Bøger i Studies in Fuzziness and Soft Computing serien

Fuzzy systems and soft computing are new computing techniques that are tolerant to imprecision, uncertainty and partial truths. Applications of these techniques in nuclear engineering present a tremendous challenge due to its strict nuclear safety regulation. The fields of nuclear engineering, fuzzy systems and soft computing have nevertheless matured considerably during the last decade. This book presents new application potentials for Fuzzy Systems and Soft Computing in Nuclear Engineering. The root of this book can be traced back to the series of the first, second and third international workshops on Fuzzy Logic and Intelligent Technologies in Nuclear Science (FUNS), which were successfully held in Mol, September 14-16, 1994 (FLINS'94), in Mol, September 25-27, 1996 (FLINS'96), and in Antwerp, September 14-16, 1998 (FLINS'98). The conferences were organised by the Belgian Nuclear Research Centre (SCKeCEN) and aimed at bringing together scientists, researchers, and engineers from academia and industry, at introducing the principles of fuzzy logic, neural networks, genetic algorithms and other soft computing methodologies, to the field of nuclear engineering, and at applying these techniques to complex problem­ solving within nuclear industry and related research fields. This book, as its title suggests, consists of nuclear engineering applications of fuzzy systems (Chapters 1-10) and soft computing (Chapters 11-21). Nine pertinent chapters are based on the extended version of papers at FLINS'98 and the other 12 chapters are original contributions with up-to-date coverage of fuzzy and soft computing applications by leading researchers written exclusively for this book.

The contributions to this book cover a wide range of applications of Soft Computing to the chemical domain. 'Soft Computing' itself became fully established about 10 years later, when the Berkeley Initiative in Soft Computing (SISC), an industrial liaison program, was put in place at the University of California - Berkeley.

This volume covers the fields of measurement and information acqulSltlon. Nowadays information acquisition should not only provide more information but also provide it in such a way as to assure effective and efficient processing of this information.

Soft computing has provided sophisticated methodologies for the development of intelligent decision support systems.

Formal Languages and Applications provides a comprehensive study-aid and self-tutorial for graduates students and researchers.

The field called Learning Classifier Systems is populated with romantics. John Holland was one of the earliest scientists with this vision, at a time when so-called artificial intelligence was in its infancy and mainly concerned with preprogrammed systems that didn't learn.

This book provides a new grade methodology for intelligent data analysis. This monograph is the only book presently available covering both the theory and application of grade data analysis and therefore aiming both at researchers, students, as well as applied practitioners.

The field of neural information processing has two main objects: investigation into the functioning of biological neural networks and use of artificial neural networks to sol ve real world problems. Hoshino and Zheng simulate a neural network of the auditory cortex to investigate neural basis for encoding and perception of vowel sounds.

Soft computing is playing an increasing role in the study of complex systems in science and engineering. It covers a range of core topics from software engineering that are soft from its very nature: selection of components, software design, software reuse, software cost estimation and software processes.

Geometric properties and relations play central roles in the description and processing of spatial data. The properties and relations studied by mathematicians usually have precise definitions, but verbal descriptions often involve imprecisely defined concepts such as elongatedness or proximity. The methods used in soft computing provide a framework for formulating and manipulating such concepts. This volume contains eight papers on the soft definition and manipulation of spatial relations and gives a comprehensive summary on the subject.

We describe in this book, new methods for intelligent manufacturing using soft computing techniques and fractal theory. Soft Computing (SC) consists of several computing paradigms, including fuzzy logic, neural networks, and genetic algorithms, which can be used to produce powerful hybrid intelligent systems. Fractal theory provides us with the mathematical tools to understand the geometrical complexity of natural objects and can be used for identification and modeling purposes. Combining SC techniques with fractal theory, we can take advantage of the "intelligence" provided by the computer methods and also take advantage of the descriptive power of the fractal mathematical tools. Industrial manufacturing systems can be considered as non-linear dynamical systems, and as a consequence can have highly complex dynamic behaviors. For this reason, the need for computational intelligence in these manufacturing systems has now been well recognized. We consider in this book the concept of "intelligent manufacturing" as the application of soft computing techniques and fractal theory for achieving the goals of manufacturing, which are production planning and control, monitoring and diagnosis of faults, and automated quality control. As a prelude, we provide a brief overview of the existing methodologies in Soft Computing. We then describe our own approach in dealing with the problems in achieving intelligent manufacturing. Our particular point of view is that to really achieve intelligent manufacturing in real-world applications we need to use SC techniques and fractal theory.

Fuzziology studies the fuzziness inherent in what we know about ourselves, the sources and nature of our experience, our thoughts and feelings, drives for understanding and urges to create and realise our potential. This kind of fuzziness is at the core of our existence, at the essence of our humanness. It affects any field of human activity, be it mathematical study of fuzzy equations and fuzzy integrals; engineering design and implementation of fuzzy logic-based methodologies; fuzzy control systems or fuzzy robots. Social fuzziology investigates the role of fuzziness in understanding the dynamic complexity of human existence in the social world. It is a study of the nexus between the complex demands of life -individual and social -and the fuzziness of thinking. Since human evolution over 2 billion years has seen the co-evolution of social complexity with human language and thought, it is likely that the fuzziness of language and thought is especially intimately formed by the demands of social complexity, just as social complexity is sustained by the inherent fuzziness of language and thought. Social fuzziology is not simply one field of application of fuzziology. Given the initial state of the development of fuzziology, social fuzziology needs to develop hand in hand with fuzziology, each helping to advance the other.

Many robotics researchers consider high-level vision algorithms (computational) too expensive for use in robot guidance. This book introduces the reader to an alternative approach to perception for autonomous, mobile robots. It explores how to apply methods of high-level computer vision and fuzzy logic to the guidance and control of the mobile robot. The book introduces a knowledge-based approach to vision modeling for robot guidance, where advantage is taken of constraints of the robot's physical structure, the tasks it performs, and the environments it works in. This facilitates high-level computer vision algorithms such as object recognition at a speed that is sufficient for real-time navigation. The texts presents algorithms that exploit these constraints at all levels of vision, from image processing to model construction and matching, as well as shape recovery. These algorithms are demonstrated in the navigation of a wheeled mobile robot.

1. The increasing number of research papers appeared in the last years that either make use of aggregation functions or contribute to its theoretieal study asses its growing importance in the field of Fuzzy Logie and in others where uncertainty and imprecision play a relevant role. Since these papers are pub­ lished in many journals, few books and several proceedings of conferences, books on aggregation are partieularly welcome. To my knowledge, "Agrega­ tion Operators. New Trends and Applications" is the first book aiming at generality , and I take it as a honour to write this Foreword in response to the gentle demand of its editors, Radko Mesiar, Tomasa Calvo and Gaspar Mayor. My pleasure also derives from the fact that twenty years aga I was one of the first Spaniards interested in the study of aggregation functions, and this book includes work by several Spanish authors. The book contains nice and relevant original papers, authored by some of the most outstanding researchers in the field, and since it can serve, as the editors point out in the Preface, as a small handbook on aggregation, the book is very useful for those entering the subject for the first time. The book also contains apart dealing with potential areas of application, so it can be helpful in gaining insight on the future developments.

Fact finding in judicial proceedings is a dynamic process. This collection of papers considers whether computational methods or other formal logical methods developed in disciplines such as artificial intelligence, decision theory, and probability theory can facilitate the study and management of dynamic evidentiary and inferential processes in litigation. The papers gathered here have several epicenters, including (i) the dynamics of judicial proof, (ii) the relationship between artificial intelligence or formal analysis and "common sense," (iii) the logic of factual inference, including (a) the relationship between causality and inference and (b) the relationship between language and factual inference, (iv) the logic of discovery, including the role of abduction and serendipity in the process of investigation and proof of factual matters, and (v) the relationship between decision and inference.

Traditional Artificial Intelligence (AI) systems adopted symbolic processing as their main paradigm. Symbolic AI systems have proved effective in handling problems characterized by exact and complete knowledge representation. Unfortunately, these systems have very little power in dealing with imprecise, uncertain and incomplete data and information which significantly contribute to the description of many real­ world problems, both physical systems and processes as well as mechanisms of decision making. Moreover, there are many situations where the expert domain knowledge (the basis for many symbolic AI systems) is not sufficient for the design of intelligent systems, due to incompleteness of the existing knowledge, problems caused by different biases of human experts, difficulties in forming rules, etc. In general, problem knowledge for solving a given problem can consist of an explicit knowledge (e.g., heuristic rules provided by a domain an implicit, hidden knowledge "buried" in past-experience expert) and numerical data. A study of huge amounts of these data (collected in databases) and the synthesizing of the knowledge "encoded" in them (also referred to as knowledge discovery in data or data mining), can significantly improve the performance of the intelligent systems designed.

Risk is a crucial element in virtually all problems people in diverse areas face in their activities. It is impossible to find adequate models and solutions without taking it into account. Due to uncertainty and complexity in those problems, traditional "hard" tools and techniques may be insufficient for their formulation and solution. This is the first book in the literature that shows how soft computing methods (fuzzy logic, neural networks, genetic algorithms, etc.) can be employed to deal with various problems related to risk analysis, evaluation and management in various fields of technology, environment and finance.

In the existing literature the intersection of agent technology with soft computing is a very recent and attractive issue. The book is devoted to a unifying perspective of this topic. In contains contributions by well-known authors whose expertise is universally recognized in these crossing areas. Particular emphasis is devoted to advanced research projects involved with Web-related technologies.Fundamental topics explored in this volume are: - formal theories and logics to represent and handle imprecise communication acts among communities of agents; - soft-computing approaches to define distributed problem-solving techniques to represent and reason about large-scale control systems; - decomposition of a complex system into autonomous or semiautonomous agents through evolutionary models; - enrichment of agent programming paradigm for cooperative soft-computing processing.

This book presents a unified view of modelling, simulation, and control of non­ linear dynamical systems using soft computing techniques and fractal theory. Our particular point of view is that modelling, simulation, and control are problems that cannot be considered apart, because they are intrinsically related in real world applications. Control of non-linear dynamical systems cannot be achieved if we don't have the appropriate model for the system. On the other hand, we know that complex non-linear dynamical systems can exhibit a wide range of dynamic behaviors ( ranging from simple periodic orbits to chaotic strange attractors), so the problem of simulation and behavior identification is a very important one. Also, we want to automate each of these tasks because in this way it is more easy to solve a particular problem. A real world problem may require that we use modelling, simulation, and control, to achieve the desired level of performance needed for the particular application.

Symbolic processing has limitations highlighted by the symbol grounding problem. Computational processing methods, like fuzzy logic, neural networks, and statistical methods have appeared to overcome these problems. However, they also suffer from drawbacks in that, for example, multi-stage inference is difficult to implement. Deep fusion of symbolic and computational processing is expected to open a new paradigm for intelligent systems. Symbolic processing and computational processing should interact at all abstract or computational levels. For this undertaking, attempts to combine, hybridize, and fuse these processing methods should be thoroughly investigated and the direction of novel fusion approaches should be clarified. This book contains the current status of this attempt and also discusses future directions.

Simultaneous considerations of multiobjectiveness, fuzziness and block angular structures involved in the real-world decision making problems lead us to the new field of interactive multiobjective optimization for large scale programming problems under fuzziness. The aim of this book is to introduce the latest advances in the new field of interactive multiobjective optimization for large scale programming problems under fuzziness on the basis of the author's continuing research. Special stress is placed on interactive decision making aspects of fuzzy multiobjective optimization for human-centered systems in most realistic situations when dealing with fuzziness. The book is intended for graduate students, researchers and practitioners in the fields of operations research, industrial engineering, management science and computer science.

Intelligence systems. We perfonn routine tasks on a daily basis, as for example: ¿ recognition of faces of persons (also faces not seen for many years), ¿ identification of dangerous situations during car driving, ¿ deciding to buy or sell stock, ¿ reading hand-written symbols, ¿ discriminating between vines made from Sauvignon Blanc, Syrah or Merlot grapes, and others. Human experts carry out the following: ¿ diagnosing diseases, ¿ localizing faults in electronic circuits, ¿ optimal moves in chess games. It is possible to design artificial systems to replace or "duplicate" the human expert. There are many possible definitions of intelligence systems. One of them is that: an intelligence system is a system able to make decisions that would be regarded as intelligent ifthey were observed in humans. Intelligence systems adapt themselves using some example situations (inputs of a system) and their correct decisions (system's output). The system after this learning phase can make decisions automatically for future situations. This system can also perfonn tasks difficult or impossible to do for humans, as for example: compression of signals and digital channel equalization.

Model-based fuzzy control uses a given conventional or a fuzzy open loop of the plant under control in order to derive the set of fuzzy if-then rules constituting the corresponding fuzzy controller. Furthermore, of central interest are the consequent stability, performance, and robustness analysis of the resulting closed loop system involving a conventional model and a fuzzy controller, or a fuzzy model and a fuzzy controller. The major objective of the model-based fuzzy control is to use the full available range of existing linear and nonlinear design of such fuzzy controllers which have better stability, performance, and robustness properties than the corresponding non-fuzzy controllers designed by the use of these same techniques.

These two volumes consIstmg of Foundations and Applications provide the current status of theoretical and empirical developments in "computing with words". In philosophy, the twentieth century is said to be the century of language. This is mainly due to Wittgenstein who said: "The meaning of a word is its use in the language game". "The concept game is a concept with blurred edges". In the first phrase, "the language game" implies the everyday human activity with language, and in the latter, "game" simply implies an ordinary word. Thus, Wittgenstein precisely stated that a word is fuzzy in real life. Unfortunately this idea about a word was not accepted in the conventional science. We had to wait for Zadeh's fuzzy sets theory. Remembering Wittgenstein's statement, we should consider, on the one hand, the concept of "computing with words" from a philosophical point of view. It deeply relates to the everyday use of a word in which the meaning of a word is fuzzy in its nature.

Research results using some of the most advanced soft computing techniques in intelligent robotic systems are presented. The main purpose of this book is to show how the power of soft computing techniques can be exploited in intelligent robotic systems. The main emphasis is on control system for a mobile robot, behavior arbitration for a mobile robot, reinforcement learning of a robot, manipulation of a robot, collision avoidance and automatic design of robots.This book will be useful for application engineers, scientists and researchers who wish to use some of the most advanced soft computing techniques in robotics.

Soft computing, as opposed to conventional "hard" computing, tolerates imprecision and uncertainty, in a way very much similar to the human mind. Part 1 of the book has seven chapters, demonstrating some of the capabilities of two major types of neural networks, i.e., multiplayer perceptron (MLP) neural networks and Hopfield-type neural networks.

The primary purpose of this book is to present information about selected topics on the interactions and applications of fuzzy + neural. Most of the discussion centers around our own research in these areas. Fuzzy + neural can mean many things: (1) approximations between fuzzy systems and neu­ ral nets (Chapter 4); (2) building hybrid neural nets to equal fuzzy systems (Chapter 5); (3) using neura.l nets to solve fuzzy problems (Chapter 6); (4) approximations between fuzzy neural nets and other fuzzy systems (Chap­ ter 8); (5) constructing hybrid fuzzy neural nets for certain fuzzy systems (Chapters 9, 10); or (6) computing with words (Chapter 11). This book is not intend to be used primarily as a text book for a course in fuzzy + neural because we have not included problems at the end of each chapter, we have omitted most proofs (given in the references), and we have given very few references. We wanted to keep the mathematical prerequisites to a minimum so all longer, involved, proofs were omitted. Elementary dif­ ferential calculus is the only prerequisite needed since we do mention partial derivatives once or twice.

This book presents the main tools for aggregation of information given by several members of a group or expressed in multiple criteria, and for fusion of data provided by several sources. It focuses on the case where the availability knowledge is imperfect, which means that uncertainty and/or imprecision must be taken into account. The book contains both theoretical and applied studies of aggregation and fusion methods in the main frameworks: probability theory, evidence theory, fuzzy set and possibility theory. The latter is more developed because it allows to manage both imprecise and uncertain knowledge. Applications to decision-making, image processing, control and classification are described.

In Part I, the impact of an integro-differential operator on parity logic engines (PLEs) as a tool for scientific modeling from scratch is presented. Part II outlines the fuzzy structural modeling approach for building new linear and nonlinear dynamical causal forecasting systems in terms of fuzzy cognitive maps (FCMs). Part III introduces the new type of autogenetic algorithms (AGAs) to the field of evolutionary computing. Altogether, these PLEs, FCMs, and AGAs may serve as conceptual and computational power tools.

Some recent fuzzy database modeling advances for the non-traditional applications are introduced in this book. The focus is on database models for modeling complex information and uncertainty at the conceptual, logical, physical design levels and from integrity constraints defined on the fuzzy relations. The database models addressed here are; the conceptual data models, including the ExIFO and ExIFO2 data models, the logical database models, including the extended NF2 database model, fuzzy object-oriented database model, and the fuzzy deductive object-oriented database model. Integrity constraints are defined on the fuzzy relations are also addressed. A continuing reason for the limited adoption of fuzzy database systems has been performance. There have been few efforts at defining physical structures that accomodate fuzzy information. A new access structure and data organization for fuzzy information is introduced in this book.