检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Dong Wang Dayong Ding Le Chen Shen Zhang Fuzong Lin Bo Zhang State Key Laboratory of Intelligent Technology & System Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)0780388747

Two open problems remain unsolved in the content based video retrieval area. Firstly, how to find useful information and express it by different features. Secondly, how to fuse the heterogeneous information together to boost the retrieval performance beyond any single component. The paper presents two kinds of timing information and their use in concept detection in news video, and a novel non-linear information fusion method to combine timing cues with other information from different sources. Experiments on the TRECVID 2004 dataset show that timing cues can boost performance when combined with other information.

关键词： Timing Content based retrieval Fuses Information retrieval Data mining Laboratories Computer science Image retrieval Shape Spatial databases

来源：评论

学校读者我要写书评

暂无评论

A new algorithm for pattern optimization in protein-protein interaction extraction system

A new algorithm for pattern optimization in protein-protein ...

引用

Second Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2005

作者： Hao, Yu Zhu, Xiaoyan Li, Ming State Key Laboratory of Intelligent Technology and System Department of Computer Science and Technology Tsinghua University Beijing China School of Computer Science University of Waterloo Waterloo Ont. N2L 3G1 Canada

In pattern matching based Protein-Protein Interaction Extraction systems, patterns generated manually or automatically exist erroneous and redundancy, which greatly affect the system's performance. In this paper, a MDL-based pattern optimizing algorithm is proposed to filter out the bad patterns and redundancy. Experiments show that our algorithm is effective in improving the system's performance while greatly cutting down the number of patterns. It also has excellent generalizability which is important in implementing practical systems. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Improved validation index for fuzzy clustering

Improved validation index for fuzzy clustering

引用

American Control Conference (ACC)

作者： Yuangang Tang Fuchun Sun Zengqi Sun Department of Computer Science and Technology State Key Laboratory of Intelligent Technology and System Tsinghua University Beijing Beijing China

ISBN: (纸本)0780390989

This paper proposes a new validation index for fuzzy clustering in order to eliminate the monotonically decreasing tendency as the number of clusters approaches to the number of data points and avoid the numerical instability of validation index when fuzzy weighting exponent increases. Limit analyses of Xie-Beni index, Kwon index and the proposed index are also considered for the convenience of contrast. Lastly, two numerical examples are presented to show the effectiveness of the proposed validation index.

关键词： Clustering algorithms Partitioning algorithms Image analysis Pattern analysis Pattern recognition Image processing Medical diagnosis Clustering methods Entropy Computer science

来源：评论

学校读者我要写书评

暂无评论

The influence of dynamic trans-tibial prosthetic alignment on standing plantar foot pressure

The influence of dynamic trans-tibial prosthetic alignment o...

引用

2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005

作者： Jia, Xiaohong Li, Xiaobing Dou, Peng Zhang, Ming Division of Intelligent and Biomechanical System State Key Laboratory of Tribology Tsinghua University Beijing 100084 China Department of Precision Instruments Tsinghua University China Jockey Club Rehabilitation Engineering Center Hong Kong Polytechnic University Hong Kong Hong Kong

ISBN: (纸本)0780387406

In order to study quantitative effect of dynamic prosthetic alignment on standing biomechanical property for trans-tibial amputees, plantar foot pressure of one subject during natural standing were recorded by using the Pedar in-shoe pressure measurement system with different alignment angles in the sagittal and frontal planes. The results showed that angular alignment had significant effects on the foot pressure distribution and magnitude of prosthetic side. Peak pressure on prosthetic foot was 1.96 times larger than the one on sound foot, although only about 38% body weight was supported by prosthetic side on average. Adjustment of alignment angle in sagittal and frontal planes made the center of pressure on foot shift in A/P and M/L directions respectively. The findings provide potentially useful information for prosthesis design and biomechanical analysis of lower limb. © 2005 IEEE.

关键词： Prosthetics

来源：评论

学校读者我要写书评

暂无评论

Extraction of tree height from large viewing angle aerial images

Extraction of tree height from large viewing angle aerial im...

引用

International Conference on Space Information Technology

作者： Li, Chaoyang Yan, Guangjian Liu, Qiang Xiao, Zhiqiang Wang, Jingdi Laboratory of Pattern Recognition and Intelligent System School of Information Engineering Beijing University of Posts and Telecommunications 86-10-58809966 China State Key Laboratory of Remote Sensing Science Beijing Normal University Institute of Remote Sensing Applications Research Center for Remote Sensing School of Geography Beijing Normal University

ISBN: (纸本)0819460079

Due to the complexity and non-regularity of tree shapes, traditional digital photogrammetry using stereo matching method is difficult to obtain the accurate tree height, This fact therefore limits the application of the aerial digital photogrammetry technology in the power line survey. This paper presents a method of tree height extraction from large viewing aerial image using the knowledge of segmented tree crown. This method is based on a rough digital surface model (DSM) of tree crowns and the exterior orientation of the image. The basic steps of this method is that the DSM is first used to find the region of interest in the image based on the exterior orientation, and then the edges of the distinct trees or branches are extracted using image segmentation technology. An algorithm that uses both the rough DSM height information and exterior orientation data to calculate the accurate heights of the segmented trees or branches is presented. The algorithm assumes that most of the trees are upright, and the projection in the large viewing angle images of the crown and branches can therefore be used to calculate their heights relative to the averaged DSM height. Hence, the accurate height of the trees around the rough DSM can be refined. Some experimental results are given with the image captured from multi-angular imaging system mounted on a helicopter in which a Position and Orientation system (POS) is onboard to record the exterior element of the cameras. The experimental results demonstrated that this algorithm can largely improve the accuracy of tree height extraction. The application in power line monitoring system is promising.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Improved vicinal SV algorithm

引用

Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology 2005年第11期25卷 967-970页

作者： Bi, Le-Peng Zheng, Zhi-Yun Song, Han-Tao Lu, Yu-Chang Department of Computer Science and Engineering School of Information Science and Technology Beijing Institute of Technology Beijing 100081 China State Key Laboratory of Intelligent Technology and System Tsinghua University Beijing 100084 China

Two improvements are introduced into vicinal-risk-minimization based support vector (SV) algorithm. Since the misclassified samples must be support vectors, a scheme for pruning hard-to-learn samples from the training set based on support vectors is presented. The parameter's determination of Gaussian vicinal function is proposed to be modified, based on the maximum likelihood criterion. Preliminary experimental results show that the pruning scheme and improvement of the parameter's determination of vicinal function much improved vicinal SV algorithm's generality, and can outperform support vector machine (SVM) by about 0.5% in test accuracy.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

REINFORCEMENT LEARNING CONTROL FOR SHIP STEERING USING RECURSIVE LEAST-SQUARES ALGORITHM

引用

IFAC Proceedings Volumes 2005年第1期38卷 133-138页

作者： Zhi-peng Shen Chen Guo Shi-chun Yuan Lab of Simulation and Control of Navigation Systems Dalian Maritime Univ. Dalian 116026 China State Key Laboratory of Intelligent Technology and system Tsinghua University Beijing 100084 China

Recursive least-squares temporal difference algorithm (RLS-TD) is deduced, which can use data more efficiently with fast convergence and less computational burden. Reinforcement learning based on recursive least-squares methods is applied to ship steering control, as provides an efficient way for the improvement of ship steering control performance. It removes the defect that the conventional intelligent algorithm learning must be provided with some sample data. The parameters of controller are on-line learned and adjusted. Simulation results show that the ship course can be properly controlled in case of the disturbances of wave, wind, current. It is demonstrated that the proposed algorithm is a promising alternative to conventional autopilots.

关键词： Recursive squares methods Learning algorithm Action network Ship control Simulation

来源：评论

学校读者我要写书评

暂无评论

Segmentation of connected Chinese characters based on genetic algorithm

Segmentation of connected Chinese characters based on geneti...

引用

International Conference on Document Analysis and Recognition

作者： Xianghui Wei Shaoping Ma Yijiang Jin Institute of Software Chinese Academy and Sciences China State Key Laboratory of Intelligent Technology & System CST Department Tsinghua University Beijing China

The accuracy of segmenting Chinese character, especially connected Chinese characters, is essential for the performance of a Chinese character recognition system. In this paper, a new approach for segmenting connected Chinese characters based on genetic algorithm is proposed. The best segmentation path is evolved by genetic algorithm from a fixed area located in the middle of character image which is defined as segmentation path zone (SPZ). The initial population is composed of each point line in SPZ. The individual coding, fitness function, crossover operator and mutation operator are also defined for this task. Experimental results on a dataset extracted from the four vaults show that our approach can get an average accuracy of 88.9% on test set and can handle some complex types of connected Chinese characters without special heuristic rules.

关键词： Genetic algorithms Image segmentation Character recognition Upper bound Software performance Content addressable storage Genetic mutations Testing Optical character recognition software Skeleton

来源：评论

学校读者我要写书评

暂无评论

Phishing Web page detection

Phishing Web page detection

引用

International Conference on Document Analysis and Recognition

作者： Liu Wenyin Guanglin Huang Liu Xiaoyue Xiaotie Deng Zhang Min Department of Computer Science City University of Hong Kong Hong Kong China State Key Laboratory of Intelligent Technology & System Tsinghua University Beijing China

An approach to detection of phishing Web pages based on visual similarity is proposed, which can be utilized as a part of an enterprise solution to antiphishing. A legitimate Web page owner can use this approach to search the Web for suspicious Web pages which are visually similar to the true Web page. The approach first decomposes the Web pages into salient (visually distinguishable) block regions. The visual similarity between two Web pages is then evaluated in three metrics: block level similarity, layout similarity, and overall style similarity. A Web page is reported as a phishing suspect if any of them (with regards to the true one) is higher than its corresponding preset threshold. Preliminary experiments show that the approach can successfully detect those phishing Web pages with few false alarms at a speed adequate for online application.

关键词： Uniform resource locators Testing Computer science Text analysis Information analysis Information filtering Credit cards Internet Electronic mail Size measurement

来源：评论

学校读者我要写书评

暂无评论

Spectral feature analysis

Spectral feature analysis

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Fei Wang Jingdong Wang Changshui Zhang State Key Laboratory of Intelligent Technology and System Department of Automation Tsinghua University Beijing China Department of Computer Science Hong Kong University of Science and Technology Clear Water Bay Hong Kong China

We have seen a surge of interest in spectral-based methods and kernel-based methods for machine learning and data mining. Despite the significant research, these methods remain only loosely related. In this paper, we give theoretically an explicit relation between spectral clustering and weighted kernel principal component analysis (WKPCA). We show that spectral clustering is not only a method for data clustering, but also for feature extraction. We are then able to reinterpret the spectral clustering algorithm in terms of WKPCA and propose our spectral feature analysis (SFA) method. The spectral features extracted by SFA can capture the distinguishing information of data from different classes effectively. Finally some experimental results are presented to show the effectiveness of our method.

关键词： Spectral analysis Kernel Data mining Feature extraction Electronic mail Principal component analysis Laboratories intelligent systems Automation Machine learning

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：