检索结果-内蒙古大学图书馆

International Conference on Image and Graphics (ICIG)

作者： Li Li Zhigeng Pan David Zhang Hangzhou Dianzi University Hangzhou China State Key Laboratory of CAD&CG University of Zhejiang Hangzhou China Multimedia Signal Processing and Department of Computing Hong Kong Polytechnic University Kowloon Hong Kong China

This paper presents a public mesh watermarking algorithm. First, the resultant watermarked image minus the original image is the watermark information. According to the addition property of the Fourier transform, a change of spatial domain will cause a change in the frequency domain. Then, the watermark information is scaled down and embedded in one part of the x-coordinate of the original mesh. Finally, the x-coordinate of the test mesh is amplified before extraction. Experimental results prove that our algorithm is resistant to a variety of attacks without the need for any preprocessing.

关键词： Watermarking Fourier transforms signal processing algorithms Data mining Frequency domain analysis Wavelet domain Partitioning algorithms Noise robustness Equations Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Grading learning for blind source separation

引用

Science in China(Series F) 2003年第1期46卷 31-44页

作者：张贤达朱孝龙保铮 Key Laboratory for Radar Signal Processing Xidian University Department of Automation State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing 100084 China

By generalizing the learning rate parameter to a learning rate matrix, this paper proposes a grading learning algorithm for blind source separation. The whole learning process is divided into three stages: initial stage, capturing stage and tracking stage. In different stages, different learning rates are used for each output component, which is determined by its dependency on other output components. It is shown that the grading learning algorithm is equivariant and can keep the separating matrix from becoming singular. Simulations show that the proposed algorithm can achieve faster convergence, better steady-state performance and higher numerical robustness, as compared with the existing algorithms using fixed, time-descending and adaptive learning rates.

关键词： blind source separation independent component analysis neural computation adaptive learning.

来源：评论

学校读者我要写书评

暂无评论

A new algorithm for 3D projective reconstruction based on infinite homography

A new algorithm for 3D projective reconstruction based on in...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Quan-Bing Zhang Hai-Xian Wang Sui Wei Key Laboratory of Intelligent Computing and Signal Processing Anhui University Hefei China

ISBN: (纸本)0780378652

This paper investigates the problem of how to carry out 3D scene reconstruction from multiple views. It improves the algorithms of projective reconstruction based on the homography induced by the infinite plane which should have 4 points on a reference plane visible in all views given by Hartley and Rother et al., and proposes a new linear algorithm based on 3 points on a reference plane visible in all views. It avoids the difficult task of determining whether 4 object points are coplanar or not, because 3 points which are not collinear just determine a plane.

关键词： Image reconstruction Cameras signal processing algorithms Layout Transmission line matrix methods Inverse problems Gold Measurement standards Maximum likelihood estimation Position measurement

来源：评论

学校读者我要写书评

暂无评论

Mental EEG analysis based on independent component analysis

Mental EEG analysis based on independent component analysis

引用

International Symposium on Image and signal processing and Analysis

作者： Xiaopei Wu Xiaojing Guo The Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University China

ISBN: (纸本)953184061X

The patterns of EEG changes with the mental tasks performed by the subject. In the field of EEG signal analysis and application, the study to get the patterns of mental EEG and then to use them to classify mental tasks has the significant scientific meaning and great application value. But for the reasons of different artifacts contained in EEG, the pattern detection in EEG produced from normal mental states is a very difficult problem. In this paper, independent component analysis is applied to EEG signals collected from different mental tasks .The experiment results show that when one subject performs a single mental task in different trails, the independent components of EEG are very similar. It means that the independent components can be used as the mental EEG patterns to classify the different mental tasks.

关键词： Independent component analysis Electroencephalography signal processing signal processing algorithms Bioelectric phenomena Biomedical signal processing signal analysis Humans Electric potential Brain modeling

来源：评论

学校读者我要写书评

暂无评论

MAGE: Multi-agent environment

MAGE: Multi-agent environment

引用

2003 International Conference on Computer Networks and Mobile computing, ICCNMC 2003

作者： Shi, Zhongzhi Zhang, Haijun Dong, Mingkai Zhao, Zhikung Sheng, Qiujian Jiang, Yuncheng Cheng, Yong Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences PO Box 2704 Beijing100080 China

ISBN: (纸本)0769520332

intelligent agent technology has been raised as the primary technology in the intelligent Internet and mobile computing. In this paper, MAGE (multi-agent environment) is introduced which is an environment for rapidly developing distributed, heterogeneous multi-agent systems. Agent model, agent architecture, MAGE platforms, comparison between MAGE and other multi-agent framework is presented in the paper. This paper illustrates two application systems, such as e-business, parallel Web spider. The MAGE is written in Java and is a powerful tool to construct multi-agent systems for Internet applications. © 2003 IEEE.

关键词： Computer architecture

来源：评论

学校读者我要写书评

暂无评论

GHUNT:A SEMANTIC INDEXING SYSTEM BASED ON CONCEPT SPACE

GHUNT:A SEMANTIC INDEXING SYSTEM BASED ON CONCEPT SPACE

引用

2003 International Conference on Natural Language processing and Knowledge Engineering

作者： Qing He Ziyan Jia Jiayou Li Haijun Zhang Qingyong Li Zhongzhi Shi Key Laboratory of Intelligent Information Processing Institute of Computing Technology

How to get text information from this huge information space becomes an even important problem with rapid growth of the *** this paper,a semantic indexing system GHUNT based on concept space is proposed to solve the problem. Some new technologies are integrated in GHUNT to obtain good *** is an all-sided solution for information retrieval on Internet.

关键词： Semantic indexing Concept space

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Based intelligent Information and Engineering Systems 1

引用

丛书名： Lecture Notes in Computer Science

2003年

作者： Vasile Palade Robert J. Howlett Lakhmi Jain

ISBN: (数字)9783540452249

ISBN: (纸本)9783540408031

2.1 Text Summarization “Text summarization is the process of distilling the most important information from a source (or sources) to produce an abridged version for a particular user (or users) and task (or tasks)” [3]. Basic and classical articles in text summarization appear in “Advances in automatic text summarization” [3]. A literature survey on information extraction and text summarization is given by Zechner [7]. In general, the process of automatic text summarization is divided into three stages: (1) analysis of the given text, (2) summarization of the text, (3) presentation of the summary in a suitable output form. Titles, abstracts and keywords are the most common summaries in Academic papers. Usually, the title, the abstract and the keywords are the first, second, and third parts of an Academic paper, respectively. The title usually describes the main issue discussed in the study and the abstract presents the reader a short description of the background, the study and its results. A keyword is either a single word (unigram), e.g.: ‘learning', or a collocation, which means a group of two or more words, representing an important concept, e.g.: ‘machine learning', ‘natural language processing'. Retrieving collocations from text was examined by Smadja [5] and automatic extraction of collocations was examined by Kita et al. [1].

关键词： Artificial Intelligence Computer Communication Networks Information Storage and Retrieval Computer and Information Systems Applications User Interfaces and Human Computer Interaction IT in Business

来源：评论

学校读者我要写书评

暂无评论

Solving traveling salesman problems by genetic algorithms

引用

自然科学进展（英文版） 2003年第2期13卷 135-141页

作者： LIANG Yanchun GE Hongwei Zhou Chunguang LEE Heow Pueh LIN Wuzhong LIM Siak Piang LEE Kwok Hong College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Institute of High Performance Computing Singapore 117528 Singapore College of Mathematics Science Jilin University Changchun 130012 China College of Computer Science and Technology Jilin University Changchun 130012 China Institute of High Performance Computing Singapore 117528 Singapore Department of Mechanical Engineering National University of Singapore Singapore 119260 Singapore

The gene section ordering on solving traveling salesman problems is analyzed by numerical experiments. Some improved crossover operations are presented. Several combinations of genetic operations are examined and the functions of these operations are analyzed. The essentiality of the ordering of the gene section and the significance of the evolutionary inversion operation are discussed. Some results and conclusions are obtained and given, which provide useful information for the implementation of the genetic operations for solving the traveling salesman problem.

关键词： genetic algorithms traveling salesman problem gene section evolutionary inversion genetic operations

来源：评论

学校读者我要写书评

暂无评论

A teamwork protocol for multi-agent system 6

引用

6th Pacific Rim International Workshop on Multi-Agents, PRIMA 2003

作者： Sheng, Qiu-Jian Zhao, Zhi-Kun Liu, Shao-Hui Shi, Zhong-Zhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704-28 Beijing 100080 China Graduate School of the Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783540204602

Teamwork is an effective way of cooperative problem solving in dynamic and unpredictable application contexts. The concept of joint intention is the key of teamwork. How various speech acts can be used to form, maintain and dissolve the joint intention is a significant problem need to be investigated. The paper makes an in-depth analysis of the insufficiency of FIPA ACL with which agents to form the required joint intention in teamwork. We distinguish joint-request between delegation-request and extend the FIPA ACL by defining a new joint-request act whose properties are discussed. Based on the defined joint-request, we propose a teamwork protocol, associated with its formal semantic description and demonstrate its application as well. The teamwork protocol presents an interaction pattern that differs from those of existing elementary request protocol, contract-net protocol and auction protocols within FIPA Interaction Protocol Specifications. The proposed protocol can facilitate design of interaction modules in multi-agent teamwork.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Grunt: a semantic indexing system based on concept space

Grunt: a semantic indexing system based on concept space

引用

IEEE International Conference on Natural Language processing and Knowledge Engineering (NLP-KE)

作者： Qing He Ziyan Jia Jiayou Li Haijun Zhang Qingyong Li Zhongzhi Shi Institute of Computing Technology Key Laboratory of Intelligent Information Processing Chinese Academy and Sciences Beijing China

ISBN: (纸本)0780379020

How to get text information from this huge information space becomes a more important problem with the rapid growth of the Internet. A semantic indexing system GHUNT based on concept space is proposed to solve the problem. Some new technologies are integrated in GHUNT to obtain good performance. GHUNT is an all-sided solution for information retrieval on the Internet.

关键词： Indexing Space technology Frequency Information retrieval Internet Databases Helium Laboratories Information processing Computers

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：