Survey of Rough and Fuzzy Hybridization

Abstract

This paper provides a broad overview of logical and black box approaches to fuzzy and rough hybridization. The logical approaches include theoretical, supervised learning, feature selection, and unsupervised learning. The black box approaches consist of neural and evolutionary computing. Since both theories originated in the expert system domain, there are a number of research proposals that combine rough and fuzzy concepts in supervised learning. However, continuing developments of rough and fuzzy extensions to clustering, neurocomputing, and genetic algorithms make hybrid approaches in these areas a potentially rewarding research opportunity as well.