LBRM Algorithm for Rule Extraction Based on Rough Membership

Abstract

Rule extraction is a main goal for rough set theory. This paper mainly constructs a new algorithm (LBRM Algorithm) for rule extraction based on rough membership. The confidence principle is established based on rough membership. Thus, LBRM Algorithm is proposed by utilizing discretization and clearness strategies under the fuzzy environment, and is applied to both interval rules and general rules in fuzzy classification. LBRM Algorithm effectiveness is illustrated by a medical example. In particular, LBRM Algorithm integrates the confidence on both previous LBR Algorithm and fundamental rough membership, and has some improvements on rule confidence.