Ensemble Classifier Design by Parallel Distributed Fuzzy Genetics-based Machine Learning

Abstract

Classifier design for a large data set by fuzzy GBML needs long computation time. In our former studies, we have proposed parallel distributed fuzzy GBML which can drastically decrease the computation time by dividing a population and a training data set into subgroups. In this paper, we propose ensemble classifier design by parallel distributed fuzzy GBML. The best classifier is selected from each sub-population as a base classifier. The base classifiers are combined into an ensemble classifier. Through computational experiments on parallel distributed fuzzy GBML, we examine the performance of the ensemble classifier design by parallel distributed fuzzy GBML.