A bi-phased multi-objective genetic algorithm based classifier

This paper presents a novel Bi-Phased Multi-Objective Genetic Algorithm (BPMOGA) based classification method. It is a Learning Classifier System (LCS) designed for supervised learning tasks. Here we have used Genetic Algorithms (GAs) to discover optimal classifiers from data sets. The objective of the work is to find out a classifier or Complete Rule (CR) which comprises of several Class Specific Rules (CSRs). Phase-I of BPMOGA extracts optimized CSRs in IF - THEN form by following Michigan approach, without considering interaction among the rules. Phase-II of BPMOGA builds optimized CRs from CSRs by following Pittsburgh way. It combines the advantages of both approaches. Extracted CRs help to build CSRs for the next run of phase-I. Hence, phase-I and phase-Il are cyclically related, which is one of the uniqueness of BPMOGA. With the help of twenty one benchmark data sets from the University of California at Irvine (UCI) machine learning repository we have compared performance of BPMOGA based classifier with fourteen GA and non-GA based classifiers. Statistical test shows that the performance of the proposed classifier is either superior or comparable to other classifiers. (C) 2020 Elsevier Ltd. All rights reserved.