Provides an up-to-date integration of expert systems with fuzzy logic and neural networks. Includes coverage of simulation models not present in other books. Presents cases and examples taken from the authors' experience in research and applying the technology to real-world situations.
This volume covers the integration of fuzzy logic and expert systems. A vital resource in the field, it includes techniques for applying fuzzy systems to neural networks for modeling and control, systematic design procedures for realizing fuzzy neural systems, techniques for the design of rule-based expert systems using the massively parallel processing capabilities of neural networks, the transformation of neural systems into rule-based expert systems, the characteristics and relative merits of integrating fuzzy sets, neural networks, genetic algorithms, and rough sets, and applications to system identification and control as well as nonparametric, nonlinear estimation. Practitioners, researchers, and students in industrial, manufacturing, electrical, and mechanical engineering, as well as computer scientists and engineers will appreciate this reference source to diverse application methodologies. - Fuzzy system techniques applied to neural networks for modeling and control - Systematic design procedures for realizing fuzzy neural systems - Techniques for the design of rule-based expert systems - Characteristics and relative merits of integrating fuzzy sets, neural networks, genetic algorithms, and rough sets - System identification and control - Nonparametric, nonlinear estimation Practitioners, researchers, and students in industrial, manufacturing, electrical, and mechanical engineering, as well as computer scientists and engineers will find this volume a unique and comprehensive reference to these diverse application methodologies
Combines the study of neural networks and fuzzy systems with symbolic artificial intelligence (AI) methods to build comprehensive AI systems. Describes major AI problems (pattern recognition, speech recognition, prediction, decision-making, game-playing) and provides illustrative examples. Includes applications in engineering, business and finance.
Artificial neural networks can mimic the biological information-processing mechanism in - a very limited sense. Fuzzy logic provides a basis for representing uncertain and imprecise knowledge and forms a basis for human reasoning. Neural networks display genuine promise in solving problems, but a definitive theoretical basis does not yet exist for their design. Fusion of Neural Networks, Fuzzy Systems and Genetic Algorithms integrates neural net, fuzzy system, and evolutionary computing in system design that enables its readers to handle complexity - offsetting the demerits of one paradigm by the merits of another. This book presents specific projects where fusion techniques have been applied. The chapters start with the design of a new fuzzy-neural controller. Remaining chapters discuss the application of expert systems, neural networks, fuzzy control, and evolutionary computing techniques in modern engineering systems. These specific applications include: direct frequency converters electro-hydraulic systems motor control toaster control speech recognition vehicle routing fault diagnosis Asynchronous Transfer Mode (ATM) communications networks telephones for hard-of-hearing people control of gas turbine aero-engines telecommunications systems design Fusion of Neural Networks, Fuzzy Systems and Genetic Algorithms covers the spectrum of applications - comprehensively demonstrating the advantages of fusion techniques in industrial applications.
This book is designed to identify some of the current applications and techniques of artificial intelligence as an aid to solving problems and accomplishing tasks. It provides a general introduction to the various branches of AI which include formal logic, reasoning, knowledge engineering, expert systems, neural networks, and fuzzy logic, etc. The book has been structured into five parts with an emphasis on expert systems: problems and state space search, knowledge engineering, neural networks, fuzzy logic, and Prolog. Features: Introduces the various branches of AI which include formal logic, reasoning, knowledge engineering, expert systems, neural networks, and fuzzy logic, etc. Includes a separate chapter on Prolog to introduce basic programming techniques in AI
Neural networks and fuzzy systems represent two distinct technologies that deal with uncertainty. This definitive book presents the fundamentals of both technologies, and demonstrates how to combine the unique capabilities of these two technologies for the greatest advantage. Steering clear of unnecessary mathematics, the book highlights a wide range of dynamic possibilities and offers numerous examples to illuminate key concepts. It also explores the value of relating genetic algorithms and expert systems to fuzzy and neural technologies.
Until recently, fuzzy logic was the intellectual plaything of a handful of researchers. Now it is being used to enhance the power of intelligent systems, as well as improve the performance and reduce the cost of intelligent and "smart" products appearing in the commercial market. Fuzzy Expert Systems focuses primarily on the theory of fuzzy expert systems and their applications in science and engineering. In doing so, it provides the first comprehensive study of "soft" expert systems and applications for those systems. Topics covered include general purpose fuzzy expert systems, processing imperfect information using structured frameworks, the fuzzy linguistic inference network generator, fuzzy associative memories, the role of approximate reasoning in medical expert systems, MILORD (a fuzzy expert systems shell), and COMAX (an autonomous fuzzy expert system for tactical communications networks. Fuzzy Expert Systems provides an invaluable reference resource for researchers and students in artificial intelligence (AI) and approximate reasoning (AR), as well as for other researchers looking for methods to apply similar tools in their own designs of intelligent systems.
There are many uncertainties in the real world. Fuzzy theory treats a kind of uncertainty called fuzziness, where it shows that the boundary of yes or no is ambiguous and appears in the meaning of words or is included in the subjunctives or recognition of human beings. Fuzzy theory is essential and is applicable to many systems -- from consumer products like washing machines or refrigerators to big systems like trains or subways. Recently, fuzzy theory has been a strong tool for combining new theories (called soft computing) such as genetic algorithms or neural networks to get knowledge from real data. This introductory book enables the reader to understand easily what fuzziness is and how one can apply fuzzy theory to real problems -- which explains why it was a best-seller in Japan.
The introduction of artificial intelligence, neural networks, and fuzzy logic into industry has given a new perspective to manufacturing processes in the U.S. and abroad. To help readers keep pace, this book addresses topics of intelligent manufacturing from a variety of theoretical, empirical, design, and implementation perspectives.