检索结果-内蒙古大学图书馆

IASTED International Conference on Artificial Intelligence and Applications, AIA 2007

作者： Kamimura, Ryotaro Yoshida, Fumihiko Kitajima, Ryozo Information Science Laboratory Information Technology Center Tokai University 1117 Kitakaname Hiratsuka Kanagawa 259-1292 Japan Department of Media Studies Tokai University 1117 Kitakaname Hiratsuka Kanagawa 259-1292 Japan Graduate Program in Computer Sciences Tokai University 1117 Kitakaname Hiratsuka Kanagawa 259-1292 Japan

ISBN: (纸本)9780889866317

In this paper, we try to estimate Japan's cabinet approval ratings by using neural networks. In addition, we try to extract the important features in input patterns. This is the first attempt to use neural networks and to interpret the mechanism of inference for approval estimation in a comprehensive way. Experimental results show that neural networks have much better performance than that obtained by the standard regression analysis in terms of training and testing errors. The information loss analysis reveals that the first variable, that is, the previous ratings should play the most important role in inference. Though the experimental result here shown is a preliminary one, it certainly suggests a possibility of the automatic inference of cabinet approval ratings.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Evolving hypernetwork classifiers for microRNA expression profile analysis

Evolving hypernetwork classifiers for microRNA expression pr...

引用

Congress on Evolutionary Computation

作者： Sun Kim Soo-Jin Kim Byoung-Tak Zhang The Center for Bioinformatics Technology Graduate Program in Bioinformatics Seoul National University Seoul South Korea The School of Computer Science and Engineering Seoul National University Seoul South Korea

High-throughput microarrays inform us on different outlooks of the molecular mechanisms underlying the function of cells and organisms. While computational analysis for the microarrays show good performance, it is still difficult to infer modules of multiple co-regulated genes. Here, we present a novel classification method to identify the gene modules associated with cancers from microarray data. The proposed approach is based on 'hypernetworks', a hypergraph model consisting of vertices and weighted hyperedges. The hypernetwork model is inspired by biological networks and its learning process is suitable for identifying interacting gene modules. Applied to the analysis of microRNA (miRNA) expression profiles on multiple human cancers, the hypernetwork classifiers identified cancer-related miRNA modules. The results show that our method performs better than decision trees and naive Bayes. The biological meaning of the discovered miRNA modules has been examined by literature search.

关键词： Cancer Gene expression Biological system modeling Data analysis Support vector machines Support vector machine classification Evolutionary computation Humans Decision trees Diseases

来源：评论

学校读者我要写书评

暂无评论

Information-Theoretic Variable Selection in Neural Networks

Information-Theoretic Variable Selection in Neural Networks

引用

IEEE Symposium on Foundations of Computational Intelligence, FOCI

作者： Ryotaro Kamimura Fumihiko Yoshida Yamashita Toshie Ryozo Kitajima Information Technology Center Information Science Laboratory Japan Department of Media Studies Tokai University Hiratsuka Kanagawa Japan Graduate Program in Computer Sciences Tokai University Hiratsuka Kanagawa Japan

In this paper, we propose a new type of information-theoretic approach to variable selection. Many approaches have been proposed in estimating the importance of input variables. The majority of these approaches have focused upon output errors. We here introduce an approach concerning internal representations. First, we delete an input unit with corresponding connection weights. Then, by examining some change in hidden unit activation with and without a input variable, we can extract an important variable. We apply this method to an artificial data in which the number of hidden units is redundantly increased so as to clearly show improved performance and the stability of our method. Then, we apply the method to the cabinet approval ratings in which better interpretation of input variables can be given

关键词： Input variables Neural networks Computational intelligence computer networks Information theory Data mining Standards development Measurement units Information science Laboratories

来源：评论

学校读者我要写书评

暂无评论

Order-computable sets

引用

Notre Dame Journal of Formal Logic 2007年第3期48卷 317-347页

作者： Hirschfeldt, Denis Miller, Russell Podzorov, Sergei Department of Mathematics University of Chicago Chicago IL 60637 5734 S University Ave United States Department of Mathematics Queens College-CUNY Flushing NY 11367 65-30 Kissena Blvd United States Ph.D. Program in Computer Science Graduate Center of CUNY New York NY 10016 365 Fifth Avenue United States Department of Mechanics and Mathematics Novosibirsk State University Novosibirsk 630090 Pirogova St 2 Russian Federation

We give a straightforward computable-model-theoretic definition of a property of Δ02 sets called order-computability. We then prove various results about these sets which suggest that, simple though the definition is... 详细信息

We give a straightforward computable-model-theoretic definition of a property of Δ⁰2 sets called order-computability. We then prove various results about these sets which suggest that, simple though the definition is, the property defies any easy characterization in pure computability theory. The most striking example is the construction of two computably isomorphic ce. sets, one of which is order-computable and the other not. © 2007 University of Notre Dame.

关键词： Computable model theory Limitwise-monotonic functions Order-computability

来源：评论

学校读者我要写书评

暂无评论

The generation challenge programme platform: Semantic standards and workbench for crop science

引用

International Journal of Plant Genomics 2008年第unknown期2008卷 369601页

作者： Bruskiewich, Richard Senger, Martin Davenport, Guy Ruiz, Manuel Rouard, Mathieu Hazekamp, Tom Takeya, Masaru Doi, Koji Satoh, Kouji Costa, Marcos Simon, Reinhard Balaji, Jayashree Akintunde, Akinnola Mauleon, Ramil Wanchana, Samart Shah, Trushar Anacleto, Mylah Portugal, Arllet Ulat, Victor Jun Thongjuea, Supat Braak, Kyle Ritter, Sebastian Dereeper, Alexis Skofic, Milko Rojas, Edwin Martins, Natalia Pappas, Georgios Alamban, Ryan Almodiel, Roque Barboza, Lord Hendrix Detras, Jeffrey Manansala, Kevin Mendoza, Michael Jonathan Morales, Jeffrey Peralta, Barry Valerio, Rowena Zhang, Yi Gregorio, Sergio Hermocilla, Joseph Echavez, Michael Yap, Jan Michael Farmer, Andrew Schiltz, Gary Lee, Jennifer Casstevens, Terry Jaiswal, Pankaj Meintjes, Ayton Wilkinson, Mark Good, Benjamin Wagner, James Morris, Jane Marshall, David Collins, Anthony Kikuchi, Shoshi Metz, Thomas McLaren, Graham Van Hintum, Theo Crop Research Informatics Laboratory International Rice Research Institute (IRRI) DAPO Box 7777 Metro Manila Philippines Crop Research Informatics Laboratory International Maize and Wheat Improvement Center (CIMMYT) DF 06600 Mexico Apdo. Postal 6-641 Mexico Centre International de Recherche Agronomique Pour le Développement (CIRAD) 34398 Montpellier Cedex 5 Avenue Agropolis France Bioversity International 00057 Maccarese (Fiumicino) Rome Via dei Tre Denari 472/a Italy National Institute for Agrobiological Sciences (NIAS) Tsukuba Ibaraki 305-8602 Kannondai 2-1-2 Japan Empresa Brasileira de Pesquisa Agropecuaria (EMBRAPA) Brasilia DF 70770-900 Parque Estaçao Biologia Final W5 Norte Brazil Centro Internacional de la Papa (CIP) Lima 12 Avenida La Molina 1895 La Molina Peru International Crops Research Institute for the Semi-Arid Tropics Patancheru Andhra Pradesh 502324 India International Center for Agricultural Research in the Dry Areas Aleppo P.O. Box 5466 Syrian Arab Republic National Center for Genetic Engineering and Biotechnology 113 Thailand Science Park Klong Luang Pathumthani 12120 Phahonyothin Road Klong 1 Thailand Institute of Computer Science College of Arts and Sciences University of the Philippines Los Banos Laguna 4031 Philippines Department of Computer Science University of the Philippines Melchor Hall Diliman Quezon City 1101 Philippines National Center for Genome Resources Santa Fe NM 87505 2935 Rodeo Park Drive East United States Scottish Crop Research Institute Invergowrie Dundee DD2 5DA United Kingdom Department of Plant Breeding Cornell University Ithaca NY 14853 United States African Centre for Gene Technologies Lynnwood Ridge 0040 P.O. Box 75011 South Africa Department of Medical Genetics Faculty of Medicine University of British Columbia Vancouver BC V6T 1Z3 Canada School of Computing Science Simon Fraser Universtiy Burnaby BC V5A 1S6 8888 University Drive Canada Bioinformatics Graduate Program Genome Sciences Centre BC

The Generation Challenge programme (GCP) is a global crop research consortium directed toward crop improvement through the application of comparative biology and genetic resources characterization to plant breeding. A key consortium research activity is the development of a GCP crop bioinformatics platform to support GCP research. This platform includes the following: (i) shared, public platform-independent domain models, ontology, and data formats to enable interoperability of data and analysis flows within the platform;(ii) web service and registry technologies to identify, share, and integrate information across diverse, globally dispersed data sources, as well as to access high-performance computational (HPC) facilities for computationally intensive, high-throughput analyses of project data;(iii) platform-specific middleware reference implementations of the domain model integrating a suite of public (largely open-access/-source) databases and software tools into a workbench to facilitate biodiversity analysis, comparative analysis of crop genomic data, and plant breeding decision making.

关键词： GENOMICS GERMPLASM resources PLANT breeding PLANT genetics computerS in biology BIOINFORMATICS -- Software

来源：评论

学校读者我要写书评

暂无评论

Computational Techniques for Accompaniment and Measuring of Otology Pathologies

Computational Techniques for Accompaniment and Measuring of ...

引用

Annual IEEE Symposium on computer-Based Medical Systems

作者： V. Heck A.v. Wangenheim D.D. Abdala E. Comunello S.S. Costa C.C. Dornelles Computer Science and Statistics Department Universidade Federal de Santa Catarina Florianópolis Santa Catarina Brazil Cyclops Group – Laboratory of Image Processing and Virtual Reality Universidade Federal de Santa Catarina Florianópolis Santa Catarina Brazil Graduate Program in Applied Computer Science Universidade do Vale do Itajaí Florianópolis Santa Catarina Brazil Otitis Media Center of Brazil Universidade Federal do Rio Grande do Sul - Medical School Porto Alegre Rio Grande do Sul Brazil

The following article presents a computational methodology to assist the assessment of tympanic pathologies, particularly chronic otitis media, based on digital otoscopic images. A computational system which implements the methodology is described. This approach does not impose additional effort to the acquisition protocol and diagnosis of tympanic pathologies. In preliminary tests, it has shown precision and easiness of use. The presented methodology and system were tested by the Otitis Media center of Brazil (***) with a case base of 660 patients, resulting in 1320 bilateral tympanic images.

关键词： Pathology Laboratories Image processing Virtual reality computer science Statistics Biomedical imaging Medical diagnostic imaging Area measurement Protocols

来源：评论

学校读者我要写书评

暂无评论

Decision Fusion of Circulating Markers for Breast Cancer Detection in Premenopausal Women

Decision Fusion of Circulating Markers for Breast Cancer Det...

引用

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： Jonathan L. Jesneck Sayan Mukherjee Loren W. Nolte Anna E. Lokshin Jeffrey R. Marks Joseph Lo Duke Advanced Imaging Labs Institute for Genome Sciences and Policy Department of Computer Science Duke University USA Department of Electrical and Computer Engineering Division of Hematology/Oncology University of Pittsburgh School of Medicine Pittsburgh PA USA Division of Hematology/Oncology University of Pittsburgh Cancer Institute Pittsburgh PA USA Division of Hematology/Oncology University of Pittsburgh Cancer Institute Pittsburgh PA Institute for Genome Sciences and Policy Department of Experimental Surgery Medical Center Duke University USA Department of Experimental Surgery Duke University Medical Center Medical Physics Graduate Program Duke University Durham NC USA

Current mammographic screening for breast cancer is less effective for younger women. To complement mammography for premenopausal women, we investigated the feasibility screening test using 98 blood serum proteins. Because the data set was very noisy and contained only weak features, we used a classifier designed for noisy data: decision fusion. Decision fusion outperformed both a support vector machine (SVM) and linear regression with forward stepwise feature selection on all three two-class classification tasks: normal tissue vs. cancer, normal tissue vs. benign lesions, and benign lesions vs. cancer. Decision fusion detected cancer moderately well (AUC=0.84 on normal vs. cancer), demonstrating promise as a screening tool. Decision fusion also detected benign lesions similarly well (AUC=0.83 on normal vs. benign lesions) and was the only classifier to achieve any success in separating benign from malignant lesions (AUC=0.64 on benign vs. cancer). The classification results suggest that the assayed proteins are more indicative of a secondary effect, such as immune response, rather than specific for breast cancer. In conclusion, the decision fusion classifier demonstrated some promise in detecting breast lesions and outperformed other classifiers, especially for the very noisy classification problem of distinguishing benign from malignant lesions.

关键词： Breast cancer Cancer detection Lesions Proteins Support vector machines Support vector machine classification Mammography Testing Blood Linear regression

来源：评论

学校读者我要写书评

暂无评论

Waters network's potential to transform environmental engineering education

Waters network's potential to transform environmental engine...

引用

114th Annual ASEE Conference and Exposition, 2007

作者： Eschenbach, Elizabeth Montgomery, Jami Johnson, James Brus, Chris Carlson, Patricia Giammar, Dan Grauer, Bette Hotaling, Liesl Oguntimein, Gbekeloluwa Safferman, Steven Wentling, Tim Humboldt State University United States Department of Environmental Resources Engineering Humboldt State University United States WATERS Network - CLEANER Project Office Network Howard University United States Department of Environmental Engineering College of Engineering Architecture and Computer Sciences Howard University United States American Academy of Environmental Engineers United States University of Iowa United States Program University of Iowa United States Rose-Hulman Institute of Technology United States Department of Rhetoric Rose-Hulman Institute of Technology United States National Research Council U. S. Air Force United States NASA's Classroom of the Future Wheeling WV United States Washington University United States Department of Energy Environmental and Chemical Engineering Washington University St. Louis United States Environmental Studies Program Center for Materials Innovation United States McPherson High School United States McPherson High School McPherson KS United States Stevens Institute of Technology United States Stevens Institute of Technology United States Morgan State University United States Michigan State University United States Biosystems and Agricultural Engineering Department Michigan State University United States University of Dayton United States Education Planning Committee National Center for Supercomputing Applications United States Department of Information Science Graduate School of Library and Information Science National Center for Supercomputing Applications University or Illinois United States Knowledge and Learning Systems Group NCSA United States

The WATERS Network (WATer and Environmental Research Systems Network) will be an integrated real-time distributed observing system which will enable academic and government scientists, engineers, educators, and practitioners to advance effective management of our nation's water resources by understanding human interactions with water and the natural and built environment. WATERS will provide easily accessible real time environmental data as well as analysis tools to engineers, scientists, educators, K- graduate students and policymakers so they can better understand how water quantity, quality and related components of the hydrologic cycle are impacted by natural and human influences. The WATERS strategic plan will be completed by July 2007 and requires constituent input. This paper describes the draft Conceptual Design and the Education Plan of WATERS Network. This paper will highlight the potential impact of WATERS on undergraduate and graduate environmental engineering education in order to elicit input from the environmental engineering education community on how WATERS Network could better meet the future needs of undergraduate and graduate students and educators. More information can be found at ***. © American Society for Engineering Education, 2007.

关键词： Water resources

来源：评论

学校读者我要写书评

暂无评论

Detecting low complexity clusters by skewness and kurtosis in data stream clustering

Detecting low complexity clusters by skewness and kurtosis i...

引用

9th International Symposium on Artificial Intelligence and Mathematics, ISAIM 2006

作者： Song, Mingzhou Wang, Hongbin Department of Computer Science New Mexico State University MSC CS P.O. Box 30001 Las Cruces NM 88003 United States Ph.D. Program in Computer Science Graduate Center City University of New York New York NY 10016 United States

Established statistical representations of data clusters employ up to second order statistics including mean, variance, and covariance. Strategies for merging clusters have been largely based on intra-and inter-cluster distance measures. The distance concept allows an intuitive interpretation, but it is not designed to merge from the viewpoint of probability distributions. We suggest an alternative strategy to compare clusters based on higher order statistics to capture the underlying probability distributions. Higher order statistics, such as multivariate skewness and kurtosis, enable a more accurate description of the shape of a cluster. Although the original definitions of kurtosis and skewness do require simultaneous involvement of all data points, our finding shows that their estimation can be decomposed into combinations of the cross moments of subsets of data. This decomposable property makes it possible to apply skewness and kurtosis to data stream clustering, where historical data are not accessible. We utilize tests for normality based on skewness and kurtosis to discover cluster pairs that can be merged to produce a less complex normal cluster even if they have different means or covariance structures.

关键词： Higher order statistics

来源：评论

学校读者我要写书评

暂无评论

An information theoretic framework for eukaryotic gradient sensing 06

An information theoretic framework for eukaryotic gradient s...

引用

Proceedings of the 20th International Conference on Neural Information Processing Systems

作者： Joseph M. Kimmel Richard M. Salter Peter J. Thomas Computer Science Program Oberlin College Oberlin Ohio and Computational Neuroscience Graduate Program The University of Chicago Computer Science Program Oberlin College Oberlin Ohio and Oberlin Center for Computation and Modeling Departments of Mathematics Biology and Cognitive Science Case Western Reserve University Cleveland Ohio and Oberlin College Research Associate

Chemical reaction networks by which individual cells gather and process information about their chemical environments have been dubbed "signal transduction" networks. Despite this suggestive terminology, there have been few attempts to analyze chemical signaling systems with the quantitative tools of information theory. Gradient sensing in the social amoeba Dictyostelium discoideum is a well characterized signal transduction system in which a cell estimates the direction of a source of diffusing chemoattractant molecules based on the spatiotemporal sequence of ligand-receptor binding events at the cell membrane. Using Monte Carlo techniques (MCell) we construct a simulation in which a collection of individual ligand particles undergoing Brownian diffusion in a three-dimensional volume interact with receptors on the surface of a static amoeboid cell. Adapting a method for estimation of spike train entropies described by Victor (originally due to Kozachenko and Leonenko), we estimate lower bounds on the mutual information between the transmitted signal (direction of ligand source) and the received signal (spatiotemporal pattern of receptor binding/unbinding events). Hence we provide a quantitative framework for addressing the question: how much could the cell know, and when could it know it? We show that the time course of the mutual information between the cell's surface receptors and the (unknown) gradient direction is consistent with experimentally measured cellular response times. We find that the acquisition of directional information depends strongly on the time constant at which the intracellular response is filtered.

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：