检索结果-内蒙古大学图书馆

5th European Conference on Speech Communication and Technology, EUROSPEECH 1997

作者： Kim, Do Yeong Kim, Nam Soo Un, Chong Kwan Department of Elec. Eng. KAIST Korea Republic of Human and Computer Interaction Lab. SAIT Korea Republic of

In this paper, we consider the hidden Markov model(HMM) parameter compensation in noisy environments with multiple noise sources based on the vector Taylor series(VTS) approach. General formulations for multiple environmental variables are derived and systematic expectation-maximization(EM) solutions are presented in maximum likelihood(ML) sense. It is assumed that each noise source is independent and having Gaussian distribution. To evaluate proposed method, we conduct speaker independent isolated word recognition experiments in various noisy environments. Experimental results show that proposed algorithm ahieves significant improvement. Especially, the proposed method is consistently more effective than the parallel model combination(PMC) based on log-normal approximation. © 1997 5th European Conference on Speech Communication and Technology, EUROSPEECH 1997. All rights reserved.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Trajectory control of robotic manipulators using chaotic neural networks

Trajectory control of robotic manipulators using chaotic neu...

引用

1997 IEEE International Conference on Neural Networks, ICNN 1997

作者： Kim, Sang-Hee Jang, Chang-Wha Chai, Chang-Hyun Choi, Han-Go Human-Computer Interaction Lab. Dept. of Electronics Kumoh Nat. Univ. of Tech. Korea Republic of

ISBN: (纸本)0780341228

This paper investigates the direct adaptive control of nonlinear systems using chaotic neural networks. Since the structure of a chaotic neural network contains self and internal feedback loops in each layer, chaotic neural networks can show robust characteristics for controlling highly nonlinear dynamics such as in robotic manipulators. This paper presents modified chaotic neural networks with the backpropagation learning algorithm. To evaluate the performance of the proposed neural networks, we simulate the trajectory control of the three-axis PUMA robot with direct adaptive control strategies. The structure of the robot controller consists of the PD controller and chaotic neural networks controller in parallel. Simulation results showed the superior performance on convergence and final error compared with recurrent neural networks. Chaotic neural networks also reduce the number of nodes and computation time. © 1997 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A rank-by-feature framework for interactive exploration of multidimensional data

引用

Information Visualization 1997年第2期4卷 96-113页

作者： Seo, Jinwook Shneiderman, Ben Department of Computer Science University of Maryland College Park MD 20742 United States Human-Computer Interaction Lab Institute for Advanced Computer Studies University of Maryland College Park MD 20742 United States Institute for Systems Research University of Maryland College Park MD 20742 United States

Interactive exploration of multidimensional data sets is challenging because: (1) it is difficult to comprehend patterns in more than three dimensions, and (2) current systems often are a patchwork of graphical and statistical methods leaving many researchers uncertain about how to explore their data in an orderly manner. We offer a set of principles and a novel rank-by-feature framework that could enable users to better understand distributions in one (1D) or two dimensions (2D), and then discover relationships, clusters, gaps, outliers, and other features. Users of our framework can view graphical presentations (histograms, boxplots, and scatterplots), and then choose a feature detection criterion to rank 1D or 2D axis-parallel projections. By combining information visualization techniques (overview, coordination, and dynamic query) with summaries and statistical methods users can systematically examine the most important 1D and 2D axis-parallel projections. We summarize our Graphics, Ranking, and interaction for Discovery (GRID) principles as: (1) study 1D, study 2D, then find features (2) ranking guides insight, statistics confirm. We implemented the rank-by-feature framework in the Hierarchical Clustering Explorer, but the same data exploration principles could enable users to organize their discovery process so as to produce more thorough analyses and extract deeper insights in any multidimensional data application, such as spreadsheets, statistical packages, or information visualization tools. © 2005, SAGE Publications. All rights reserved.

关键词： dynamic query exploratory data analysis feature detection/selection graphical displays information visualization Rank-by-feature framework

来源：评论

学校读者我要写书评

暂无评论

JOINT ESTIMATION OF PITCH, BAND MAGNITUDES AND V/UV DECISIONS FOR MBE VOCODER 5

JOINT ESTIMATION OF PITCH, BAND MAGNITUDES AND V/UV DECISION...

引用

5th European Conference on Speech Communication and Technology, EUROSPEECH 1997

作者： Cho, Yong Duk Kim, Hong Kook Kim, Moo Young Kim, Sang Ryong Human & Computer Interaction Lab. Samsung Advanced Institute of Technology San 14 Nongseo-Ri Kiheung-Eup Kyungki-Do Yongin City449-712 Korea Republic of

The multiband excitation (MBE) vocoder represents speech signal with a pitch, band magnitudes, and a voice/unvoice (V/UV) decision for each spectral band. In the conventional MBE model, model parameters are sequentially estimated in two steps. The pitch and band magnitudes are firstly estimated on the assumption of voiced speech model by the analysis-by-synthesis (AbS) in frequency domain, and then the V/UVs are decided. However, the synthetic spectrum by the above assumption may have large spectral distortion if the speech frame is strongly unvoiced such as transient region. In this paper, we propose joint estimation method which estimates and decides all the model parameters in AbS loop. For this, voiced or unvoiced speech models for each band are used during the analysis procedure. After estimating the parameters with the two speech models, a model for each band is selected so as to produce smaller spectral estimation error. By analyzing the short time spectrum and the long time spectrogram, it is shown that the reproduced speech of the proposed model is superior to that of the conventional one. In addition, through informal listening test we also confirm the superiority of the proposed model. © 1997 5th European Conference on Speech Communication and Technology, EUROSPEECH 1997. All rights reserved.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Trajectory control of robotic manipulators using chaotic neural networks

Trajectory control of robotic manipulators using chaotic neu...

引用

International Conference on Neural Networks

作者： Sang-Hee Kim Chang-Wha Jang Chang-Hyun Chai Han-Go Choi Human-Computer Interaction Lab Department of Electronics Kum-Oh National University of Technology South Korea

ISBN: (纸本)0780341228

关键词： Robot control Chaos Neural networks Manipulator dynamics Adaptive control Nonlinear systems Feedback loop Robust control Backpropagation algorithms Parallel robots

来源：评论

学校读者我要写书评

暂无评论

Negotiating user-initiated cancellation and interruption requests 96

Negotiating user-initiated cancellation and interruption req...

引用

Proceedings of the 1996 Conference on human Factors in Computing Systems, CHI 96

作者： Perez-Quinones, Manuel A. Sibert, John L. Human-Computer Interaction Lab Washington United States

ISBN: (纸本)9780897918329

Interruptions and cancellations are important parts of a user interface, yet they are treated as special cases in user interface design and notations. In an effort to build a dialogue notation that allows for effective definition of these commands that allows for effective definition of these commands or user turns, we present a behavioral definition of interruptions and cancellations. We show several examples of how our definition accounts for different forms of behavior. The behavioral definitions provided here are a step towards providing better support for the definition and implementation of these turns.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional computation visualization for computer graphics rendering algorithms

SIGCSE Bulletin (Association for Computing Machinery, Specia...

引用

SIGCSE Bulletin (Association for Computing Machinery, Special Interest Group on computer Science Education) 1996年第1期28卷 358-362页

作者： Goldman, David A. Eckert, Richard R. Watson, Thoms J. Cohen, Maxine S. Human Computer Interaction Lab Computer Science Dep

Computation visualization or algorithm animation is becoming an increasingly popular and effective way of teaching, debugging, and analyzing algorithms. Over the past ten years, several algorithm animation systems have been produced. Proposed here is a new approach and framework for visualizing three-dimensional algorithms or computations. Implemented on a prototype algorithm animation system, this framework, termed the vector-guided view, produces insightful visualizations of three-dimensional computation by effectively solving the problems of 3D scene navigation. The creation of this framework was motivated by the desire to produce visualizations of an increasingly large and complex set of rendering algorithms now ubiquitous in the field of computer graphics. To show the potential of this framework, a dynamic visualization of a recursive ray-tracing program has been created. A brief summary of the algorithm animation system is presented.

关键词： Algorithms

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional computation visualization for computer graphics rendering algorithms 96

Three-dimensional computation visualization for computer gra...

引用

Proceedings of the twenty-seventh SIGCSE technical symposium on computer science education

作者： David A. Goldman Richard R. Eckert Maxine S. Cohen Human Computer Interaction Lab. Computer Science Dept. Thomas J. Watson School of Engineering and Applied Science Binghamton University Binghamton New York Staff Programmer - User Centered Design Solutions Boca Raton Florida

ISBN: (纸本)9780897917575

关键词：

来源：评论

学校读者我要写书评

暂无评论

Situation assessment through collaborative human-computer interaction

引用

NAVAL ENGINEERS JOURNAL 1996年第4期108卷 41-51页

作者： Kushnier, SD Heithecker, CH Ballas, JA McFarlane, DC Scott Kushnier:is an engineer at the Naval Air Warfare Center in Warminster Pennsylvania where he has worked for the past seven years. He earned an M.S. degree in Computer Science from the University of Delaware in 1994. Scott has worked on projects in automated classification plan recognition interface design and modeling & simulation to support various aspects of the Naval Air Warfare mission. He is interested in humun-computer interaction artificial intelligence natural language pvocessing modeling & simulation and open systems architectures. Jim Ballas:is a scientist at the Navy Center for Applied Research in Artificial Intelligence at the Naval Research Lab. He has a Ph.D. in Applied Experimental Psychology has been active in seueral areas of human-computer systems design and integration and has forty-two publications and technical reports. Prior to his position at NRL. he held faculty appointments at Georgetown and George Mason University. He is a member of the Acoustical Society of America the Human Factors and Ergonomics Society and Sigma Xi. He served in U.S. Army Intelligence and was awarded the Bronze Star for service in Vietnam.

Data fusion has been characterized as taking place at four levels oi abstraction: the unit level, the situation level, the threat level, and the resource allocation level. A unit level characterization tries to pin down the attributes of individual platform objects, At the situation level, organized groups of units, such as battle groups, are explored. At the threat level and resource allocation level, reasoning about possible enemy intentions and possible responses is undertaken. Little work, however has been done concerning some of the higher levels of abstraction, namely the force and threat levels. This paper presents an approach toward situation assessment which includes explicit conceptualizations of forces and threats. Graphical representations of these forces and threats are designed to enhance the unit level depiction without obscuring it. This paper explores a novel style of user interface-one designed to allow collaboration between the person and the machine, enabling a tactical assessment which is superior to one in which either the person or the machine works in isolation. The paper will then describe a natural division of responsibilities between person and machine and illustrate the benefit of such a collaborative system in light of an example based on a warfare scenario.

关键词： human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Focus in graphical user interfaces 93

Focus in graphical user interfaces

引用

1st International Conference on Intelligent User Interfaces, IUI 1993

作者： Pérez, Manuel A. Sibert, John L. Human-Computer Interaction Lab Naval Research Laboratory WashingtonDC20375-5320 United States Department of Electrical Engineering and Computer Science George Washington University WashingtonDC United States

ISBN: (纸本)0897915569

Focus in natural language processing is used to keep track of the attentional space of the participants in the dialogue. Graphical interfaces have still to benefit from the use of this level of communication. We discuss a graphical interface counter part called a focus space. Focus spaces can be used to combine multiple interaction styles (e.g. natural language with graphical pointing). We describe how a specific theory of discourse structure and focus space can be applied to graphical interfaces. The attentional space is maintained automatically by the system, and can be used by the software under program control. An example is provided showing how the attentional space can be used. © 1992 ACM.

关键词： Graphical user interfaces

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：