检索结果-内蒙古大学图书馆

IEEE Symposium on Intelligent Vehicle

作者： R. Kovordanyi K. Ohlsson T. Alm Cognitive technology at the Department of Computer and Information Science Linköping Universitet Sweden Human-machine interaction at the division of Industrial Ergonomics Department of Mechanical Engineering Linköping Universitet Sweden Division of Industriai Ergonomics Department of Mechanical Engineering Linköping Universitet Linkoping Sweden

Advanced driver assistance systems are designed to make driving easier that is, to alleviate the driver's workload, and to increase traffic safety. However, traffic safety is affected by negative behavioral adaptation, meaning that drivers tend to increase speed and pay less attention to driving when supported by an advanced assistance system. We relate behavioral adaptation to reinforcement learning at a subconscious level, and propose that driver assistance is dynamically varied within predetermined safety limits. The aim of employing a dynamic assistance policy is to prevent the driver from noticing a constant improvement in vehicle handling. We conclude by describing ongoing work for empirically evaluating an improved lane departure warning system that uses a dynamic assistance policy.

关键词： Safety Vehicle dynamics Alarm systems Wheels US department of Transportation Learning Vehicle driving Sensor systems Ergonomics Torque

来源：评论

学校读者我要写书评

暂无评论

Graduate education in human-computer interaction

Graduate education in human-computer interaction

引用

Conference on human Factors in Computing Systems, CHI EA 2005

作者： Foley, James Beaudouin-Lafon, Michel Grudin, Jonathan Hollan, James Hudson, Scott Olson, Judy Verplank, Bill Laboratoire de Recherche en Informatique Bât 490 Université Paris Sud 91405 Orsay Cedex France GVU Center and College of Computing Georgia Institute of Technology Atlanta GA 30332-0280 United States Microsoft Research Bellevue WA United States Department of Cognitive Science University of California San Diego CA 92093-0515 United States Human-Computer Interaction Institute Carnegie Mellon University Pittsburgh PA 15213-3891 United States School of Information Univ. of Michigan Ann Arbor MI 48109-1092 United States Visiting Scholar Stanford University Department of Computer Science Stanford CA 94305-9035 United States

来源：评论

学校读者我要写书评

暂无评论

Feature selection for classification of SELDI-TOF-MS proteomic profiles

引用

Applied Bioinformatics 2005年第4期4卷 227-246页

作者： Hauskrecht, Milos Pelikan, Richard Malehorn, David E. Bigbee, William L. Lotze, Michael T. Zeh III, Herbert J. Whitcomb, David C. Lyons-Weiler, James Department of Computer Science University of Pittsburgh Pittsburgh PA United States University of Pittsburgh Cancer Institute University of Pittsburgh Pittsburgh PA United States Clinical Proteomics Facility University of Pittsburgh Pittsburgh PA United States Department of Pathology University of Pittsburgh Pittsburgh PA United States Department of Surgery University of Pittsburgh Pittsburgh PA United States Department of Medicine Cell Biology and Physiology Department of Human Genetics University of Pittsburgh Pittsburgh PA United States Cancer Biomarkers Laboratory University of Pittsburgh Pittsburgh PA United States Centers for Pathology and Oncology Informatics University of Pittsburgh Pittsburgh PA United States Center for Biomedical Informatics University of Pittsburgh Pittsburgh PA United States Department of Computer Science 5329 Sennott Building University of Pittsburgh Pittsburgh PA 15260 United States

Background: Proteomic peptide profiling is an emerging technology harbouring great expectations to enable early detection, enhance diagnosis and more clearly define prognosis of many diseases. Although previous research work has illustrated the ability of proteomic data to discriminate between cases and controls, significantly less attention has been paid to the analysis of feature selection strategies that enable learning of such predictive models. Feature selection, in addition to classification, plays an important role in successful identification of proteomic biomarker panels. Methods: We present a new, efficient, multivariate feature selection strategy that extracts useful feature panels directly from the high-throughput spectra. The strategy takes advantage of the characteristics of surface-enhanced laser desorption/ionisation time-of-flight mass spectrometry (SELDI-TOF-MS) profiles and enhances widely used univariate feature selection strategies with a heuristic based on multivariate de-correlation filtering. We analyse and compare two versions of the method: one in which all feature pairs must adhere to a maximum allowed correlation (MAC) threshold, and another in which the feature panel is built greedily by deciding among best univariate features at different MAC levels. Results: The analysis and comparison of feature selection strategies was carried out experimentally on the pancreatic cancer dataset with 57 cancers and 59 controls from the University of Pittsburgh Cancer Institute, Pittsburgh, Pennsylvania, USA. The analysis was conducted in both the whole-profile and peak-only modes. The results clearly show the benefit of the new strategy over univariate feature selection methods in terms of improved classification performance. Conclusion: Understanding the characteristics of the spectra allows us to better assess the relative importance of potential features in the diagnosis of cancer. Incorporation of these characteristics into feature selection strat

关键词：

来源：评论

学校读者我要写书评

暂无评论

The ISI and the CTW

引用

Cognition, Technology & Work 2005年第1期7卷 1-2页

作者： Hollnagel, Erik Cacciabue, Pietro C. Department of Computer and Information Science Cognitive Systems Engineering Laboratory (CSELAB) University of Linköping Linköping Sweden EC Joint Research Centre Institute for System Informatics and Safety Human Factors Sector Ispra (VA) Italy

来源：评论

学校读者我要写书评

暂无评论

Inverse kinematics learning for robotic arms with fewer degrees of freedom by modular neural network systems

Inverse kinematics learning for robotic arms with fewer degr...

引用

2005 IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： E. Oyama T. Maeda J.Q. Gan E.M. Rosales K.F. MacDorman S. Tachi A. Agah National Institute of Advanced Industrial Science and Technology Tsukuba Ibaraki Japan Human and Information Science Laboratory NTT Communication Science Laboratories Atsugi Kanagawa Japan Department of Computer Science University of Essex Colchester UK Department of Adaptive Machine Systems Osaka University Suita Osaka Japan School of Engineering University of Tokyo Bunkyo Tokyo Japan Department of Electrical Engineering and Computer Science University of Kansas Lawrence KS USA

Artificial neural networks have been traditionally employed to learn and compute the inverse kinematics of a robotic arm. However, the inverse kinematics model of a typical robotic arm with joint limits is a multi-valued and discontinuous function. Because it is difficult for a multilayer neural network to approximate this type of function, an accurate inverse kinematics model cannot be obtained by using a single neural network. In order to overcome the difficulties of inverse kinematics learning, we propose a novel modular neural network system that consists of a number of expert modules, where each expert approximates a continuous part of the inverse kinematics function. The proposed system selects one appropriate expert whose output minimizes the expected position/orientation error of the end-effector of the arm. The system can learn a precise inverse kinematics model of a robotic arm with equal or more degrees of freedom than that of its end-effector. However, there are robotic arms with fewer degrees of freedom, where the system cannot learn their precise inverse kinematics model. We have adopted a modified Gauss-Newton method for finding the least-squares solution to address this issue. Through the modifications presented in this paper, the improved modular neural network system can obtain a precise inverse kinematics model of a general robotic arm.

关键词： Kinematics Robots Arm Neural networks Artificial neural networks Multi-layer neural network computer networks Newton method Least squares methods Recursive estimation

来源：评论

学校读者我要写书评

暂无评论

WACL: supporting telecommunications using - wearable active camera with laser pointer

WACL: supporting telecommunications using - wearable active ...

引用

International Symposium on Wearable computers

作者： N. Sakata T. Kurata T. Kato M. Kourogi H. Kuzuoka Institute of Engineering Mechanics University of Tsukuba Japan Human Interface Technology Laboratory University of Washington USA Institute of Advanced Industrial Science and Technology AIST Intelligent Systems Institute AIST Japan Department of Computer and Communication Sciences Wakayama University Japan

来源：评论

学校读者我要写书评

暂无评论

The influence of synchrony and sensory modality on the person perception process in computer-mediated groups

引用

Journal of computer-Mediated Communication 2005年第3期10卷 00-00页

作者： Nowak, Kristine L. Watt, James Walther, Joseph B. Communication Science Department University of Connecticut United States Rensselaer Social and Behavioral Research Laboratory Rensselaer Polytechnic Institute United States Department of Communication Cornell University United States Human Computer Interaction Lab. University of Connecticut United States Department of Communication Sciences University of Connecticut 850 Bolton Road U-1085 Storrs CT 06269 United States Rensselaer Social and Behavioral Research Laboratory United States Department of Language Literature and Communication Rensselaer Polytechnic Institute United States James Watt LL and C Rensselaer Polytechnic Institute 110 8th Street Troy NY 12180 United States Dept. of Communication Cornell University 336 Kennedy Hall Ithaca NY 14853-4203 United States

This study examined the effects of synchrony and the number of cues on the person perception process in computer-mediated communication. One hundred and forty-two participants in groups of three or four engaged in collaboration over five weeks to develop oral reports, using alternate versions of communication systems or meeting face-to-face. Consistent with the hyperpersonal model, those using low cue media felt their partners were more credible, and reported more social attraction, less uncertainty, and more involvement in the interaction than those using high cue media. People interacting with synchronous media felt increased social attraction, self-reported involvement, and certainty. They also felt that their conversations were more effective, although this effect appeared mainly in low cue groups. Results of an exploratory path analysis suggest that future research should focus on causal chains rather than direct effects, and that intervening variables (such as involvement) may be central to our understanding of the effects of communication technology systems. © 2005 Journal of computer-Mediated Communication.

关键词： Communication systems

来源：评论

学校读者我要写书评

暂无评论

Evolution: Dynamics of mammalian chromosome evolution inferred from multispecies comparative maps

引用

science 2005年第5734期309卷 613-617页

作者： Murphy, William J. Larkin, Denis M. Everts-Van Der Wind, Annelie Bourque, Guillaume Tesler, Glenn Auvil, Loretta Beever, Jonathan E. Chowdhary, Bhanu P. Galibert, Francis Gatzke, Lisa Hitte, Christophe Meyers, Stacey N. Milan, Denis Ostrander, Elaine A. Pape, Greg Parker, Heidi G. Raudsepp, Terje Rogatcheva, Margarita B. Schook, Lawrence B. Skow, Loren C. Welge, Michael Womack, James E. O'Brien, Stephen J. Pevzner, Pavel A. Lewin, Harris A. Department of Veterinary Integrative Biosciences Texas A and M University College Station TX 77843 United States Department of Veterinary Pathobiology Texas A and M University College Station TX 77843 United States SAIC-Frederick Inc. National Cancer Institute Frederick MD 21702 United States Laboratory of Genomic Diversity National Cancer Institute Frederick MD 21702 United States Department of Animal Sciences University of Illinois at Urbana-Champaign Urbana IL 61801 United States National Center for Supercomputing Applications University of Illinois at Urbana-Champaign Urbana IL 61801 United States Institute for Genomic Biology University of Illinois at Urbana-Champaign Urbana IL 61801 United States Genome Institute of Singapore 138672 Singapore Singapore Department of Mathematics University of California San Diego CA 92093 United States Department of Computer Science and Engineering University of California San Diego CA 92093 United States UMR6061-CNRS Genetique et Developpement Université de Rennes 1 35043 Rennes France Laboratoire de Génétique Cellulaire INRA 31326 Castanet-Tolosan France National Human Genome Research Institute Bethesda MD 20892 United States

The genome organizations of eight phylogenetically distinct species from five mammalian orders were compared in order to address fundamental questions relating to mammalian chromosomal evolution. Rates of chromosome evolution within mammalian orders were found to increase since the Cretaceous-Tertiary boundary. Nearly 20% of chromosome breakpoint regions were reused during mammalian evolution;these reuse sites are also enriched for centromeres. Analysis of gene content in and around evolutionary breakpoint regions revealed increased gene density relative to the genome-wide average. We found that segmental duplications populate the majority of primate-specific breakpoints and often flank inverted chromosome segments, implicating their role in chromosomal rearrangement.

关键词： Biodiversity

来源：评论

学校读者我要写书评

暂无评论

CrossY: A crossing-based drawing application

CrossY: A crossing-based drawing application

引用

UIST: Proceedings of the Annual ACM Symposium on User Interface Software and Technology

作者： Apitz, Georg Guimbretiére, François Department of Computer Science Human-Computer Interaction Lab University of Maryland College Park MD 20742

We introduce CrossY, a simple drawing application developed as a benchmark to demonstrate the feasibility of goal crossing as the basis for a graphical user interface. We show that crossing is not only as expressive as the current point-and-click interface, but also offers more flexibility in interaction design. In particular, crossing encourages the fluid composition of commands which supports the development of more fluid interfaces. While crossing was previously identified as a potential substitute for the classic point-and-click interaction, this work is the first to report on the practical aspects of implementing an interface based on goal crossing as the fundamental building block. Copyright © 2004 ACM.

关键词： Drawing (graphics)

来源：评论

学校读者我要写书评

暂无评论

Design and display of enhancing information in desktop information-rich virtual environments: Challenges and techniques

引用

Virtual Reality 2004年第1期8卷 41-54页

作者： Polys, Nicholas F. Bowman, Doug A. Department of Computer Science Center for Human Computer Interaction Virginia Polytechnic Institute and State University Blacksburg VA 24060 United States

Information-rich virtual environments (IRVEs) have been described as environments in which perceptual information is enhanced with abstract (or symbolic) information, such as text, numbers, images, audio, video, or hyperlinked resources. Desktop virtual environment (VE) applications present similar information design and layout challenges as immersive VEs, but, in addition, they may also be integrated with external windows or frames commonly used in desktop interfaces. This paper enumerates design approaches for the display of enhancing information both internal and external to the virtual world's render volume. Using standard Web-based software frameworks, we explore a number of implicit and explicit spatial layout methods for the display and linking of abstract information, especially text. Within the VE view, we demonstrate both heads-up-displays (HUDs) and encapsulated scenegraph behaviors we call semantic objects. For desktop displays, which support information display venues external to the scene, we demonstrate the linking and integration of the scene with Web browsers and external visualization applications. Finally, we describe the application of these techniques in the PathSim visualizer, an IRVE interface for the biomedical domain. These design techniques are relevant to instructional and informative interfaces for a wide variety of VE applications. © Springer-Verlag London Limited 2004.

关键词： Desktop virtual environments Information psychophysics Information-rich virtual environments Multiple view architectures Visualization design

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：