Interpretability improvement of fuzzy rule-based classifiers via rule compression

Abstract

Rule-level feature selection, also termed as rule compression, is an important technique for improving interpretability of fuzzy rule-based classifiers. In this paper we present three different rule compression algorithms and analyze their performance and characteristics on the classifiers identified from wellknown classification benchmarks, namely the Iris, Wine and two versions of Wisconsin Breast Cancer data sets. Our study shows that the classifiers, in which the overlap between either the rules representing different classes or all rules is eliminated, can be usually compressed at a higher rate and that the interpretation of such classifiers is more insightful.

Design of Fuzzy Rule-based Classifiers through Granulation and Consolidation

“…To reduce the number of conditions in fuzzy classifiers we apply the naive rule compression method [28]. The algorithm is based on simple trial and error and is described as follows:…”