Soft Computing

This book is a tribute to Lotfi A. Zadeh, the father of fuzzy logic, on the occasion of his 90th Birthday. The book gathers original scientific contributions written by top scientists and presenting the latest theories, applications and new trends in the fascinating and challenging field of soft computing.

This textbook provides a thorough introduction to the field of learning from experimental data and soft computing. Support vector machines (SVM) and neural networks (NN) are the mathematical structures, or models, that underlie learning, while fuzzy logic systems (FLS) enable us to embed structured human knowledge into workable algorithms. The book assumes that it is not only useful, but necessary, to treat SVM, NN, and FLS as parts of a connected whole. Throughout, the theory and algorithms are illustrated by practical examples, as well as by problem sets and simulated experiments. This approach enables the reader to develop SVM, NN, and FLS in addition to understanding them. The book also presents three case studies: on NN-based control, financial time series analysis, and computer graphics. A solutions manual and all of the MATLAB programs needed for the simulated experiments are available.

Neuro-Fuzzy and Soft Computing provides the first comprehensive treatment of the constituent methodologies underlying neuro-fuzzy and soft computing, an evolving branch of computational intelligence. The constituent methodologies include fuzzy set theory, neural networks, data clustering techniques, and several stochastic optimization methods that do not require gradient information. In particular, the authors put equal emphasis on theoretical aspects of covered methodologies, as well as empirical observations and verifications of various applications in practice. The book is well suited for use as a text for courses on computational intelligence and as a single reference source for this emerging field. To help readers understand the material the presentation includes more than 50 examples, more than 150 exercises, over 300 illustrations, and more than 150 Matlab scripts. In addition, Matlab is utilized to visualize the processes of fuzzy reasoning, neural-network learning, neuro-fuzzy integration and training, and gradient-free optimization (such as genetic algorithms, simulated annealing, random search, and downhill Simplex method). The presentation also makes use of SIMULINK for neuro-fuzzy control system simulations. All Matlab scripts used in the book are available on the free companion software disk that may be ordered by using the enclosed reply card. The book also contains an "Internet Resource Page" to point the reader to on-line neuro-fuzzy and soft computing home pages, publications, public-domain software, research institutes, news groups, etc. All the HTTP and FTP addresses are available as a bookmark file on the companion software disk.

An in-depth look at soft computing methods and their applications in the human sciences, such as the social and the behavioral sciences. Soft computing methods - including fuzzy systems, neural networks, evolutionary computing and probabilistic reasoning - are state-of-the-art methods in theory formation and model construction. The powerful application areas of these methods in the human sciences are demonstrated, including the replacement of statistical models by simpler numerical or linguistic soft computing models and the use of computer simulations with approximate and linguistic constituents. "Dr. Niskanen's work opens new vistas in application of soft computing, fuzzy logic and fuzzy set theory to the human sciences. This book is likely to be viewed in retrospect as a landmark in its field" (Lotfi A. Zadeh, Berkeley)

Soft computing embraces various methodologies for the development of intelligent systems that have been successfully applied to a large number of real-world problems. Soft Computing in Industry contains a collection of papers that were presented at the 6th On-line World Conference on Soft Computing in Industrial Applications that was held in September 2001. It provides a comprehensive overview of recent theoretical developments in soft computing as well as of successful industrial applications. It is divided into seven parts covering material on: keynote papers on various subjects ranging from computing with autopoietic systems to the effects of the Internet on education; intelligent control; classification, clustering and optimization; image and signal processing; agents, multimedia and Internet; theoretical advances; prediction, design and diagnosis. The book is aimed at researchers and professional engineers who develop and apply intelligent systems in computer engineering.

This new volume explores a variety of modern techniques that deal with estimated models and give resolutions to complex real-life issues. Soft computing has played a crucial role not only with theoretical paradigms but is also popular for its pivotal role for designing a large variety of expert systems and artificial intelligence-based applications. Involving the concepts and practices of soft computing in conjunction with other frontier research domains, this book begins with the basics and goes on to explore a variety of modern applications of soft computing in areas such as approximate reasoning, artificial neural networks, Bayesian networks, big data analytics, bioinformatics, cloud computing, control systems, data mining, functional approximation, fuzzy logic, genetic and evolutionary algorithms, hybrid models, machine learning, metaheuristics, neuro fuzzy system, optimization, randomized searches, and swarm intelligence. This book will be helpful to a wide range of readers who wish to learn applications of soft computing approaches. It will be useful for academicians, researchers, students, and machine learning experts who use soft computing techniques and algorithms to develop cutting-edge artificial intelligence-based applications.

Traditional artificial intelligence (AI) techniques are based around mathematical techniques of symbolic logic, with programming in languages such as Prolog and LISP invented in the 1960s. These are referred to as "crisp" techniques by the soft computing community. The new wave of AI methods seeks inspiration from the world of biology, and is being used to create numerous real-world intelligent systems with the aid of soft computing tools. These new methods are being increasingly taught at the upper end of the curriculum, sometimes as an adjunct to traditional AI courses, and sometimes as a replacement for them. Where a more radical approach is taken and the course is being taught at an introductory level, we have recently published Negnevitsky's book. Karray and Silva will be suitable for the majority of courses which will be found at an advanced level. Karray and de Silva cover the problem of control and intelligent systems design using soft-computing techniques in an integrated manner. They present both theory and applications, including industrial applications, and the book contains numerous worked examples, problems and case studies. Covering the state-of-the-art in soft-computing techniques, the book gives the reader sufficient knowledge to tackle a wide range of complex systems for which traditional techniques are inadequate.

Science has made great progress in the twentieth century, with the establishment of proper disciplines in the fields of physics, computer science, molecular biology, and many others. At the same time, there have also emerged many engineering ideas that are interdisciplinary in nature, beyond the realm of such orthodox disciplines. These in clude, for example, artificial intelligence, fuzzy logic, artificial neural networks, evolutional computation, data mining, and so on. In or der to generate new technology that is truly human-friendly in the twenty-first century, integration of various methods beyond specific disciplines is required. Soft computing is a key concept for the creation of such human friendly technology in our modern information society. Professor Rutkowski is a pioneer in this field, having devoted himself for many years to publishing a large variety of original work. The present vol ume, based mostly on his own work, is a milestone in the devel opment of soft computing, integrating various disciplines from the fields of information science and engineering. The book consists of three parts, the first of which is devoted to probabilistic neural net works. Neural excitation is stochastic, so it is natural to investi gate the Bayesian properties of connectionist structures developed by Professor Rutkowski. This new approach has proven to be par ticularly useful for handling regression and classification problems vi Preface in time-varying environments. Throughout this book, major themes are selected from theoretical subjects that are tightly connected with challenging applications.