Fuzzy Expert Systems /

By:

Phillip Kotler

Language: Inglés Series: SeriePublication details: CRC Press EUA 1991Edition: 3Description: 307ISBN:

9688801569

LOC classification:

Contents:

TABLE OF CONTENTS FUZZY EXPERT SYSTEMS THEORY Chapter 1 The Evolution From Expert Systems to Fuzzy Expert Systems Lawrence O. Hall and Abraham Kandel Chapter 2 General Purpose Fuzzy Expert Systems Mordechay Schneider and Abraham Kandel Chapter 3 Inferences With Imprecisions and Uncertainities in Expert Systems Bernadette Bouchon-Meunier Chapter 4 On the Representation of Relational Production Rules in Expert Systems Ronald R. Yager Chapter 5 23 43 55 Reduction Procedures for Rule-based Expert Systems as a Tool for Studies of Properties of Expert's Knowledge Antonio Di Nola, Witold Pedrycz, and Salvatore Sessa 69 Chapter 6 The Physiology of the Expert System A. F. Rocha, F. Giorno, B. Leão and A. Theoto 81 Chapter 7 On the Processing of Im… [APPLICATIONS OF FUZZY EXPERT SYSTEMS Chapter 11 The Role of Approximate Reasoning in a Medical Expert System D. L. Hudson and M. E. Cohen 165 Chapter 12 Fess: A Reusable Fuzzy Expert System Lawrence O. Hall and Abraham Kandel 181 Chapter 13 Design for Designing: Fuzzy Relational Environmental Design Assistant (FREDA).... Vasco Mancini and Wyllis Bandler 195 Chapter 14 On the Design of a Fuzzy Intelligent Differential Equation Solver Menahem Friedman and Abraham Kandel 203 Chapter 15 MILORD: A Fuzzy Expert Systems Shell R. López de Mántaras, J. Agusti, E. Plaza, and C. Sierra 213 Chapter 16 Medical Decision Making Using Multidimensional Polynomials M. E. Cohen and D. L. Hudson 225 Chapter 17 Fuzzy Expert Systems for an Intelligent Computer-based Tutor Lois W. Hawkes, Sharon J. Derry, and Abraham Kandel 237 Chapter 18 Expert System on a Chip: An Engine for Approximate Reasoning Masaki Togai and Hiroyuki Watanabe 2.59 Chapter 19 A Probabilistic Logic for Expert Systems Arie Tzvieli 275 Chapter 20 COMEX - An Autonomous Fuzzy Expert System for Tactical Communications Networks Mordechay Schneider, Joseph M. Perl, and Abraham Kandel

Summary: PREFACE This edited volume addresses the specific area of fuzzy expert systems and the choices knowledge engineers and expert systems designers must make to succeed in the field of artificial intelligence To a large extent the field of uncertainty managment, in general, and fuzzy set theory, in particular, is not driven just by an interest in exploring fuzziness and managing uncertainty in what appears to be a vague and imprecise environment, but also by a practical interest in producing better expert systems and knowledge-based systems. In this book we examine the choices within the context of specific and general purpose fuzzy expert systems. In the first chapter Hall and Kandel identify the basic features of the evolution from expert systems to fuzzy expert systems, investigating the different choices provided by fuzziness. The choices here involve deciding how to handle fuzziness by both machines and humans and how to exploit fuzziness at each level of imprecision. Some of these features may not be visible to the user, but they largely determine the performance of a given expert system implementation. Their selection is based on expected performance benefits vs. the complexity associated with their inclusion. The method of handling imprecision in the system leads us through that evolution to fuzzy expert systems. In Chapter 2, Schneider and Kandel illustrate the evolutionary process described earlier by discussing the design principles of a general purpose fuzzy expert system using fuzzy expected values and fuzzy expected intervals. It is also shown how to use them as an integral part of the fuzzy expert system. Chapter 3. by Bouchon-Meunier, discusses inferences with inaccuracy and uncertainty in expert systems. This is the first step in the previously discussed evolution. The knowledge base of an expert system may contain uncertainties and inaccuracies. They are either as-sociated with the inference rules given by the experts or deduced from the observation of facts which do not fit exactly the conditions expressed in the premises of the rules A good tool to cope with these problems is one of the fuzzy implications introduced in fuzzy logics. In this chapter Bouchon-Meunier indicates some reasons supporting the choice of these inferences and the corresponding combination operator. The representation within the framework of approximate reasoning of relational type rules is illustrated by Yager in Chapter 4. A relational production rule consists of a rule in which one of the antecedent requirements involves the satisfaction of a relationship between two variables. This concept is used by Yager to represent his view of expert systems and the issues involved in some of their trade-offs. Chapter 5, by Di Nola, Pedrycz, and Sessa, is devoted to the problem of reduction of the knowledge base in rule-based expert systems. The authors first point out that this problem is placed in the main stream of procedures of expert's knowledge (or its implementation) validation. Subsequently, some algorithms leading to its resolution are given in detail and their complementary character is also underlined. The entire analysis is performed treating the knowledge base in the form of a fuzzy relation, while an inference mechanism is given by means of fuzzy relation equations. This chapter represents, like the previous chapters, important stages in the evolution of expert systems to fuzzy expert systems. In Chapter 6, Rocha, Giorno, Lelio, and Theoto use a fuzzy automata model to describe neural networks and perform experiments in the acquisition and use of knowledge hy experts. This is an interesting attempt to shed light on some of the problems of knowledge engineering and presents a set of ideas concerning theoretic vs. expert knowledge.

Holdings
Item type	Current library	Call number	Copy number	Status	Date due	Barcode
Libro	CI Gustavo A. Madero 2	LCC	1	Available

TABLE OF CONTENTS

FUZZY EXPERT SYSTEMS THEORY

Chapter 1

The Evolution From Expert Systems to Fuzzy Expert Systems Lawrence O. Hall and Abraham Kandel

Chapter 2

General Purpose Fuzzy Expert Systems Mordechay Schneider and Abraham Kandel

Chapter 3

Inferences With Imprecisions and Uncertainities in Expert Systems Bernadette Bouchon-Meunier

Chapter 4

On the Representation of Relational Production Rules in Expert Systems Ronald R. Yager

Chapter 5

23

43

55

Reduction Procedures for Rule-based Expert Systems as a Tool for Studies of Properties of Expert's Knowledge Antonio Di Nola, Witold Pedrycz, and Salvatore Sessa

69

Chapter 6

The Physiology of the Expert System A. F. Rocha, F. Giorno, B. Leão and A. Theoto

81

Chapter 7

On the Processing of Im…
[APPLICATIONS OF FUZZY EXPERT SYSTEMS

Chapter 11

The Role of Approximate Reasoning in a Medical Expert System D. L. Hudson and M. E. Cohen

165

Chapter 12

Fess: A Reusable Fuzzy Expert System Lawrence O. Hall and Abraham Kandel

181

Chapter 13

Design for Designing: Fuzzy Relational Environmental Design Assistant (FREDA).... Vasco Mancini and Wyllis Bandler

195

Chapter 14

On the Design of a Fuzzy Intelligent Differential Equation Solver Menahem Friedman and Abraham Kandel

203

Chapter 15

MILORD: A Fuzzy Expert Systems Shell R. López de Mántaras, J. Agusti, E. Plaza, and C. Sierra

213

Chapter 16

Medical Decision Making Using Multidimensional Polynomials M. E. Cohen and D. L. Hudson

225

Chapter 17

Fuzzy Expert Systems for an Intelligent Computer-based Tutor Lois W. Hawkes, Sharon J. Derry, and Abraham Kandel 237

Chapter 18

Expert System on a Chip: An Engine for Approximate Reasoning Masaki Togai and Hiroyuki Watanabe

2.59

Chapter 19

A Probabilistic Logic for Expert Systems Arie Tzvieli

275

Chapter 20

COMEX - An Autonomous Fuzzy Expert System for Tactical Communications Networks Mordechay Schneider, Joseph M. Perl, and Abraham Kandel

PREFACE

This edited volume addresses the specific area of fuzzy expert systems and the choices knowledge engineers and expert systems designers must make to succeed in the field of artificial intelligence To a large extent the field of uncertainty managment, in general, and fuzzy set theory, in particular, is not driven just by an interest in exploring fuzziness and managing uncertainty in what appears to be a vague and imprecise environment, but also by a practical interest in producing better expert systems and knowledge-based systems. In this book we examine the choices within the context of specific and general purpose fuzzy expert systems.

In the first chapter Hall and Kandel identify the basic features of the evolution from expert systems to fuzzy expert systems, investigating the different choices provided by fuzziness. The choices here involve deciding how to handle fuzziness by both machines and humans and how to exploit fuzziness at each level of imprecision. Some of these features may not be visible to the user, but they largely determine the performance of a given expert system implementation. Their selection is based on expected performance benefits vs. the complexity associated with their inclusion. The method of handling imprecision in the system leads us through that evolution to fuzzy expert systems.

In Chapter 2, Schneider and Kandel illustrate the evolutionary process described earlier by discussing the design principles of a general purpose fuzzy expert system using fuzzy expected values and fuzzy expected intervals. It is also shown how to use them as an integral part of the fuzzy expert system.

Chapter 3. by Bouchon-Meunier, discusses inferences with inaccuracy and uncertainty in expert systems. This is the first step in the previously discussed evolution. The knowledge base of an expert system may contain uncertainties and inaccuracies. They are either as-sociated with the inference rules given by the experts or deduced from the observation of facts which do not fit exactly the conditions expressed in the premises of the rules A good

tool to cope with these problems is one of the fuzzy implications introduced in fuzzy logics. In this chapter Bouchon-Meunier indicates some reasons supporting the choice of these inferences and the corresponding combination operator.

The representation within the framework of approximate reasoning of relational type rules is illustrated by Yager in Chapter 4. A relational production rule consists of a rule in which one of the antecedent requirements involves the satisfaction of a relationship between two variables. This concept is used by Yager to represent his view of expert systems and the issues involved in some of their trade-offs.

Chapter 5, by Di Nola, Pedrycz, and Sessa, is devoted to the problem of reduction of the knowledge base in rule-based expert systems. The authors first point out that this problem is placed in the main stream of procedures of expert's knowledge (or its implementation) validation. Subsequently, some algorithms leading to its resolution are given in detail and their complementary character is also underlined. The entire analysis is performed treating the knowledge base in the form of a fuzzy relation, while an inference mechanism is given

by means of fuzzy relation equations. This chapter represents, like the previous chapters, important stages in the evolution of expert systems to fuzzy expert systems.

In Chapter 6, Rocha, Giorno, Lelio, and Theoto use a fuzzy automata model to describe neural networks and perform experiments in the acquisition and use of knowledge hy experts. This is an interesting attempt to shed light on some of the problems of knowledge engineering and presents a set of ideas concerning theoretic vs. expert knowledge.