Soft Computing For Knowledge Discovery And Data Mining

Data Mining is the science and technology of exploring large and complex bodies of data in order to discover useful patterns. It is extremely important because it enables modeling and knowledge extraction from abundant data availability. This book introduces soft computing methods extending the envelope of problems that data mining can solve efficiently. It presents practical soft-computing approaches in data mining and includes various real-world case studies with detailed results.

"Foundations of Data Mining and Knowledge Discovery" contains the latest results and new directions in data mining research. Data mining, which integrates various technologies, including computational intelligence, database and knowledge management, machine learning, soft computing, and statistics, is one of the fastest growing fields in computer science. Although many data mining techniques have been developed, further development of the field requires a close examination of its foundations. This volume presents the results of investigations into the foundations of the discipline, and represents the state of the art for much of the current research. This book will prove extremely valuable and fruitful for data mining researchers, no matter whether they would like to uncover the fundamental principles behind data mining, or apply the theories to practical applications.

The volume includes a set of selected papers extended and revised from the 4th International conference on Knowledge Discovery and Data Mining, March 1-2, 2011, Macau, Chin. This Volume is to provide a forum for researchers, educators, engineers, and government officials involved in the general areas of knowledge discovery and data mining and learning to disseminate their latest research results and exchange views on the future research directions of these fields. 108 high-quality papers are included in the volume.

Many business decisions are made in the absence of complete information about the decision consequences. Credit lines are approved without knowing the future behavior of the customers; stocks are bought and sold without knowing their future prices; parts are manufactured without knowing all the factors affecting their final quality; etc. All these cases can be categorized as decision making under uncertainty. Decision makers (human or automated) can handle uncertainty in different ways. Deferring the decision due to the lack of sufficient information may not be an option, especially in real-time systems. Sometimes expert rules, based on experience and intuition, are used. Decision tree is a popular form of representing a set of mutually exclusive rules. An example of a two-branch tree is: if a credit applicant is a student, approve; otherwise, decline. Expert rules are usually based on some hidden assumptions, which are trying to predict the decision consequences. A hidden assumption of the last rule set is: a student will be a profitable customer. Since the direct predictions of the future may not be accurate, a decision maker can consider using some information from the past. The idea is to utilize the potential similarity between the patterns of the past (e.g., "most students used to be profitable") and the patterns of the future (e.g., "students will be profitable").

The authors have consolidated their research work in this volume titled Soft Computing for Data Mining Applications. The monograph gives an insight into the research in the ?elds of Data Mining in combination with Soft Computing methodologies. In these days, the data continues to grow - ponentially. Much of the data is implicitly or explicitly imprecise. Database discovery seeks to discover noteworthy, unrecognized associations between the data items in the existing database. The potential of discovery comes from the realization that alternate contexts may reveal additional valuable information. The rate at which the data is storedis growing at a phenomenal rate. Asaresult,traditionaladhocmixturesofstatisticaltechniquesanddata managementtools are no longer adequate for analyzing this vast collection of data. Severaldomainswherelargevolumesofdataarestoredincentralizedor distributeddatabasesincludesapplicationslikeinelectroniccommerce,bio- formatics, computer security, Web intelligence, intelligent learning database systems,?nance,marketing,healthcare,telecommunications,andother?elds. E?cient tools and algorithms for knowledge discovery in large data sets have been devised during the recent years. These methods exploit the ca- bility of computers to search huge amounts of data in a fast and e?ective manner. However,the data to be analyzed is imprecise and a?icted with - certainty. In the case of heterogeneous data sources such as text and video, the data might moreover be ambiguous and partly con?icting. Besides, p- terns and relationships of interest are usually approximate. Thus, in order to make the information mining process more robust it requires tolerance toward imprecision, uncertainty and exceptions.

Knowledge discovery is an area of computer science that attempts to uncover interesting and useful patterns in data that permit a computer to perform a task autonomously or assist a human in performing a task more efficiently. Soft Computing for Knowledge Discovery provides a self-contained and systematic exposition of the key theory and algorithms that form the core of knowledge discovery from a soft computing perspective. It focuses on knowledge representation, machine learning, and the key methodologies that make up the fabric of soft computing - fuzzy set theory, fuzzy logic, evolutionary computing, and various theories of probability (e.g. naïve Bayes and Bayesian networks, Dempster-Shafer theory, mass assignment theory, and others). In addition to describing many state-of-the-art soft computing approaches to knowledge discovery, the author introduces Cartesian granule features and their corresponding learning algorithms as an intuitive approach to knowledge discovery. This new approach embraces the synergistic spirit of soft computing and exploits uncertainty in order to achieve tractability, transparency and generalization. Parallels are drawn between this approach and other well known approaches (such as naive Bayes and decision trees) leading to equivalences under certain conditions. The approaches presented are further illustrated in a battery of both artificial and real-world problems. Knowledge discovery in real-world problems, such as object recognition in outdoor scenes, medical diagnosis and control, is described in detail. These case studies provide further examples of how to apply the presented concepts and algorithms to practical problems. The author provides web page access to an online bibliography, datasets, source codes for several algorithms described in the book, and other information. Soft Computing for Knowledge Discovery is for advanced undergraduates, professionals and researchers in computer science, engineering and business information systems who work or have an interest in the dynamic fields of knowledge discovery and soft computing.

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.

The authors have consolidated their research work in this volume titled Soft Computing for Data Mining Applications. The monograph gives an insight into the research in the ?elds of Data Mining in combination with Soft Computing methodologies. In these days, the data continues to grow - ponentially. Much of the data is implicitly or explicitly imprecise. Database discovery seeks to discover noteworthy, unrecognized associations between the data items in the existing database. The potential of discovery comes from the realization that alternate contexts may reveal additional valuable information. The rate at which the data is storedis growing at a phenomenal rate. Asaresult,traditionaladhocmixturesofstatisticaltechniquesanddata managementtools are no longer adequate for analyzing this vast collection of data. Severaldomainswherelargevolumesofdataarestoredincentralizedor distributeddatabasesincludesapplicationslikeinelectroniccommerce,bio- formatics, computer security, Web intelligence, intelligent learning database systems,?nance,marketing,healthcare,telecommunications,andother?elds. E?cient tools and algorithms for knowledge discovery in large data sets have been devised during the recent years. These methods exploit the ca- bility of computers to search huge amounts of data in a fast and e?ective manner. However,the data to be analyzed is imprecise and a?icted with - certainty. In the case of heterogeneous data sources such as text and video, the data might moreover be ambiguous and partly con?icting. Besides, p- terns and relationships of interest are usually approximate. Thus, in order to make the information mining process more robust it requires tolerance toward imprecision, uncertainty and exceptions.