Showing papers on "Fuzzy associative matrix published in 1992"
01 Jan 1992
TL;DR: The mapping is proved to be capable of approximating any real continuous function on a compact set to arbitrary accuracy and applications to truck backer-upper control and time series prediction problems are presented.
Abstract: A general method is developed to generate fuzzy rules from numerical data. The method consists of five steps: divide the input and output spaces of the given numerical data into fuzzy regions; generate fuzzy rules from the given data; assign a degree of each of the generated rules for the purpose of resolving conflicts among the generated rules; create a combined fuzzy rule base based on both the generated rules and linguistic rules of human experts; and determine a mapping from input space to output space based on the combined fuzzy rule base using a defuzzifying procedure. The mapping is proved to be capable of approximating any real continuous function on a compact set to arbitrary accuracy. Applications to truck backer-upper control and time series prediction problems are presented. >
2,892 citations
TL;DR: A fuzzy modeling method using fuzzy neural networks with the backpropagation algorithm is presented that can identify the fuzzy model of a nonlinear system automatically.
Abstract: A fuzzy modeling method using fuzzy neural networks with the backpropagation algorithm is presented. The method can identify the fuzzy model of a nonlinear system automatically. The feasibility of the method is examined using simple numerical data. >
894 citations
Book•
01 Jul 1992TL;DR: Partial table of contents:Issues in the MANAGEMENT of UNCERTAINty A Survey of Uncertain and Approximate Inference.
Abstract: Partial table of contents: ISSUES IN THE MANAGEMENT OF UNCERTAINTY A Survey of Uncertain and Approximate Inference (R. Neapolitan) Rough Sets: A New Approach to Vagueness (Z. Pawlak) ASPECTS OF FUZZY LOGIC: THEORY AND IMPLEMENTATIONS LT-Fuzzy Logics (H. Rasiowa & N. Cat Ho) On Fuzzy Intuitionistic Logic (E. Turunen) On Modifier Logic (J. Mattila) FUZZY LOGIC FOR APPROXIMATE REASONING Presumption, Prejudice, and Regularity in Fuzzy Material Implication (T. Whalen & B. Schott) Inference for Information Systems Containing Probabilistic and Fuzzy Uncertainties (J. Baldwin) FUZZY LOGIC FOR KNOWLEDGE REPRESENTATION AND ELICITATION Approximate Reasoning in Diagnosis, Therapy, and Prognosis (A. Rocha, et al.) Elementary Learning in a Fuzzy Expert System (J. Buckley) KNOWLEDGE-BASED SYSTEMS USING FUZZY LOGIC Structured Local Fuzzy Logics in MILORD (J. Agustm, et al.) The Validation of Fuzzy Knowledge-Based Systems (A. Chang & L. Hall) FUZZY LOGIC FOR INTELLIGENT DATABASE MANAGEMENT SYSTEMS Fuzzy Querying in Conventional Databases (P. Bosc & O. Pivert) Index.
714 citations
TL;DR: This paper introduces the concept of distributed representation of fuzzy rules and applies it to classification problems, and proposes a fuzzy inference method using the generated fuzzy rules.
513 citations
Book•
01 Jan 1992
493 citations
08 Mar 1992
TL;DR: The authors develop a training algorithm, similar to the backpropagation algorithm for neural networks, to train fuzzy systems to match desired input-output pairs and demonstrate how the fuzzy system learns to match an unknown nonlinear mapping as training progresses and that performance is improved by incorporating linguistic rules.
Abstract: The authors develop a training algorithm, similar to the backpropagation algorithm for neural networks, to train fuzzy systems to match desired input-output pairs. The key ideas in developing this training algorithm are to view a fuzzy system as a three-layer feedforward network, and to use the chain rule to determine gradients of the output errors of the fuzzy system with respect to its design parameters. It is shown that this training algorithm performs an error backpropagation procedure: hence, the fuzzy system equipped with the backpropagation training algorithm is called the backpropagation fuzzy system (BP FS). An online initial parameter choosing method is proposed for the BP FS, and it is shown that it is straightforward to incorporate linguistic if-then rules into the BP FS. Two examples are presented which demonstrate (1) how the fuzzy system learns to match an unknown nonlinear mapping as training progresses and (2) that performance is improved by incorporating linguistic rules. >
475 citations
TL;DR: Fuzzy logic provides here means for a formal handling of such a fuzzy majority which was not possible by using traditional formal apparata, and redefine solution concepts in group decision making, and present new ‘soft’ degrees of consensus.
455 citations
[...]
TL;DR: An orderly design procedure that can help prevent problems in the development of fuzzy logic systems is presented and a four-step methodology for fuzzy system design is described.
Abstract: An orderly design procedure that can save time and help prevent problems in the development of fuzzy logic systems is presented. The nature of fuzzy logic is examined, and the design of fuzzy control systems is discussed. The architecture of a simple fuzzy controller for a steam turbine is used as an example, to show how fuzzy control models work. A four-step methodology for fuzzy system design is described. >
390 citations
TL;DR: The fuzzy judgement matrix is constructed by using a set-valued statistics method on continuous judgment matrix and it is proved that every element of the fuzzy judgment scale can be represented by a positive bounded closed fuzzy number.
140 citations
TL;DR: The sensitivity of the output to noisy input distributions and the ability of the networks to internalize multiple conjunctive clause and disjunctive clause rules are demonstrated.
08 Mar 1992
TL;DR: The author shows that proportional-integral-derivative (PID) controllers can be realized by fuzzy control methods based on the product-sum-gravity method and the simplified fuzzy reasoning method.
Abstract: The author shows that proportional-integral-derivative (PID) controllers can be realized by fuzzy control methods based on the product-sum-gravity method and the simplified fuzzy reasoning method. PID controllers, however, cannot be constructed by the min-max gravity method known as the Mamdani's fuzzy reasoning method. Extrapolative reasoning can be executed by the product-sum-gravity method and the simplified fuzzy reasoning method by extending membership functions of antecedent parts of fuzzy rules. >
17 Sep 1992
TL;DR: A detailed neuronal morphology based upon fuzzy logic and its generalization in the form of T-operators are provided and for such fuzzy logic based neurons, the learning and adaptation algorithm is developed.
Abstract: Some basic principles of fuzzy neural computing using synaptic and somatic operations are presented. The neural systems based upon conventional algebraic synaptic (confluence) and somatic (aggregation) operations are briefly reviewed. A detailed neuronal morphology based upon fuzzy logic and its generalization in the form of T-operators are provided. For such fuzzy logic based neurons, the learning and adaptation algorithm is developed. >
TL;DR: The authors use a simplified fuzzy control algorithm which allows fuzzy control rules to be regulated on line, thus constructing a Rule Self- Regulating Fuzzy Controller (RSFC).
TL;DR: A fixed network architecture employing general fuzzy unions and intersections is proposed as a mechanism to implement fuzzy logic inference and it is shown that these networks possess desirable theoretical properties.
Abstract: Fuzzy logic has been applied in many engineering disciplines. The problem of fuzzy logic inference is investigated as a question of aggregation of evidence. A fixed network architecture employing general fuzzy unions and intersections is proposed as a mechanism to implement fuzzy logic inference. It is shown that these networks possess desirable theoretical properties. Networks based on parameterized families of operators (such as Yager's union and intersection) have extra predictable properties and admit a training algorithm which produces sharper inference results than were earlier obtained. Simulation studies corroborate the theoretical properties. >
TL;DR: The problem of fuzzy optimal control of nonlinear systems is formulated and solved on the basis of fuzzy mathematical programming and the case of multicriteria optimal control with fuzzy objective function and crisp transversality conditions is considered.
TL;DR: The role of and interaction between statistical, fuzzy, and neural-like models for certain problems associated with the three main areas of pattern recognition system design are discussed and some questions concerning fuzzy sets are answered.
Abstract: The role of and interaction between statistical, fuzzy, and neural-like models for certain problems associated with the three main areas of pattern recognition system design are discussed. Some questions concerning fuzzy sets are answered, and the design of fuzzy pattern recognition systems is reviewed. Pattern recognition, statistical pattern recognition and fuzzy pattern recognition systems are described. The use of computational neural-like networks in fuzzy pattern recognition is also discussed. >
[...]
TL;DR: A unified approach is presented for solving fuzzy linear systems of equations and inequalities over a bounded chain with polynomial time algorithms, concerned with establishing the consistency of the system, computing all kinds of solutions, or marking the contradictory equations (respectively inequalities) if the system is inconsistent.
TL;DR: This paper defines, and studies the basic properties of, a fuzzy contour integral for fuzzy mappings which map a rectifiable curve in the complex plane into fuzzy complex numbers.
08 Mar 1992
TL;DR: It is shown that, by providing an ordering over the criteria, a fair procedure can be obtained for aggregation of linear orders for fuzzy MCDM, the basic methodology for representing multicriterion decision-making functions with fuzzy sets.
Abstract: Issues in the use of fuzzy set theory for decision and control are examined. The basic methodology for representing multicriterion decision-making (MCDM) functions with fuzzy sets is examined. A procedure for aggregating criteria which judge the alternatives with linear orderings is analyzed. It is shown that, by providing an ordering over the criteria, a fair procedure can be obtained for aggregation of linear orders. Two issues central to use of fuzzy logic control are investigated. The problem of aggregating the outputs of the individual rules is examined to form overall controller fuzzy output. Two families of aggregation procedures are proposed, one based on an orlike aggregation and one based on an andlike aggregation. Defuzzification is discussed. A parameterized family of defuzzification operators based upon the BADD transformation is introduced. The operation of nonmonotonic intersection is studied, and it is shown that it can form the basis for the introduction of a prioritization among criteria in fuzzy MCDM. >
01 Jan 1992
TL;DR: Four distinct types of rules with different semantics involving gradedness and uncertainty are introduced and the combination operations which appear for taking advantage of the available knowledge are all derived from the intended semantics of the rules.
Abstract: The paper starts with ideas of possibility qualification and certainty qualification for specifying the possible range of a variable whose value is ill-known. The notion of possibility which is used for that purpose is not the standard one in possibility theory, although the two notions of possibility can be related. Based on these considerations four distinct types of rules with different semantics involving gradedness and uncertainty are then introduced. The combination operations which appear for taking advantage of the available knowledge are all derived from the intended semantics of the rules. The processing of these four types of rules is studied in detail. Fuzzy rules modelling preference in decision processes are also discussed.
TL;DR: A fuzzy associative memory system called FAMOUS (Fuzzy Associative Memory Organizing Units System) simulates the knowledge representation and inference process by using fuzzy notation and by association in neural networks.
Abstract: To achieve self-organizing control based on fuzzy rules, we propose a fuzzy associative memory system called FAMOUS (Fuzzy Associative Memory Organizing Units System). FAMOUS simulates the knowledge representation and inference process by using fuzzy notation and by association in neural networks. FAMOUS's learning algorithm uses training steps to generate operation skills by modifying the expert knowledge that is initially built-in. A set of fuzzy if-then rules is used for controlling variable parameter processes. The control knowledge is represented as pairs consisting of a ‘condition’ in the if-part and an ‘operation (controller)’ in the then-part. The controllers are designed for optimization and stabilization in specific conditions. The fuzzy controller described in FAMOUS recalls well-trained controllers associated with the input condition and makes the final control output by synthesizing the intermediate outputs of their controllers. FAMOUS can highly refine knowledge by using neural network learn...
27 May 1992
TL;DR: Fuzzy logic and the calculus of fuzzy if-then rules are reviewed and their importance is discussed.
Abstract: Summary form only given. Fuzzy logic and the calculus of fuzzy if-then rules are reviewed. The agenda of the calculus of fuzzy if-then rules is set forth briefly. Their importance is discussed. >
08 Mar 1992
TL;DR: The authors proposed an architecture of multilayer feedforward neural networks for classification problems of fuzzy vectors where the activation function is extended to a fuzzy input-output relation by the extension principle.
Abstract: The authors proposed an architecture of multilayer feedforward neural networks for classification problems of fuzzy vectors. A fuzzy input vector is mapped to a fuzzy number by the proposed neural network where the activation function is extended to a fuzzy input-output relation by the extension principle. A learning algorithm is derived from a cost function defined by a target output and the level set of a fuzzy output. The proposed classification method of fuzzy vectors is illustrated by a numerical example. >
TL;DR: A fuzzy logic controller architecture that is efficient in both performance and cost is proposed, and optimization of the fuzzy logic circuits is discussed to speed up the inference process.
Abstract: A fuzzy logic controller architecture that is efficient in both performance and cost is proposed. Optimization of the fuzzy logic circuits is discussed. To speed up the inference process, the defuzzification operation is precomputed, and partial results are stored for runtime uses. Thus, larger memory is traded for better performance. The proposed architecture is less general than previous implementations, but offers better performance and cost. >
TL;DR: This work assumes that the fuzzy rules are regular and shows the existence of limit laws for five different fuzzy control rules, and considers the convergence of fuzzy controllers as the number of fuzzy rules tends to infinity.
TL;DR: It is shown how fuzzy logic programs can be transformed to neural networks, where adaptations of uncertainties in the knowledge base increase the reliability of the program and are carried out automatically.
Abstract: A foundational development of propositional fuzzy logic programs is presented. Fuzzy logic programs are structured knowledge bases including uncertainties in rules and facts. The precise specifications of uncertainties have a great influence on the performance of the knowledge base. It is shown how fuzzy logic programs can be transformed to neural networks, where adaptations of uncertainties in the knowledge base increase the reliability of the program and are carried out automatically. >
08 Mar 1992
TL;DR: The authors consider a fuzzy controller that processes fuzzy information, with fuzzy inputs for error and change in error, using a max-min neural network and a new learning algorithm, a modified delta rule, is derived.
Abstract: The authors consider a fuzzy controller that processes fuzzy information. They discuss the model of the fuzzy controller, with fuzzy inputs for error and change in error, using a max-min neural network. A new learning algorithm, a modified delta rule, is derived. The generalization property of the neural net can be used to find a controller output for new fuzzy values of error and change in error. An example is presented showing the applicability of the fuzzy neural controller. >
08 Mar 1992
TL;DR: A type of fuzzy inference coprocessor in which active rules can be detected from a set of arbitrary fuzzy rules was designed and the basic function of the cop rocessor was confirmed using a logic simulator.
Abstract: A type of fuzzy inference coprocessor in which active rules can be detected from a set of arbitrary fuzzy rules was designed In this architecture, referred to as the flexible active-rule-driven architecture, active rules are detected for various fuzzy rules and for various membership functions The fuzzy inference scheme and the concept of active rules are reviewed It is shown that active rules can be defined for different fuzzy inference methods The main features of the flexible active-rule-drive architecture are described The basic function of the coprocessor was confirmed using a logic simulator Other features of the coprocessor, such as arithmetic-unit calculation of membership grades, are also discussed The circuit simulations of the coprocessor and its implementation are outlined >
TL;DR: A general method of solving fuzzy matrix games is presented, suitable when players choose their fuzzy number ranking procedures in a wide class, i.e., that which may be represented by means of a linear ranking functions.