A genetic learning of the fuzzy rule-based classification system granularity for highly imbalanced data-sets

Abstract

In this contribution we analyse the significance of the granularity level (number of labels) in Fuzzy Rule-Based Classification Systems in the scenario of data-sets with a high imbalance degree. We refer to imbalanced data-sets when the class distribution is not uniform, a situation that it is present in many real application areas. The aim of this work is to adapt the number of fuzzy labels for each problem, applying a fine granularity in those variables which have a higher dispersion of values and a thick granularity in the variables where an excessive number of labels may result irrelevant. We compare this methodology with the use of a fixed number of labels and with the C4.5 decision tree.