检索结果-内蒙古大学图书馆

A DESIGN METHODOLOGY FOR FUZZY SYSTEM INTERFACES

IEEE TRANSACTIONS ON FUZZY systems 1995年第4期3卷 404-414页

作者： DEOLIVEIRA, JV INESC Control of Dynamic Systems Group Lisboa Portugal

Conceptually, a fuzzy system interacting with a numerical environment has three components: a numeric/linguistic interface, a linguistic processing unit, and a linguistic/numeric interface, At these interfaces, membership functions representing linguistic terms play a top role both for the linguistic meaning provided and for the pre/post information processing introduced to the fuzzy system, Considering these issues, a set of membership function properties is postulated, Furthermore, an expert-free interface design methodology able to meet these properties, and based on the concept of optimal interfaces, is proposed, This concept simply states an equivalence between information formats (numeric and linguistic), thereby making the methodology appealing from the applicational point of view, An algorithm is developed, and brief notes on selected applications are outlined stressing relevant issues of the proposed methodology.

关键词： Design methodology Fuzzy systems Fuzzy control Hypercubes Data analysis Fuzzy sets Artificial neural networks Performance analysis Clustering methods control systems

来源：评论

学校读者我要写书评

暂无评论

NEURON INSPIRED LEARNING RULES FOR FUZZY RELATIONAL STRUCTURES

引用

FUZZY SETS AND systems 1993年第1期57卷 41-53页

作者： DEOLIVEIRA, JV INESC Control of Dynamic Systems Group 1017 Lisboa Codex Portugal

Fuzzy relational equations are a suitable framework for fuzzy modelling. However their constructive resolution methods suffer from known drawbacks. In order to determine approximate solutions, both conventional and adaptive gradient based learning methods are proposed, namely for extended versions of fuzzy relational structures. Simulation results show that, for both learning methods, good approximate solutions are found. However the adaptive version shows considerably quicker convergence rates. The problem of process fuzzy identification using the proposed framework is then outlined, as an illustrative application.

关键词： ADAPTIVE LEARNING FUZZY RELATIONS FUZZY IDENTIFICATION AND MODELING NEURAL NETWORKS OPERATORS

来源：评论

学校读者我要写书评

暂无评论

Sampling, fuzzy discretization, and signal reconstruction

引用

FUZZY SETS AND systems 1996年第2期79卷 151-161页

作者： deOliveira, JV INESC - Control of Dynamic Systems Group Apartado 13069 1000 Lisboa Portugal

The sampling theorem provides the condition under which a continuous-time signal can be precisely represented and completely recovered from its instantaneous values equally spaced in time;it gives a condition for the signal reconstruction problem. The importance of this theorem pertains to the necessity of knowing when a continuous-time signal is uniquely represented by its discrete version, so that continuous-time signals can be properly converted and handled by sampled-data systems like digital computers. The problem of the equivalence between (either continuous-time or discrete-time) signals and their fuzzy descriptions is analyzed here. This encompasses the analysis of signal reconstruction when fuzzy systems are used as sampled-data systems such as fuzzy filters, fuzzy models, or fuzzy controllers. A necessary and sufficient condition is given for ensuring that the fuzzy system processes the legitimate representations of the signal presented at its interfaces. Furthermore, a sufficient condition suitable for automatic tuning of membership functions is proposed and discussed. The discussion encompasses the outline of some requirements that membership functions at fuzzy system interfaces should meet to allow humans to assess their semantic meaning.

关键词： fuzzy aliasing fuzzy control information processing linguistic modelling membership functions sampling signal processing

来源：评论

学校读者我要写书评

暂无评论

LONG-RANGE PREDICTIVE ADAPTIVE FUZZY RELATIONAL control

引用

FUZZY SETS AND systems 1995年第2-3期70卷 337-357页

作者： DEOLIVEIRA, JV LEMOS, JM INESC — Control of Dynamic Systems Group Apartado 10105 1017 Lisboa Codex Portugal

A class of lone-range predictive adaptive fuzzy relational controllers is presented. The plant behavior is described over an extended time horizon by a fuzzy relational model which is identified based on input-output closed-loop observations of the plant variables, In this class of adaptive controllers the control law attempts to minimize a quadratic cost over an extended control horizon. When used with linear models, this approach has revealed a significant potential for overcoming the limitations of one-step ahead schemes, such as the stabilization of non-minimum phase plants. Here, a uniform framework is adopted for implementing both the fuzzy model and the fuzzy controller, namely distributed fuzzy relational structures gaining from their massive parallel processing features and from the learning capabilities typical of the connectivist approaches. Issues such as maintenance during the adaptation process of the meaning of linguistic terms used at both fuzzy systems interfaces are addressed, namely by introducing a new design methodology for on-line fuzzy systems interface adaptation. The examples presented reinforce the claim of the usefulness of this new approach.

关键词： ADAPTIVE control FUZZY IDENTIFICATION AND MODELING FUZZY RELATIONAL STRUCTURES, FUZZY SYSTEM INTERFACES LONG-RANGE PREDICTION MEMBERSHIP FUNCTIONS

来源：评论

学校读者我要写书评

暂无评论

On optimal fuzzy systems I/O interfaces

On optimal fuzzy systems I/O interfaces

引用

Second IEEE International Conference on Fuzzy systems

作者： de Oliveira, J.Valente INESC - Control of Dynamic Systems Group Lisbon Portugal

ISBN: (纸本)0780306155

Many fuzzy systems can be viewed as having a numeric/linguistic interface, a linguistic subsystem whose I/O are linguistic terms, and a linguistic/numeric interface. It is shown that for such fuzzy systems the construction of its interfaces can be formulated as a problem of numeric optimization with constraints. Two algorithms for finding optimal interfaces are derived from two successive reformulations of the original problem. Simulation results are provided showing the efficiency as well as the impact of these algorithms on an overall system performance.

关键词： Interfaces (computer)

来源：评论

学校读者我要写书评

暂无评论

System modelling and fuzzy relational identification

System modelling and fuzzy relational identification

引用

Second IEEE International Conference on Fuzzy systems

作者： de Oliveira, J.Valente Lemos, J.Miranda INESC - Control of Dynamic Systems Group Lisbon Portugal

ISBN: (纸本)0780306155

Fuzzy relation equations are a suitable framework for modelling physical processes. However their applications to the Identification and Modelling problems are still weakly explored. In order to fill this gap, two related critical issues are addressed: the construction of numeric/linguistic interfaces and the computation of the fuzzy relation. An optimizing algorithm is adopted for the construction of numeric/linguistic interface. Adaptive learning is proposed for determining approximated solutions for systems of fuzzy relation equations, namely for its extended versions. Simulation results are provided showing both fast learning rates, and good performance for the derived model.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

A SET-THEORETICAL DEFUZZIFICATION METHOD

引用

FUZZY SETS AND systems 1995年第1期76卷 63-71页

作者： DEOLIVEIRA, JV INESC - Control of Dynamic Systems Group R. Alves Redol 9. Apartado 13069 1000 Lisboa Portugal

A defuzzification method coinciding with the result of the subsethood theorem, and including a family of averaging methods (like mean of maxima and center of gravity) as special cases is presented. The defuzzification method, named subsethood defuzzification (SD) method, has the advantage of being exclusively based on set theoretical operations, giving thus an insight on the nature of the computations involved in one of the most controversial stages of the fuzzy controller architecture. In addition, the SD method allows its customization also in the aim of set theory. Customization is believed as a necessary feature as the defuzzification problem seems ill-defined and application dependent.

关键词： DEFUZZIFICATION FUZZY control FUZZY SETS OPERATORS SUBSETHOOD THEOREM

来源：评论

学校读者我要写书评

暂无评论

System modelling and fuzzy relational identification

System modelling and fuzzy relational identification

引用

IEEE International Conference on Fuzzy systems (FUZZ-IEEE)

作者： J.V. de Oliveira J.M. Lemos INESC-Control of Dynamic Systems Group Lisboa Portugal

Fuzzy relation equations are a suitable framework for modeling physical processes. However, their applications to identification and modeling problems are still weakly explored. To fill this gap, two related critical issues are addressed: the construction of numeric/linguistic interfaces and the computation of the fuzzy relation. An optimizing algorithm is adopted for the construction of the numeric/linguistic interface. Adaptive learning is proposed for determining approximated solutions for systems of fuzzy relation equations, namely for their extended versions. Simulation results are provided showing both fast learning rates and good performance for the derived model.< >

关键词： Fuzzy systems Fuzzy sets control systems Nonlinear equations Computational modeling Fuzzy control Discrete transforms Testing

来源：评论

学校读者我要写书评

暂无评论

Towards Neuro-Linguistic Modelling

引用

IFAC Proceedings Volumes 1997年第7期30卷 521-526页

作者： J. Valente de Oliveira INESC - Research Group on Control of Dynamic Systems Apartado 13069 1000 Lisboa Portugal

In neuro-fuzzy (or fuzzy-neural) models using unconstrained learning it is not possible to guarantee that the resulting membership functions represent human-interpretable linguistic terms. However one of the most interesting features of fuzzy systems is the insight provided on the linguistic relationship between their variables. This paper summarizes the requirements to build neuro-linguistic models. These are linguistically intrepretable due to the employement of a set of constraints that when used within an optimization scheme, such as backpropagation, obviate the subjective task of interpretating membership functions. Examples illustrating the performance of neuro-linguistic models are included.

关键词： Adaptive systems Fuzzy modelling Learning algorithms Membership functions Neural networks Optimization

来源：评论

学校读者我要写书评

暂无评论

Fuzzy model based long-range predictive control

Fuzzy model based long-range predictive control

引用

IEEE International Conference on Fuzzy systems (FUZZ-IEEE)

作者： J.V. de Oliveira J.M. Lemos INESC-Control of Dynamic Systems Group Lisboa Portugal

Fuzzy model based long-range predictive control algorithms are presented. A distributed fuzzy relational model is used for forecasting. The control law seeks to minimize a multi-step performance index using a receding horizon strategy. The adaptation mechanisms deal with the linguistic maintenance of the involved membership functions. A case study is presented.< >

关键词： Fuzzy control Predictive models Predictive control Fuzzy systems Adaptive control Open loop systems Programmable control Neural networks control systems Sampling methods

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：