Multistage Fuzzy Control : A Model-Based Approach to Fuzzy Control and Decision Making

This valuable and timely publication from a highly acclaimed expert in the field provides an overall view of the discipline of multistage fuzzy control as well as a wealth of new ideas in decision-making and reinforcement learning Multistage Fuzzy Control 2nd Edition follows its predecessor, a classic in the field, in explaining the essential principles of fuzzy logic and describing both the theoretical and practical advantages of a model-based, prescriptive approach. In the 10 years since the first edition however, a myriad of new perspectives and developments have emerged - many as a result of the author s own research that earned him the 2006 IEEE Computational Intelligence Society Fuzzy Systems Pioneer Award for pioneering works on multistage fuzzy control. The use of some fuzzy tools for the analysis and optimization of multistage decision-making and control, notably of a fuzzy dynamic programming type, is now considered important and popular with researchers from different fields. This new edition features 30% new material in both theory and applications, with much space devoted to new research into reinforcement learning (a sub-area of machine learning concerned with how actions are to be taken in an environment so as to maximize some long term reward), and also to some extensions towards fuzzy reinforcement learning or neurofuzzy reinforcement learning. It also includes many new elements related to IT (information technology), notably to data mining, learning, bioinformatics, etc. Multistage Fuzzy Control 2nd Edition is an essential handbook for those wishing to resolve real-world problems in control and decision analysis through the use of fuzzy-logic-based methods. * Offers a valuable and timely publication from a highly acclaimed expert in the field, providing an overall view of the discipline of multistage fuzzy control as well as a wealth of new research. * Presents 30% new material, including important new ideas such as reinforcement learning, neurofuzzy architectures, evolutionary optimization and applications in the areas of bioinformatics, mobile robots and computer communication. * Includes a range of new applications related to power engineering, such as the use of fuzzy dynamic programming for water reservoir control, mobile robot control, data transfer control in computer networks, sequential pattern mining and predicting the secondary structure of ribonucleic acid (and some other problems in bioinformatics.