan characters recognition. It can be seen from this primary study that this method is effective in printing Tibetan recognition.

关键词： Printing Character recognition Fuzzy systems Feature extraction Intelligent control Automation

来源：评论

学校读者我要写书评

暂无评论

Human systems integration and advanced technology in engineering department workload and manpower reduction

引用

NAVAL ENGINEERS JOURNAL 2003年第1期115卷 57-65页

作者： Lively, KA Seman, AJ Kirkpatrick, M KENNETH A. LIVELY graduated from the University of Colorado with a BS in applied mathematics and an MS in mathematics in 1976 and from the Massachusetts Institute of Technology with an MS in electrical engineering and the degree ocean engineer in naval architecture and marine engineering in 1984. He retired from the U.S. Navy in 1989 after 23 years of service. Assignments included electrical officer on the USS Constellation (CV 64) project engineer for the DDG 51 machinery control system (NAVSEA) and DDG 51 Technical Director (NAVSEA). He was vice president of the PDI Division of Bird-Johnson Company from July 1989 to November 1998 where he managed various gas turbine and machinery controls related development projects. He joined Anteon Corporation's Systems Engineering Group as senior controls engineer in December 1998 where he provided technical support to the integrated power systems program (NAVSEA PMS 510) and managed the Office of Naval Research Afloat Laboratory. DR. MARK KIRKPATRICK is currently an independent consultant in human factors and work-load/manning analysis and modeling. He holds a Ph.D. degree in experimental psychology from The Ohio State University and has 34 years of experience in applied human factors. From 1982 through 2000 Dr. Kirkpatrick served as the senior vice president of Carlow International. Prior to joining Carlow in 1982 Dr. Kirkpatrick served as a member of the technical staff at North American Rockwell's Missiles Division and as a project director and vice president for Essex Corporation. His areas of expertise include workload simulation task analysis operator-in-the-loop simulation human performance experimentation statistical analysis and human factors T&E. He has directed and/or participated in human factors projects for the U.S. Navy U.S. Army NASA Department of Transportation the U.S. Nuclear Regulatory Commission and private industry. ANTHONY J. SEMAN III is the technical manager for the reduced ship's crew by virtual presence (RSVP) advanced technology d

Aboard current ships, such as the DDG 51, engineering control and damage control activities are manpower intensive. It is anticipated that, for future combatants, the workload demand arising from operation of systems under conditions of normal steaming and during casualty response will need to be markedly reduced via automated monitoring, autonomous control, and other technology initiatives. Current DDG 51 class ships can be considered as a manpower baseline and under Condition III typical engineering control involves seven to eight watchstanders at manned stations in the Central Control Station, the engine rooms and other machinery spaces. In contrast to this manning level, initiatives such as DD 21 and the integrated engineering plant (IEP) envision a partnership between the operator and the automation system, with more and more of the operator's functions being shifted to the automation system as manning levels decrease. This paper describes some human systems integration studies of workload demand reduction and, consequently, manning reduction that can be achieved due to application of several advanced technology concepts. Advanced system concept studies in relation to workload demand are described and reviewed including. Piecemeal applications of diverse automation and remote control technology concepts to selected high driver tasks in current DDG 51 activities. Development of the reduced ship's crew by virtual presence system that will provide automated monitoring and display to operators of machinery health, compartment conditions, and personnel health. The IEP envisions the machinery control system as a provider of resources that are used by various consumers around the ship. Resource needs and consumer priorities are at all times dependent upon the ship's current mission and the availability of equipment pawnbrokers.

关键词： Naval warfare

来源：评论

学校读者我要写书评

暂无评论

Anaphora resolution in Chinese financial news for information extraction

Anaphora resolution in Chinese financial news for informatio...

引用

World Congress on Intelligent Control and Automation (WCICA)

作者： Ning Wang Chunfa Yuan K.F. Wong Wenjie Li Department of Computer Science & Technology State Key Laboratory of Intelligent Technology and System Tsinghua University Beijing China Department of System Engineering & Engineering Management Chinese University of Hong Kong Hong Kong China Department of Computing Hong Kong Polytechnic University Hong Kong China

Anaphora always appears in the text and it is a hot topic in linguistics and computational linguistics area. Anaphora resolution is an important part of the information extraction, and it is also important to discourse understanding, machine translation, abstract extraction and so on. After studying on the text in Chinese financial domain, an anaphora resolution system is proposed, which is built on a set of filtration rules and a set of evaluation rules. The experiment result shows the precision is 91.4%.

关键词： Data mining Laboratories Intelligent systems computer science systems engineering and theory Research and development management Computational linguistics Filtration Intelligent control Automation

来源：评论

学校读者我要写书评

暂无评论

A force feedback system based on robot control

A force feedback system based on robot control

引用

World Congress on Intelligent Control and Automation (WCICA)

作者： Yang Zehong Jia Peifa Zhao Yannan Yang Yuandong The State Key Laboratory of Intelligent Technology and System Department of Computer Science and Technology Tsinghua University Beijing China Tsinghua University Beijing Beijing CN Dept. of Comput. Sci. & Technol. Tsinghua Univ. Beijing China

This paper mainly introduces the designed force feedback system based on robot control. It first introduces the framework of the force feedback system, the higher and lower level control system, and some of the relate... 详细信息

关键词： Robot control Force feedback Laboratories Intelligent systems Intelligent robots computer science State feedback Level control virtual reality Intelligent control

来源：评论

学校读者我要写书评

暂无评论

Hyper-Distributed Hyper-Parallel Self-Organizing Dynamic Scheduling Based on Solitary Wave

引用

Journal of computer Science & technology 2001年第5期16卷 434-442页

作者：帅典勋顾静顾慧平邓志东 Department of Computer Science East China University of Science and Technology Shanghai P.R. China State Key Laboratory of Intelligence Technology and System Tsinghua University Beijing P.R. China

This paper presents a new soliton approach to hyper-distributed hyper-parallel self-organizing dynamic scheduling for task allocations among rational autonomous agents in a multi-agent system (MAS). This approach can overcome many drawbacks of other mechanisms currently used for coalition formation and cooperation in MAS. The thorny problems, such as overabundant bid, social behaviors, colony intelligence, variable neighbors, and interdepen-dency, can easily be treated by using the proposed approach, whereas they are very difficult for other conventional approaches. The simulation on a distributed transport scheduling sys-tem shows the soliton approach featured by hyper-parallelism, effectiveness, openness, dynamic alignment and adaption.

关键词： soliton distributed artificial intelligence multi-agent system hyper-distributed hyper-parallel problem-solving dynamic task allocation

来源：评论

学校读者我要写书评

暂无评论

Learning bayesian networks with hidden variables using the combination of em and evolutionary algorithms 5th

引用

5th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2001

作者： Tian, Fengzhan Lu, Yuchang Shi, Chunyi The State Key Laboratory of Intelligent Technology and System The Department of Computer Science and Technology Tsinghua University Beijing100084 China

ISBN: (纸本)3540419101

In this paper, a new method, called EM-EA, is put forward for learning Bayesian network structures from incomplete data. This method combines the EM algorithm with an evolutionary algorithm (EA) and transforms the incomplete data to complete data using EM algorithm and then evolve network structures using the evolutionary algorithm with the complete data. In order to learn Bayesian networks with hidden variables, a new mutation operator has been introduced and the function of the crossover has been correspondingly expanded. The results of the experiments show that EM-EA is more accurate and practical than other network structure learning algorithms that deal with the incomplete data. © Springer-Verlag Berlin Heidelberg 2001.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

引用

5th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2001

作者： Ming, Xiao Lu, Yuchang Shi, Chunyi The State Key Laboratory of Intelligent Technology and System Computer Science and Technology Dept Tsinghua University Beijing100084 China

ISBN: (纸本)3540419101

Currently there is no model available that would facilitate the task of finding similar time series based on partial information that interest users. We studied a novel query problem class that we termed micro similarity queries (MSQ) in this paper. We present the formal definition of MSQ. A method is investigated for the purpose of efficient processing of MSQ. We evaluated the behavior of MSQ problem and our query algorithm with both synthetic data and real data. The results show that the knowledge revealed by MSQ corresponds with the subjective feeling of similarity based on singular interest. © Springer-Verlag Berlin Heidelberg 2001.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Incremental learning of bayesian networks with hidden variables

引用

作者： Tian, Fengzhan Zhang, Hongwei Lu, Yuchang Shi, Chunyi State Key Laboratory of Intelligent Technology and System Department of Computer Science and Technology Tsinghua University 100084 Beijing China

ISBN: (纸本)0769511198

In this paper, an incremental method for learning Bayesian networks based on evolutionary computing, IEMA, is put forward. IEMA introduces the evolutionary algorithm and EM algorithm into the process of incremental learning, can not only avoid getting into local maxima, but also incrementally learn Bayesian networks with high accuracy in presence of missing values and hidden variables. In addition, we improved the incremental learning process by Friedman et al. The experimental results verified the validity of IEMA. In terms of storage cost, IEMA is comparable with the incremental learning method of Friedman et al, while it is more accurate. © 2001 IEEE.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Incremental learning of Bayesian networks with hidden variables

引用

IEEE International Conference on Data Mining (ICDM)

作者： Fengzhan Tian Hongwei Zhang Yuchang Lu Chunyi Shi The State Key Laboratory of Intelligent Technology and System The Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)0769511198

An incremental method for learning Bayesian networks based on evolutionary computing, IEMA, is put forward. IEMA introduces the evolutionary algorithm and EM algorithm into the process of incremental learning; it can avoid getting into local maxima, and also incrementally learn Bayesian networks with high accuracy in the presence of missing values and hidden variables. In addition, we improved the incremental learning process by N. Friedman and M. Goldschmidt (1997). The experimental results verified the validity of IEMA. In terms of storage cost, IEMA is comparable with the incremental learning method of Friedman et al, while it is more accurate.

关键词： Bayesian methods Statistics Learning systems Evolutionary computation Laboratories Intelligent systems Intelligent networks computer science computer networks Costs

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：