检索结果-内蒙古大学图书馆

IEE Colloquium on Internet Technology and the Integrated Enterprise (Digest No: 1997/149)

作者： M. Hanneghan G. Colquhoun M. Merabti Sch. of Comput. & Math. Sci. Liverpool John Moores Univ. UK School of Computer and Mathematical Sciences Liverpool John Moores University Liverpool UK

Concurrent engineering (CE) is a manufacturing philosophy and right-first-time approach to the product lifecycle that has the potential to produce dramatic reductions in product development time and cost. The paper discusses the CONCERT architecture (Concurrent Engineering Support) distributed middleware services which support concurrent engineering. The CONCERT architecture allows Internet clients (virtual team members) to access these middleware services through a special cross-platform control-panel application or (in a restricted form) via the World Wide Web.

关键词： Internet

来源：评论

学校读者我要写书评

暂无评论

An improved scheme for the fuzzifier in fuzzy clustering

An improved scheme for the fuzzifier in fuzzy clustering

引用

IEEE Workshop on Neural Networks for Signal Processing

作者： L.B. Romdhane B. Ayeb S. Wang Dept. of Math. & Comput. Sci. Sherbrooke Univ. Que. Canada Mathematical and Computer Science Department Faculty of Sciences University Of Sherbrooke Sherbrooke QUE Canada

Clustering is an important research area and of practical applications in many fields. Fuzzy clustering has shown advantages over crisp and probabilistic clustering especially when there are significant overlaps between clusters. However, all of the fuzzy clustering algorithms are sensitive to an exponent parameter, namely the fuzzifier. To our knowledge, no theoretical foundations are yet available for the optimal choice of this parameter. The current work develops an improved scheme for the fuzzifier by embedding more knowledge about the data set to cluster in its comput.tion.

关键词： Fuzzy sets Clustering algorithms Partitioning algorithms Thumb comput.r sci.nce Application software Embedded comput.ng Neural networks Fuzzy neural networks Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Learning orthographic transformations for object recognition

Learning orthographic transformations for object recognition

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： G. Bebis M. Georgiopoulos S. Bhatia Dept. of Math. & Comput. Sci. Missouri Univ. St. Louis MO USA Department of Mathematics & Computer Science University of Missouri Saint Louis MO USA

Considers the problem of learning to predict the correct pose of a 3D object, assuming orthographic projection and 3D linear transformations. A neural network is trained to learn the desired mapping. First, we consider the problem of predicting all possible views that an object can produce. This is performed by representing the object with a small number of reference views and using algebraic functions of views to construct the space of all possible views that the object can produce. Fundamental to this procedure is a methodology based on singular value decomposition and interval arithmetic for estimating of the ranges of values that the parameters of algebraic functions can assume. Then, a neural network is trained using a number of views (training views) which are generated by sampling the space of views of the object. During learning, a training view is presented to the inputs of the network which is required to respond at its outputs with the parameters of the algebraic functions used to generate the view from the reference views. Compared to similar approaches in the literature, the proposed approach has the advantage that it does not require the 3D models of the objects or a large number of views, it is extendible to other types of projections, and it is more practical for object recognition.

关键词： Object recognition Neural networks math.matics comput.r sci.nce comput.r graphics Singular value decomposition Arithmetic Data preprocessing Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

An intelligent agent for adaptive processor allocation in parallel databases

An intelligent agent for adaptive processor allocation in pa...

引用

IEEE International Conference on Intelligent Processing Systems, ICIPS

作者： K.H. Lin Y. Jiang C.H.C. Leung Dept. of Comput. & Math. Sci. Victoria Univ. of Technol. Melbourne Vic. Australia Department of Computer and Mathematical Sciences Victoria University of Technology Melbourne VIC Australia

The use of software agents has become an increasingly valuable approach in dealing with information filtering and resource allocation. Parallel query execution has gained currency in high performance databases in recent years, and existing works have focused on either developing parallel algorithms for individual query operations or parallelising query execution plans, but few of them have studied processor allocation for parallel processing. This paper presents an intelligent agent system that exploits both intra-operation and inter-operation parallelism for multiple query execution. It monitors data loading with learning capabilities and processes queries adaptively based on phase-based and non-phase-based processor allocation strategy. An experimental study is presented to assess the performance benefits of the proposed agent system.

关键词： Intelligent agent Parallel processing Relational databases Software agents Query processing Resource management Concurrent comput.ng Information filtering Database systems Application software

来源：评论

学校读者我要写书评

暂无评论

A new typicality-based weight function for robust mixture decomposition

A new typicality-based weight function for robust mixture de...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： S. Medasani R. Krishnapuram W. Caldwell Dept. of Math. & Comput. Sci. Colorado Sch. of Mines Golden CO USA Department of Mathematical and Computer Sciences Colorado Schml of Mines Golden CO USA Department of Pathology and Anatomical Sciences University of Missouri Columbia MO USA

One of the fundamental problems in applications of fuzzy set theory is the estimation of membership functions from data. In methods based on probability theory one of the techniques used to estimate probability densities is mixture decomposition. This method assumes that a given data set comes from a distribution that is a convex combination of parametrized components (density functions) such as Gaussians. A similar method can be used to estimate membership functions. In other words, a membership function can be modeled as a convex combination of parametrized models. Therefore, the task of estimating the membership function can be viewed as a mixture decomposition problem. Mixture decomposition involves estimation of the parameters of each component in the mixture. The expectation-maximization (EM) algorithm has been traditionally used for Gaussian mixture decomposition. However, this algorithm is not robust, and gives poor results in the presence of noise. In this paper, we present a robust algorithm for Gaussian mixture decomposition. The algorithm uses robust statistical methods to construct a weight function. Since the weight function is based on the idea of typicality, it gives low weights to noise points and outliers. Thus, the algorithm gives robust estimates of the parameters. The weight function we propose uses the distribution of the distances of good points to component prototypes. We present results of the algorithm for both synthetic and real data sets.

关键词： Noise robustness Gaussian processes Gaussian distribution Parameter estimation Iterative algorithms Pathology Application software Fuzzy set theory Estimation theory Density functional theory

来源：评论

学校读者我要写书评

暂无评论

Design and modeling of a piezo-actuated positioning mechanism

Design and modeling of a piezo-actuated positioning mechanis...

引用

IEEE Conference on Decision and Control

作者： J.M.T.A. Adriaens W.L. de Koning R. Banning Dept. of Appl Math. & Comput. Sci. Delft Univ. of Technol. Netherlands Department of Applied Mathematics and Computer Science Delft University of Technnology Delft Netherlands Delft Institute of Microelectronics and SubmicrontechnologyDepartment of Applied Physics Delft University of Technnology Delft Netherlands

ISBN: (纸本)0780341872

We are involved in the design and control of a 1-dimensional positioning mechanism for a range of 50 /spl mu/m and an accuracy of 30 pm. Only piezoelectric actuators can be used to manage such small displacements. However, these actuators show hysteretic behavior and lengthening saturation. The extremely small displacements are measured by means of capacitive sensors. In order to design a controller a model of the positioning mechanism and the actuators is developed. Contrary to the existing literature, in our model the hysteresis is described by a differential equation. The mechanical characteristics of the design, and therefore also of the model, are chosen such that they are practically realizable and advantageous for controller design. The final nonlinear fifth order state space model is believed to be suitable for a nonlinear control technique like feedback linearization.

关键词： Magnetic hysteresis Actuators History Differential equations Sensor phenomena and characterization Magnetic materials math.matics comput.r sci.nce Microelectronics Physics

来源：评论

学校读者我要写书评

暂无评论

Optimally routing LC permutations on k-extra-stage cube-type networks

引用

IEEE TRANSACTIONS ON comput.RS 1996年第1期45卷 97-103页

作者： Hu, Q Shen, XJ Liang, WF Comput. Sci. Telecommun. Program Missouri Univ. Kansas City MO USA

It is difficult to partition an arbitrary permutation into a minimum number of groups such that conflict-free paths for ail source-destination pairs in each group can be established on an omega network. Based on linear algebra theory, this paper presents an optimal algorithm which solves this problem for the LC class of permutations on a large class of multi-stage networks. This algorithm extends the previous result which deals with the BPC class of permutations on the omega network.

关键词： k-extra-stage cube-type networks LC permutations multistage interconnection networks optimization problems permutation realization

来源：评论

学校读者我要写书评

暂无评论

Relevance feedback in the retrieval of reusable software components 29

Relevance feedback in the retrieval of reusable software com...

引用

29th Hawaii International Conference on System sci.nces, HICSS 1996

作者： Toptsis, A.A. Jin, Lan Dept. of Comput. Sci. and Math. York Univ. Atkinson College TorontoON Canada

ISBN: (纸本)0818673249

We focus on the issue of retrieving software from a collection of reusable software components. The proposed method is a variation of the relevance feedback process, a popular retrieval mechanism typically used for text document environments. We describe how this method can be adapted for reusable software collections. Two variations of a relevance feedback process are presented. Also, experimental results of the methods' performance evaluation on two different software collections are presented and analyzed. The results show that both methods perform well, by attaining recall and precision values above 70% on the average. Specific drawbacks of the methods are also identified and discussed. Our proposal constitutes an attempt to put the software retrieval problem in the map of technical obstacles for software reuse. Unlike most related reports that treat software retrieval as a subissue of some other software reusability issue (such as classification), we believe that software retrieval is a self-standing issue. As such, we address the problem of software retrieval in a general framework, that is, without being attached to particular software classification and repository organization techniques. © 1996 IEEE.

关键词： comput.r software reusability

来源：评论

学校读者我要写书评

暂无评论

Simulation of chaotic iterative processes in speed-independent comput.ng networks 4

Simulation of chaotic iterative processes in speed-independe...

引用

4th Euromicro Workshop on Parallel and Distributed Processing, PDP 1996

作者： Goubareni, N.M. Inst. of Math. and Comput. Sci. Tech. Univ. of Czestochowa Chqstochowa42-200 Poland

ISBN: (纸本)0818673761

math.matical simulation of self organizing chaotic processes in networks with speed independent processes by means of the asynchronous method of chaotic relaxations with delay using the Monte-Carlo method is considered. This method allows to imitate effectively the fulfilment of chaotic comput.ng processes depending on the spread of time parameters of speed independent processors. Every speed independent processor is a nonsynchronous competing device in which the duration of the transient process is a random variable. In this work it is assumed that the random variable has normal distribution as far as the duration of work of the logical elements has namely such law of distribution. For comput.r simulation the Dirichlet problem was chosen for Laplace's equation, on a rectangular domain of R2. Numerical calculations for solving this problem, comparing evaluations of errors and speed of convergence of comput.ng processes arising in networks with speed independent processors are presented. © 1996 IEEE.

关键词： Random variables

来源：评论

学校读者我要写书评

暂无评论

Minimizing communication of a recirculating bitonic sorting network 25

Minimizing communication of a recirculating bitonic sorting ...

引用

25th International Conference on Parallel Processing, ICPP 1996

作者： Lee, Jae-Dong Batcher, K.E. Dept. of Math. and Comput. Sci. Kent State Univ. OH44242-0001 United States

ISBN: (纸本)081867623X

This paper presents the construction of a new recirculating bitonic sorting network which reduces the O(Nlog2N) cost complexity of the original bitonic sorting network to O(NlogN) while preserving the well known time complexity of O(log2N). Network communication is reduced by one half by leaving the N/2 even-parity keys in the local memory of each comparator. © 1996 IEEE.

关键词： Complex networks

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：