检索结果-内蒙古大学图书馆

5th IEEE International Symposium on Multimedia Software engineering, ISMSE 2003

作者： Shyu, M.-L. Chen, S.-C. Chen, M. Zhang, C. Shu, Chi-Min Department of Electrical and Computer Engineering University of Miami Coral GablesFL33124 United States Distributed Multimedia Information System Laboratory School of Computer Science Florida International University MiamiFL33199 United States Department of Environmental and Safety Engineering National Yunlin University of Science and Technology Yunlin Taiwan

ISBN: (纸本)0769520316

We present a mechanism called the Markov model mediator (MMM) to facilitate the effective retrieval for content-based image retrieval (CBIR). Different from the common methods in content-based image retrieval, our stochastic mechanism not only takes into consideration the low-level image content features, but also learns high-level concepts from a set of training data, such as access frequencies and access patterns of the images. The advantage of our proposed mechanism is that it exploits the structured description of visual contents as well as the relative affinity measurements among the images. Consequently, it provides the capability to bridge the gap between the low-level features and high-level concepts. Our experimental results demonstrate that the MMM mechanism can effectively assist in retrieving more accurate results for user queries. © 2003 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic scheduling issues in SMT architectures

Dynamic scheduling issues in SMT architectures

引用

International Parallel and Distributed Processing Symposium, IPDPS 2003

作者： Shin, Chulho Lee, Seong-Won Gaudiot, Jean-Luc System Design Technology Laboratory Samsung Electronics Corporation Korea Republic of Dept. of Electrical Engineering - Systems University of Southern California United States Dept. of Electrical Engineering and Computer Science University of California Irvine United States

ISBN: (纸本)0769519261

Simultaneous multithreading (SMT) attempts to attain higher processor utilization by allowing instructions from multiple independent threads to coexist in a processor and compete for shared resources. Previous studies have shown, however, that its throughput may be limited by the number of threads. A reason is that a fixed thread scheduling policy cannot be optimal for the varying mixes of threads it may face in an SMT processor. Our adaptive dynamic thread scheduling (ADTS) was previously proposed to achieve higher utilization by allowing a detector thread to make use of wasted pipeline slots with nominal hardware and software costs. The detector thread adaptively switches between various fetch policies. Our previous study showed that a single fixed thread scheduling policy presents much room (some 30%) for improvement compared to an oracle-scheduled case. In this paper, we take a closer look at ADTS. We implemented the functional model of the ADTS and its software architecture to evaluate various heuristics for determining a better fetch policy for a next scheduling quantum. We report that performance could be improved by as much as 25%. © 2003 IEEE.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Mining high-level user concepts with multiple instance learning and relevance feedback for content-based image retrieval

Mining high-level user concepts with multiple instance learn...

引用

International Workshop on Mining Complex Data: Multimedia Data Mining, MDM/KDD at KDD 2002 and International Workshop on Knowledge Discovery from Multimedia and Complex Data, KDMCD at PAKDD 2002

作者： Huang, Xin Chen, Shu-Ching Shyu, Mei-Ling Zhang, Chengcui Distributed Multimedia Information System Laboratory School of Computer Science Florida International University MiamiFL33199 United States Department of Electrical and Computer Engineering University of Miami Coral GablesFL33124 United States

ISBN: (纸本)3540203052

Understanding and learning the subjective aspect of humans in Content-Based Image Retrieval has been an active research field during the past few years. However, how to effectively discover users’ concept patterns when there are multiple visual features existing in the retrieval system still remains a big issue. In this book chapter, we propose a multimedia data mining framework that incorporates Multiple Instance Learning into the user relevance feedback in a seamless way to discover the concept patterns of users, especially where the user’s most interested region and how to map the local feature vector of that region to the high-level concept pattern of users. This underlying mapping can be progressively discovered through the feedback and learning procedure. The role the user plays in the retrieval system is to guide the system mining process to his/her own focus of attention. The retrieval performance is tested to show the feasibility and effectiveness of the proposed multimedia data mining framework. © Springer-Verlag Berlin Heidelberg 2003.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Adaptive background learning for vehicle detection and spatio temporal tracking 4

Adaptive background learning for vehicle detection and spati...

引用

Joint Conference of the 4th International Conference on Information, Communications and Signal Processing and 4th Pacific-Rim Conference on Multimedia, ICICS-PCM 2003

作者： Zhang, Chengcui Chen, Shu-Ching Shyu, Mei-Ling Peeta, Srinivas Distributed Multimedia Information System Laboratory School of Computer Science Florida International University MiamiFL33199 United States Department of Electrical and Computer Engineering University of Miami Coral GablesFL33124 United States School of Civil Engineering Purdue University West LafayetteIN47907 United States

ISBN: (纸本)0780381858

Traffic video analysis can provide a wide range of useful information such as vehicle identification, traffic flow, to traffic planners. In this paper, a framework is proposed to analyze the traffic video sequence using unsupervised vehicle detection and spatio-temporal tracking that includes an image/video segmentation method, a background learning/subtraction method and an object tracking algorithm. A real-life traffic video sequence from a road intersection is used in our study and the experimental results show that our proposed unsupervised framework is effective in vehicle tracking for complex traffic situations. © 2003 IEEE.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

An Automated Method for Neuronal Spike Source Identification

An Automated Method for Neuronal Spike Source Identification

引用

International Joint Conference on Neural Networks 2003

作者： Santiago, Roberto A. McNames, James Burchiel, Kim Lendaris, George G. NW Compl. Intelligence Laboratory System Science Portland State University Portland OR United States Biomed. Signal Processing Laboratory Electrical and Computer Engineering Portland State University Portland OR United States Department of Neurological Surgery Oregon Health Sciences University Portland OR United States

Analysis of microelectrode recordings (MER) of extracellular neuronal activity has gained increasing interest due to potential improvements to surgical techniques involving ablation or placement of deep brain stimulators, as is common in the treatment of Parkinson's disease. Critical to these procedures is the identification of different brain structures such as the globus pallidus internus (GPI). Evidence suggests that the spike trains from individual neurons contain enough information to identify the brain structure in which they are located. For the work reported here, spike train data gathered during surgical procedure from multiple patients is used. Using a moving window sampling approach, a novel feature extraction method for spike trains was developed. This method is then used in combination with a support vector classification algorithm. Results strongly indicate that the sampling methods reported here are able to extract the necessary information for highly accurate spike source identification.

关键词： Neurosurgery

来源：评论

学校读者我要写书评

暂无评论

A journey trough clinical applications of multimethod decision trees

引用

9th Conference on Artificial Intelligence on in Medicine in Europe, AIME 2003

作者： Povalej, Petra Lenič, Mitja Štiglic, Milojka Molan Kavalar, Maja Skerbinjek Završnik, Jernej Kokol, Peter Laboratory for System Design Faculty of Electrical Engineering and Computer Science University of Maribor SI-2000 Maribor Slovenia Adolf Drolc Health Centre SI-2000 Maribor Slovenia Department of Paediatric Surgery Maribor Teaching Hospital SI-2000 Maribor Slovenia

ISBN: (纸本)3540201297

We present a journey through successful applications of multimethod approach to induction of decision trees in knowledge extraction, discovery of new knowledge and early diagnosis on the cases of asthma, cardiovascular problems and mitral valve prolapse. The results show that the multimethod approach is a powerful and promising technique enabling the conformation of existing medical knowledge and more interestingly, also enables the induction of new facts and hypothesis, which can reveal some new interesting patterns and possibly improve the existing medical knowledge. © Springer-Verlag Berlin Heidelberg 2003.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

An automated method for neuronal spike source identification

An automated method for neuronal spike source identification

引用

International Joint Conference on Neural Networks (IJCNN)

作者： R.A. Santiago J. McNames K. Burchiei G.G. Lendaris NW Computational Intelligence Laboratory System Science Portland State University USA NW Computational Intelligence Laboratory System Science Portland State Universityt Biomedical Signal Processing Laboratory Electrical & Computer Engineering Portland State University USA

Analysis of microelectrode recordings (MER) of extracellular neuronal activity has gained increasing interest due to potential improvements to surgical techniques involving ablation or placement of deep brain stimulators, as is common in the treatment of Parkinson's disease. Critical to these procedures is the identification of different brain structures such as the globus pallidus internus (GPI). Evidence suggests that the spike trains from individual neurons contain enough information to identify the brain structure in which they are located For the work reported here, spike train data gathered during surgical procedure from multiple patients is used. Using a moving window sampling approach, a novel feature extraction method for spike trains was developed. This method is then used in combination with a support vector classification algorithm. Results strongly indicate that the sampling methods reported here are able to extract the necessary information for highly accurate spike source identification.

关键词： Surgery Brain Sampling methods Microelectrodes Extracellular Parkinson's disease Neurons Feature extraction Classification algorithms Data mining

来源：评论

学校读者我要写书评

暂无评论

Research of Extracting Data from HTML Web Pages Automatically

引用

Journal of Beijing Institute of Technology 2003年第S1期12卷 104-108页

作者：王茹宋瀚涛陆玉昌 Department of Computer Science and Engineering School of Information Science and TechnologyBeijing Institute of TechnologyBeijing 100081China State Key Laboratory of Intelligent Technology and System Tsinghua UniversityBeijing 100084China

In order to use data information in the Internet, it is necessary to extract data from web pages. An HTT tree model representing HTML pages is presented. Based on the HTT model, a wrapper generation algorithm AGW is proposed. The AGW algorithm utilizes comparing and correcting technique to generate the wrapper with the native characteristic of the HTT tree structure. The AGW algorithm can not only generate the wrapper automatically, but also rebuild the data schema easily and reduce the complexity of the computing.

关键词： information extraction data transformation wrapper HTML page

来源：评论

学校读者我要写书评

暂无评论

Integration of trusted operating system from open source

Integration of trusted operating system from open source

引用

International Carnahan Conference on Security Technology

作者： Yung-Feng Lu Chin-Fu Kuo Chung-Hsin Chen Institute for Information Industry Information System Laboratory Taipei Taiwan Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Department of Computer Science National Chengchi University Taipei Taiwan

ISBN: (纸本)0780378822

An operating system (OS) can be viewed as the collection progress of required directives before a computer system can run. Thus, OS is the most important software in any computer system. If OS is risky, then the computer system could be in danger. So, information security has become a critical issue for computer systems, it is necessary to develop a trusted operating system. As the result, in order to improve system security, there are many enhancements, which are developed. Some of them are open source. We can integrate appropriate software to construct a trusted system. The paper first gives a discussion covered the current security problems and the difficulty in solving those problems. Then, we study security function requirements from "protection profile for multilevel operating systems in environments requiring medium robustness", to find important secure features. Next, we demonstrate important security enhancement projects of OS with these corresponding security features. Finally, we give an idea about how to combine some of well-done open source secure software, and satisfy the secure features.

关键词： Operating systems Information security National security Laboratories Protection computer security Access control Kernel Data security Power system security

来源：评论

学校读者我要写书评

暂无评论

Intelligent data analysis of human bone density

Intelligent data analysis of human bone density

引用

Annual IEEE Symposium on computer-Based Medical systems

作者： P. Povalej M. Lenic M. Zorman P. Kokol M.G.E. Peterson J.M. Lane Laboratory for System Design Faculty of Electrical Engineering and Computer Science University of Maribor Maribor Slovenia Hospital for Special Surgery New York NY USA

In this paper we present the results of an intelligent analysis of osteoporosis database gathered during a longitudinal study in which a random sample of 100 women who had passed precautionary examinations for detection of osteoporosis over five years and were not referred for a definite medical diagnosis was pulled from the records. The intelligent data analysis using advanced methods for decision tree construction was used in order to try to find the main factors that can reduce the risk for development of osteoporosis in women. Most of the extracted knowledge confirmed known medical criteria that put women to risk for osteoporosis, however some new interesting patterns have also been shown.

关键词： Data analysis Humans Osteoporosis Medical diagnostic imaging Bones Decision trees Minerals Databases Medical diagnosis Decision making

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：