Multiple Fuzzy Classification Systems

This book presents a novel approach for exploratory data analysis with ensembles of various neuro-fuzzy systems. It places emphasis on ensembles that can work on incomplete data, thanks to rough set theory.

Fuzzy classiers are important tools in exploratory data analysis, which is a vital set of methods used in various engineering, scientic and business applications. Fuzzy classiers use fuzzy rules and do not require assumptions common to statistical classication. Rough set theory is useful when data sets are incomplete. It denes a formal approximation of crisp sets by providing the lower and the upper approximation of the original set. Systems based on rough sets have natural ability to work on such data and incomplete vectors do not have to be preprocessed before classication. To achieve better performance than existing machine learning systems, fuzzy classifiers and rough sets can be combined in ensembles. Such ensembles consist of a nite set of learning models, usually weak learners.

The present book discusses the three aforementioned elds fuzzy systems, rough sets and ensemble techniques. As the trained ensemble should represent a single hypothesis, a lot of attention is placed on the possibility to combine fuzzy rules from fuzzy systems being members of classication ensemble. Furthermore, an emphasis is placed on ensembles that can work on incomplete data, thanks to rough set theory. .

Novel approach for exploratory data analysis with ensembles of various neuro-fuzzy systems Derivation of various ensemble architectures that are able to work with missing data Written by an expert in this field

Inhalt
Introduction to fuzzy systems.- Ensemble techniques.- Relational modular fuzzy systems.- Ensembles of the Mamdani fuzzy systems.- Logical type fuzzy systems.- Takagi-Sugeno fuzzy systems.- Roughneurofuzzy Ensembles for Classification with Missing Data.- Concluding remarks and challenges for future research.