Fuzzy‐Rough Feature Selection usingf‐Information Measures
Pradipta Maji, Sankar Kumar Pal · 2012
Feature selection or dimensionality reduction of a data set is an essential preprocessing step used for pattern recognition, data mining, and machine learning. The generalized theories of rough-fuzzy sets and fuzzy-rough sets have been applied successfully to feature selection of real-valued data. This chapter first briefly introduces the necessary notions of fuzzy-rough sets. It then reports the formulae of Shannon's entropy for fuzzy approximation spaces with a fuzzy equivalence partition matrix (FEPM). The chapter presents the f-information measures for fuzzy approximation spaces. It also describes the feature selection method based on f-information measures for fuzzy approximation spaces. Next the chapter reports several quantitative measures to evaluate the performance of different fuzzy-rough-set-based feature selection methods. Finally, it presents a few case studies and a comparison with other methods. Controlled Vocabulary Terms fuzzy set theory; rough set theory