检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing

作者： S. Shah J.K. Aggarwal J. Eledath J. Ghosh Computer and Vision Research Center Department of Electrical and Computer Engineering University of Texas Austin Austin TX USA University of Texas at Austin Austin TX US Laboratory for Artificial Neural Systems Department of Electrical and Computer Engineering University of Texas Austin Austin TX USA

This paper presents a system for classification of scenes using a multisensor integration framework. Indoor scenes are imaged using a visual and an infrared sensor and the images processed in three stages to perform classification of sensed objects into two classes: human and background. Finally, information from individual classifiers is integrated in order to obtain an improved classification performance. Details of feature extraction and classification using neural network combining a multi-Bayesian framework are presented. Segmentation of the imaged scene is performed using existing techniques such as texture analysis and histogram modeling. Classification results on real-world data are presented. The system represents a first step in the development of improved, robust classifiers based on the concepts of neural networks and multisensor integration.

关键词： Layout neural networks Infrared sensors Humans Feature extraction Image segmentation Image analysis Image texture analysis Performance analysis Histograms

来源：评论

学校读者我要写书评

暂无评论

Incorporating contextual information in white blood cell identification 97

Incorporating contextual information in white blood cell ide...

引用

Proceedings of the 11th International Conference on neural Information Processing systems

作者： Xubo Song Yaser Abu-Mostafa Joseph Sill Department of Electrical Engineering California Institute of Technology Pasadena CA Dept. of Electrical Engineering and Dept. of Computer Science California Institute of Technology Pasadena CA Computation and Neural Systems Program California Institute of Technology Pasadena CA

In this paper we propose a technique to incorporate contextual information into object classification. In the real world there are cases where the identity of an object is ambiguous due to the noise in the measurements based on which the classification should be made. It is helpful to reduce the ambiguity by utilizing extra information referred to as context, which in our case is the identities of the accompanying objects. This technique is applied to white blood cell classification. Comparisons are made against "no context" approach, which demonstrates the superior classification performance achieved by using context. In our particular application, it significantly reduces false alarm rate and thus greatly reduces the cost due to expensive clinical tests.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human point-of-regard tracking using state space and modular neural network models

Human point-of-regard tracking using state space and modular...

引用

IEEE Workshop on neural Networks for Signal Processing

作者： J.L. Mitchell R. Kothari Artificial Neural Systems Laboratory Department of Electrical & Computer Engineering and Computer Science University of Cincinnati Cincinnati OH USA

The presence of saccadic and smooth movements in the eye makes modular neural networks composed of two experts, each individually responsible for saccadic and smooth movements of the eyes, well suited for the tracking of human point-of-regard. To establish a basis for comparison on our data, we also consider a scalar ARMA model and a (vector) state space model. The purpose of this analysis is to build a reasonable model of human eye motion to use in prediction of point-of-regard. The ability to predict the point-of-regard of a human subject has applications in eye-tracking for man-machine interfacing, vigilance detection, and as a tool in cognitive psychology.

关键词： Humans State-space methods neural networks Eyes Artificial neural networks Predictive models Magnetic heads Tracking Collision mitigation Autocorrelation

来源：评论

学校读者我要写书评

暂无评论

On lateral connections in feed-forward neural networks

On lateral connections in feed-forward neural networks

引用

International Conference on neural Networks

作者： R. Kothari K. Agyepong Department of Electrical & Computer Engineering and Computer Science Artificial Neural Systems Laboratory University of Cincinnati Cincinnati OH USA

Feed-forward neural networks trained with back-propagation, or a variation of it, constitute the most widely applied of all synthetic neural network paradigms. Several efforts have been directed towards faster training of such networks. Most of these efforts attempt to take as large steps as possible during the training process. However, another potential source of inefficiency arising from the independent evolution of the hidden layer neurons has received considerably less attention. Fahlman and Lebiere (1991) have called this the herd effect. The herd effect arises because all the hidden layer neurons receive similar information, and thus evolve to reduce the then largest source of error during the training process. In this paper we introduce local lateral connections in a feed-forward network towards reducing this effect. A new algorithm, based on gradient descent, is derived for the proposed architecture and its efficacy evaluated through simulations.

关键词： Intelligent networks Feedforward systems neural networks Feedforward neural networks Neurons Artificial neural networks Training data Error correction Laboratories computer networks

来源：评论

学校读者我要写书评

暂无评论

Reliability evaluation of highly reliable computer control systems for energy generation, transmission and distribution

引用

EUROPEAN TRANSACTIONS ON electrical POWER 1996年第2期6卷 111-118页

作者： Kochs, HD Dieterle, W Dittmar, E [?]Prof. Dr.-Ing. Hans-Dieter Kochs (1943) VDE is head of the Department of Computer Science and Information Processing Systems at the Gerhard Mercator-University of Duisburgl Germany. He received the Dip1.-Ing. degree in Electrical Engineering and the Dr.-Ing. degree from the RWTH Aached Germany in 1972 and 1976 respectively. From 1979 to 1991 he was system engineer and division leader in the areas of R & D of highly-reliable large-scale control and information systems (AEGIDaimler FAG-Kugelfischer). Since 199 1 he has been Professor at the University of Duisburg. His current R & D areas are reliability safety and fault tolerance of technical systems especially automation systems and hybridknowledge based systems including fuzzy-logic and neural networks. (Gerhard-Menxitor-University-GH Duisburg FB 71FG 10 Lotharstr. 1 D-47048 Duisburg T +49203/379-2204 Fax +49203I379-2205)

The paper presents the results of an application-based reliability study of distributed computer control systems with very high reliability demand, e.g. for supervision and control of power plants and energy distribution systems. A reliability classification scheme is presented and typical redundant control system structures are evaluated and classified due to their system reliability Special focus is placed on assessing the influence of the communication system on total system reliability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Roles of neural and evolutionary computing in intelligent software systems

British Telecom technology journal

引用

British Telecom technology journal 1996年第4期14卷 46-54页

作者： Tsui, K.C. Azvine, B. Plumbley, M. Hong Kong Polytechnic University of Essex Kings College University of London BT Laboratories Manchester University Dynamics and Control Research Group Engineering Department Manchester University Contr. and Instrum. Research Group Staffordshire University Intelligent Systems Research Group Churchill College Cambridge United Kingdom Thorn-EMI Ctrl. Res. Laboratories Cambridge Univ. Eng. Department Centre for Neural Networks King's College London Department of Computer Science Electron. and Electrical Engineering King's College London United Kingdom European Neural Network Society

This paper describes two computing paradigms known as neural computing and evolutionary computing, and their potential contribution to building intelligent software systems. The paper begins by giving a brief introduction to the origins of each paradigm. Then two sections introduce the basic principles, and identify the role of each paradigm in intelligent system design. Each section ends with a number of applications that have been or are being investigated. These include connection admission control, modem communication, adaptive model-based control, face and handwriting recognition, frequency assignment, help-desk scheduling, financial time-series prediction, face recognition and evolving agent behavior. A section introduces the idea of using communications theory to design neural networks and the paper concludes with the authors' views on the future of neural and evolutionary computing for intelligent software systems.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Steady‐state security evaluation of electrical power systems by means of artificial neural network

引用

European Transactions on electrical Power 1995年第2期5卷 91-97页

作者： Chiodo, E. Menniti, D. Testa, A. Picardi, C. Elio Chiodo (1959) received the degree in Electronics Engineering in 1985 and the Ph.D. degree in Computational Statistics both from the University of Naplefltaly. He is a Researcher at the Department of Electrical Engineering of the University of Naples and a member of the Italian Statistical Society. His areas of interest include probabilistic methods applied to electric power systems analysis. (University of Naples Fedrrico 11. Electrical Engineering Dept.via Claudio 21 1-80125 Naplefltaly T +3981/7683226 Fax+3981/2396897) Daniele Menniti (1958) received the degree in Electrical Engineering from the University of Calabria. Cosenzataly and the Ph.D. degree in Electrical Engineering from the University of NapleslItaly in 1984 and 1989 respectively. He is a researcher at the Electronic. Computer and Systems Science Department of the University of Calabria. Italy. Hiscurrent research interests concern electric power system analysis real-time control and automation. (University of Calabria Electronic Computer and Systems Science Dep. Arcavacataji Rende (CS). 1-87036 CosenzdItaly T +39984/494707. Fax +39984/4947 13) Alfredo Testa (1950) received the degree in Electrical Engineering from the University of Naples/Italy in 1975. He is an Associate Professor in Electrical Power Systems at the Department of Electrical Engineering of the University of Naples. He is engaged in researches on electrical power systems reliability and harmonic analysis. (University of Naples Federico 11. Electrical Engineering Dep. via Claudio '2 1 1-80 I25 NapleslItaly T + 39 8 I/7 68 3'2 11. Fax+3981/2396897) Ciro Picardi (1949) received the degree in Electronics Engineering from the University of Naples/Italy in 1975. He is currently Associate Professor in Process Control at the Department of Electronic Computer and System Science of the University of Calabria. Italy. His current research interests are in the area of electrical drives robotics neural networks and fuzzy control. (University of Calabria Electronic. Compu

An artificial‐neural‐network (ANN) application for steady‐state security evaluation of electrical power systems is presented. Such application is based upon a combined use of a multilayer back‐propagation neural network and of an opportune electrical system model, previously proposed by some of the authors. In the paper, the definition of steady‐state security and the problems arising from its on‐line evaluation are briefly recalled. Then, the ANN utilized is described with particular reference to the solutions adopted by the authors. Afterwards, some remarks on the system model utilized are reported. Finally, numerical applications on the AEP‐14 bus system are presented and the results obtained with different ANN configurations are analyzed. Copyright © 1995 John Wiley & Sons, Ltd.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Random parameter variation in analog VLSI neural networks for linear image filtering

Random parameter variation in analog VLSI neural networks fo...

引用

International Joint Conference on neural Networks (IJCNN)

作者： B.E. Shi T. Roska L.O. Chua Department of Electrical Engineering and Computer Sciences University of California Berkeley CA USA Dual and Neural and Neural Computing Systems Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

This paper introduces an analytic method to determine the sensitivity to random parameter variations of analog VLSI neural network architectures for linear image filtering. The authors compare the robustness of several different circuit architectures for low pass filtering. This method can also determine which components within a particular architecture should specified the most precisely.< >

关键词： Intelligent networks Very large scale integration neural networks Nonlinear filters Circuits Filtering Robustness Low pass filters computer architecture Cellular neural networks

来源：评论

学校读者我要写书评

暂无评论

TECHNICAL ISSUES REGARDING SATELLITE PACKET-SWITCHING

引用

INTERNATIONAL JOURNAL OF SATELLITE COMMUNICATIONS 1994年第3期12卷 257-267页

作者： IVANCIC, WD CHU, P SHYY, DJ National Aeronautics and Space Administration Lewis Research Center Cleveland Ohio 44135 USA. A design engineer in the Digital Technology Branch of the Space Electronics Division. He has extensive experience in satellite communications systems modulation and coding on-board switching and routeing and high speed digital design. Since joining NASA in 1982 Mr. Ivancic has been responsible for the development of a variety of matrix switch controllers ground terminal equipment numerous pieces of special test equipment a beacon controller for the SARSAT program (Search and Rescue Satellite) and a time-shared decoder for a processing satellite. In addition Mr. Ivancic has been technical contract monitor on a number of advanced communications technology contracts including the Advanced Modulation Technology Development a 5 GHz fibre-optic link and multi-programmable modem study. He was awarded the B.S.E.E. and M.S.E.E. degrees by Cleveland State University in 1982 and 1986 respectively. Cleveland State University Cleveland Ohio 44115 USA. Currently an assistant professor of Electrical Engineering Department at Cleveland State University. He obtained the M.S. and Ph.D. degrees from Iowa State University majoring in Electrical and Computer Engineering. His research interests include high-speed computer networks digital systems and neural networks applications. He is a member of Sigma Xi Phi Kappa Phi as well as the IEEE and ACM. ComSearch Reston Virginia 22091 USA. Received the B.S. degree in electrical engineering from National Chiao-Tung University Hsin-Chu Taiwan in 1983 and the M.S. and Ph.D. degrees in electrical engineering from Georgia Institute of Technology Atlanta GA in 1986 and 1990 respectively. From June 1987 to October 1987 he worked for the Department of Neurology Emory University Atlanta as a Programmer. From September 1989 to December 1989 he worked for the Advanced Development Laboratory. AMP Inc. Atlanta as a Test Engineer. From February 1990 to August 1993 he wor

Many concepts for advanced communication satellite networks have recently been proposed. Critical technical issues relating to satellite packet switching for meshed very small aperture terminal networks and broadband ... 详细信息

关键词： FAST PACKET SWITCH BISDN MESHED VSAT ON-BOARD PROCESSING

来源：评论

学校读者我要写书评

暂无评论

An approach to the direct analysis of transient stability

引用

European Transactions on electrical Power 1993年第3期3卷 241-248页

作者： Djukanovic, M.B. Sobajic, D.J. Pao, Y.‐H. Miodrag B. Djukanovic (1959) received his B.S. M.Sc. and Ph.D. degrees in Electrical Engineering from the University of Belgrade/Yugoslavia in 1982 1985 and 1992 respectively specializing in electric power systems. In 1984 he joined the Electrical Engineering Institute “Nikola Tesla” in Belgrade where he was working on the scientific studies in the field of power systems planning operation and control. In 1985 and 1990 he was appointed as a research scholar at the Royal Institute of Technology Stockholm and Case Western Reserve University Cleveland Ohio. His major in- terests are in the area of power system analysis steady-state and dynamic security and application of neural networks in electric power systems. (Electrical Engineering Institute “Nicola Tesla” ul. Koste Glavinica 8A YU-11000 Belgrad T +3811/2351-619 Fax + 3811/2351-823) Dejan J. Sobajic (1949) received the B.S.E.E. and the M.S.E.E. degrees from the University of Belgrade/Yugoslavia in 1972 and 1976 respectively and the Ph.D. degree from Case Western Reserve University Cleveland Ohio in 1988. At present he is with the Department of Electrical Engineering and Applied Physics Case Western Reserve University Cleveland. He is also the Engineering Manager of A1 WARE Inc. Cleveland. His current research interests include power system operation and control neuralnet systems and adaptive control. He is a member of the IEEE Task Force on Neural-Network Applications in Power Systems and of the IEEE Intelligent Controls Committee. He is the Chairman of the International Neural-Networks Society Special Interest Group on Power Engineering. (Case Western Reserve University Department of Electrial Engineering and Computer Sciences Glennan Building Ohio 44 106 USA T + 1216/421-2380 Fax +1216/368-8776) Yoh-Han Pao (1922) has been a Professor of Electrical Engineering and Computer Science at Case Westem Reserve University (CWRU) Cleveland Ohio since 1967. He has served as chairman of the University's Electrical Engineering Department

The Transient Energy Function (TEF) method has been intensely investigated over the last decade as a reliable and accurate tool for transient stability assessment of multimachine power systems. In this paper we propose the Potential Energy Boundary Surface (PEBS) based method for direct analysis of transient stability. The critical value of transient energy and the Critical Clearing Time (T_CCT) are evaluated without the need for successive calculation and memorization of the system kinetic and potential energy values along the sustained fault trajectory. The method is used for determination of output features in the training phase of the neural‐net based transient security assessment. The proposed approach is tested on the well‐known ten‐generator New England test system demonstrating the validity and accuracy of obtained results. Copyright © 1993 John Wiley & Sons, Ltd.

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：