The objective of this book is two-fold. Firstly, it is aimed at bringing to gether key research articles concerned with methodologies for knowledge discovery in databases and their applications. Secondly, it also contains articles discussing fundamentals of rough sets and their relationship to fuzzy sets, machine learning, management of uncertainty and systems of logic for formal reasoning about knowledge. Applications of rough sets in different areas such as medicine, logic design, image processing and expert systems are also represented. The articles included in the book are based on selected papers presented at the International Workshop on Rough Sets and Knowledge Discovery held in Banff, Canada in 1993. The primary methodological approach emphasized in the book is the mathematical theory of rough sets, a relatively new branch of mathematics concerned with the modeling and analysis of classification problems with imprecise, uncertain, or incomplete information. The methods of the theory of rough sets have applications in many sub-areas of artificial intelligence including knowledge discovery, machine learning, formal reasoning in the presence of uncertainty, knowledge acquisition, and others. This spectrum of applications is reflected in this book where articles, although centered around knowledge discovery problems, touch a number of related issues. The book is intended to provide an important reference material for students, researchers, and developers working in the areas of knowledge discovery, machine learning, reasoning with uncertainty, adaptive expert systems, and pattern classification.

The papers on rough set theory and its applications placed in this volume present a wide spectrum of problems representative to the present. stage of this theory. Researchers from many countries reveal their rec.ent results on various aspects of rough sets. The papers are not confined only to mathematical theory but also include algorithmic aspects, applications and information about software designed for data analysis based on this theory. The volume contains also list of selected publications on rough sets which can be very useful to every one engaged in research or applications in this domain and sometimes perhaps unaware of results of other authors. The book shows that rough set theory is a vivid and vigorous domain with serious results to its credit and bright perspective for future developments. It lays on the crossroads of fuzzy sets, theory of evidence, neural networks, Petri nets and many other branches of AI, logic and mathematics. These diverse connec tions seem to be a very fertile feature of rough set theory and have essentially contributed to its wide and rapid expansion. It is worth mentioning that its philosophical roots stretch down from Leibniz, Frege and Russell up to Popper. Therefore many concepts dwelled on in rough set theory are not entirely new, nevertheless the theory can be viewed as an independent discipline on its own rights. Rough set theory has found many interesting real life applications in medicine, banking, industry and others.

The ideas and techniques worked out in Rough Set Theory allow for knowledge reduction and to finding near - to - functional dependencies in data. This fact determines the importance of these techniques for the rapidly growing field of knowledge discovery. Volume 1 and 2 will bring together articles covering the present state of the methods developed in this field of research. Among the topics covered we may mention: rough mereology and rough mereological approach to knowledge discovery in distributed systems; discretization and quantization of attributes; morphological aspects of rough set theory; analysis of default rules in the framework of rough set theory.

Rough set approach to reasoning under uncertainty is based on inducing knowledge representation from data under constraints expressed by discernibility or, more generally, similarity of objects. Knowledge derived by this approach consists of reducts, decision or association rules, dependencies, templates, or classifiers. This monograph presents the state of the art of this area. The reader will find here a deep theoretical discussion of relevant notions and ideas as well as rich inventory of algorithmic and heuristic tools for knowledge discovery by rough set methods. An extensive bibliography will help the reader to get an acquaintance with this rapidly growing area of research.

The ideas and techniques worked out in Rough Set Theory allow for knowledge reduction and to finding near - to - functional dependencies in data. This fact determines the importance of these techniques for the rapidly growing field of knowledge discovery. Volume 1 and 2 will bring together articles covering the present state of the methods developed in this field of research. Among the topics covered we may mention: rough mereology and rough mereological approach to knowledge discovery in distributed systems; discretization and quantization of attributes; morphological aspects of rough set theory; analysis of default rules in the framework of rough set theory.

The LNCS journal Transactions on Rough Sets is devoted to the entire spectrum of rough sets related issues, starting from logical and mathematical foundations, through all aspects of rough set theory and its applications, such as data mining, knowledge discovery, and intelligent information processing, to relations between rough sets and other approaches to uncertainty, vagueness and incompleteness, such as fuzzy sets and theory of evidence. This second volume of the Transactions on Rough Sets presents 17 thoroughly reviewed revised papers devoted to rough set theory, fuzzy set theory; these papers highlight important aspects of these theories, their interrelation and application in various fields.

This book covers methods based on a combination of granular computing, rough sets, and knowledge discovery in data mining (KDD). The discussion of KDD foundations based on the rough set approach and granular computing feature illustrative applications.