Witold Pedrycz Livres

Data Mining Methods for Knowledge Discovery provides an introduction to the data mining methods that are frequently used in the process of knowledge discovery. This book first elaborates on the fundamentals of each of the data mining rough sets, Bayesian analysis, fuzzy sets, genetic algorithms, machine learning, neural networks, and preprocessing techniques. The book then goes on to thoroughly discuss these methods in the setting of the overall process of knowledge discovery. Numerous illustrative examples and experimental findings are also included. Each chapter comes with an extensive bibliography.Data Mining Methods for Knowledge Discovery is intended for senior undergraduate and graduate students, as well as a broad audience of professionals in computer and information sciences, medical informatics, and business information systems.

This book presents a wealth of deep-learning algorithms and demonstrates their design process. It also highlights the need for a prudent alignment with the essential characteristics of the nature of learning encountered in the practical problems being tackled. Intended for readers interested in acquiring practical knowledge of analysis, design, and deployment of deep learning solutions to real-world problems, it covers a wide range of the paradigm’s algorithms and their applications in diverse areas including imaging, seismic tomography, smart grids, surveillance and security, and health care, among others. Featuring systematic and comprehensive discussions on the development processes, their evaluation, and relevance, the book offers insights into fundamental design strategies for algorithms of deep learning.

Focusing on the fundamentals and technology of fuzzy sets, this book offers a clear introduction to key concepts such as information granules and their processing. It covers recent advances in fuzzy modeling, neurocomputing, and higher-order fuzzy sets, enriched with examples, case studies, and problems linked to artificial intelligence. The balanced approach between theory and application makes it suitable for both academic and industrial audiences, as well as an ideal textbook for graduate and undergraduate students in relevant fields.

Temporal and spatiotemporal data form an inherent fabric of the society as we are faced with streams of data coming from numerous sensors, data feeds, recordings associated with numerous areas of application embracing physical and human-generated phenomena (environmental data, financial markets, Internet activities, etc.).

“Fuzziness”—represented through information granules and fuzzy sets—is a key characteristic of human cognition and our understanding of reality. Fuzzy phenomena are prevalent in nature and society. The concept of fuzzy sets was introduced by L. A. Zadeh in 1965 to formalize human concepts and facilitate the representation of natural language and reasoning with words. Fuzzy sets and fuzzy logic enable modeling of imprecise reasoning, which is crucial for human decision-making in uncertain environments. The rise of fuzzy set applications stems from an “empirical-semantic” approach, emphasizing practical interpretations over the mathematical structures of fuzzy sets. For example, in control theory, fuzzy sets have demonstrated significant practical relevance. While fuzzy sets can be viewed as abstract concepts with formal foundations, their operational meaning varies across different contexts. This variability highlights the importance of understanding how membership functions operate in various applications, underlining the need for a nuanced approach to fuzzy sets in practice.

Granular Computing is concerned with constructing and processing carried out at the level of information granules. Using information granules, we comprehend the world and interact with it, no matter which intelligent endeavor this may involve. The landscape of granular computing is immensely rich and involves set theory (interval mathematics), fuzzy sets, rough sets, random sets linked together in a highly synergetic environment. This volume is a first comprehensive treatment of this emerging paradigm and embraces its fundamentals, underlying methodological framework, and a sound algorithmic environment. The panoply of applications covered includes system identification, telecommunications, linguistics and music processing. Written by experts in the field, this volume will appeal to all developing intelligent systems, either working at the methodological level or interested in detailed system realization.