The recent interest in artificial neural networks has motivated the publication of numerous books, including selections of research papers and textbooks presenting the most popular neural architectures and learning schemes. Artificial Neural Networks: Learning Algorithms, Performance Evaluation, and Applications presents recent developments which can have a very significant impact on neural network research, in addition to the selective review of the existing vast literature on artificial neural networks. This book can be read in different ways, depending on the background, the specialization, and the ultimate goals of the reader. A specialist will find in this book well-defined and easily reproducible algorithms, along with the performance evaluation of various neural network architectures and training schemes. Artificial Neural Networks can also help a beginner interested in the development of neural network systems to build the necessary background in an organized and comprehensive way. The presentation of the material in this book is based on the belief that the successful application of neural networks to real-world problems depends strongly on the knowledge of their learning properties and performance. Neural networks are introduced as trainable devices which have the unique ability to generalize. The pioneering work on neural networks which appeared during the past decades is presented, together with the current developments in the field, through a comprehensive and unified review of the most popular neural network architectures and learning schemes. Efficient LEarning Algorithms for Neural NEtworks (ELEANNE), which can achieve much faster convergence than existing learningalgorithms, are among the recent developments explored in this book. A new generalized criterion for the training of neural networks is presented, which leads to a variety of fast learning algorithms. Finally, Artificial Neural Networks presents the development of learning algorithms which determine the minimal architecture of multi-layered neural networks while performing their training. Artificial Neural Networks is a valuable source of information to all researchers and engineers interested in neural networks. The book may also be used as a text for an advanced course on the subject.

The function of a filter is to transform a signal into another one more suit able for a given purpose. As such, filters find applications in telecommunica tions, radar, sonar, remote sensing, geophysical signal processing, image pro cessing, and computer vision. Numerous authors have considered deterministic and statistical approaches for the study of passive, active, digital, multidimen sional, and adaptive filters. Most of the filters considered were linear although the theory of nonlinear filters is developing rapidly, as it is evident by the numerous research papers and a few specialized monographs now available. Our research interests in this area created opportunity for cooperation and co authored publications during the past few years in many nonlinear filter families described in this book. As a result of this cooperation and a visit from John Pitas on a research leave at the University of Toronto in September 1988, the idea for this book was first conceived. The difficulty in writing such a mono graph was that the area seemed fragmented and no general theory was available to encompass the many different kinds of filters presented in the literature. However, the similarities of some families of nonlinear filters and the need for such a monograph providing a broad overview of the whole area made the pro ject worthwhile. The result is the book now in your hands, typeset at the Department of Electrical Engineering of the University of Toronto during the summer of 1989."

This book is devoted to the study of fuzzy reasoning as applied to decision making and control processes. It contains a collection of important contributions covering a wide well-selected range of topics within the field. The book contains twenty-one papers, written by thirty-four distinguished contributors and is divided into five parts. Part 1 involves four chapters providing background material together with useful techniques for the validation of fuzzy knowledge bases and the software representation of fuzzy sets and fuzzy logic. Part 2 presents an overview of neuro-fuzzy expert systems along with an important case study, and a neural network model which is suitable for fuzzy reasoning. Part 3 presents the state of art of fuzzy controllers, including design and implementation aspects. This part starts with a chapter on the demystification of fuzzy control and includes critical evaluations of fuzzy controllers, along with new types of fuzzy controllers such as the sliding mode fuzzy controller. Part 4 involves a chapter on fuzzy parameter and state estimation, which is of fundamental importance in a variety of applications, a chapter on fuzzy reasoning as used in rule-based systems, and a chapter on computing the multivariable shape of an n-D pattern class. Finally, Part 5 presents six important applications dealing with industrial robotic systems, mechanical systems, manipulators with artificial rubber muscles, Petri nets, biomedical engineering, and nondestructive fruit collection. The book is suitable for the researcher and practitioner, as well as for the teacher and student in related Master and Doctoral courses.

Color Image Processing: Methods and Applications embraces two decades of extraordinary growth in the technologies and applications for color image processing. The book offers comprehensive coverage of state-of-the-art systems, processing techniques, and emerging applications of digital color imaging. To elucidate the significant progress in specialized areas, the editors invited renowned authorities to address specific research challenges and recent trends in their area of expertise. The book begins by focusing on color fundamentals, including color management, gamut mapping, and color constancy. The remaining chapters detail the latest techniques and approaches to contemporary and traditional color image processing and analysis for a broad spectrum of sophisticated applications, including: Vector and semantic processing Secure imaging Object recognition and feature detection Facial and retinal image analysis Digital camera image processing Spectral and superresolution imaging Image and video colorization Virtual restoration of artwork Video shot segmentation and surveillance Color Image Processing: Methods and Applications is a versatile resource that can be used as a graduate textbook or as stand-alone reference for the design and the implementation of various image and video processing tasks for cutting-edge applications. This book is part of the Digital Imaging and Computer Vision series.

Describing the relevant detection and estimation theory, this detailed guide provides the background knowledge needed to tackle the design of practical WLAN positioning systems. It sets out key system-level challenges and design considerations in increasing positioning accuracy and reducing computational complexity, and it also examines design trade-offs and experimental results. Radio characteristics in real environments are discussed, as are the theoretical aspects of non-parametric statistical tools appropriate for modeling radio signals, statistical estimation techniques and the model-based stochastic estimators often used for positioning. A historical account of positioning systems in also included, giving graduate students, researchers and practitioners alike the perspective needed to understand the benefits and potential applications of WLAN positioning.

Great progresses have been made in the application of fuzzy set theory and fuzzy logic. Most remarkable area of application is 'fuzzy control', where fuzzy logic was first applied to plant control systems and its use is expanding to consumer products. Most of fuzzy control systems uses fuzzy inference with max-min or max-product composition, similar to the algorithm that first used by Mamdani in 1970s. Some algorithms are developed to refine fuzzy controls systems but the main part of algorithm stays the same. Triggered by the success of fuzzy control systems, other ways of applying fuzzy set theory are also investigated. They are usually referred to as 'fuzzy expert sys tems', and their purpose are to combine the idea of fuzzy theory with AI based approach toward knowledge processing. These approaches can be more generally viewed as 'fuzzy information processing', that is to bring fuzzy idea into informa tion processing systems."

1.1 Overview We are living in a decade recently declared as the "Decade of the Brain." Neuroscientists may soon manage to work out a functional map of the brain, thanks to technologies that open windows on the mind. With the average human brain consisting of 15 billion neurons, roughly equal to the number of stars in our milky way, each receiving signals through as many as 10,000 synapses, it is quite a view. "The brain is the last and greatest biological frontier," says James Weston codiscoverer of DNA, considered to be the most complex piece of biological machinery on earth. After many years of research by neuroanatomists and neurophys iologists, the overall organization of the brain is well understood, but many of its detailed neural mechanisms remain to be decoded. In order to understand the functioning of the brain, neurobiologists have taken a bottom-up approach of studying the stimulus-response characteristics of single neurons and networks of neurons, while psy chologists have taken a top-down approach of studying brain func tions from the cognitive and behavioral level. While these two ap proaches are gradually converging, it is generally accepted that it may take another fifty years before we achieve a solid microscopic, intermediate, and macroscopic understanding of brain."

The function of a filter is to transform a signal into another one more suit able for a given purpose. As such, filters find applications in telecommunica tions, radar, sonar, remote sensing, geophysical signal processing, image pro cessing, and computer vision. Numerous authors have considered deterministic and statistical approaches for the study of passive, active, digital, multidimen sional, and adaptive filters. Most of the filters considered were linear although the theory of nonlinear filters is developing rapidly, as it is evident by the numerous research papers and a few specialized monographs now available. Our research interests in this area created opportunity for cooperation and co authored publications during the past few years in many nonlinear filter families described in this book. As a result of this cooperation and a visit from John Pitas on a research leave at the University of Toronto in September 1988, the idea for this book was first conceived. The difficulty in writing such a mono graph was that the area seemed fragmented and no general theory was available to encompass the many different kinds of filters presented in the literature. However, the similarities of some families of nonlinear filters and the need for such a monograph providing a broad overview of the whole area made the pro ject worthwhile. The result is the book now in your hands, typeset at the Department of Electrical Engineering of the University of Toronto during the summer of 1989."