A Voronoi Diagram Based Classifier for Multiclass Imbalanced Data Sets

Abstract

The imbalance problem is receiving an increasing attention in the literature. Studies in binary cases are recurrent, however there still are several real world problems with more than two classes. The known solutions for binary datasets may not be applicable in this case. Some efforts are being applied in decomposition techniques which transforms a multiclass problem into some binary problems. However it is also possible to face a multiclass problem with an ad hoc approach, i.e., a classifier able to handle all classes at once. In this work a method able to handle several classes is proposed. This new method is based on the Voronoi diagram. We try to dynamically divide the feature space into several regions, each one assigned to a different class. It is expected for the method to be able to construct a complex classification model. However, as it is in its beginning, some tests need to be performed in order to evaluate its feasibility. Experiments with some classical classifiers confirm its feasibility, and comparisons with ad hoc methods found in literature show its potentiality.