Visual K-Means approach for handling class imbalance learning

Abstract

In this paper, a novel clustering algorithm dubbed as Visual K-Means (VKM) is proposed. The proposed algorithm deals with the uniform effect which is very much visible in k-means algorithm for skewed distributed data sources. The evaluation of the proposed algorithm is conducted with 10 imbalanced dataset against five benchmark algorithms on six evaluation metrics. The observations from the simulation results project that the proposed algorithm is one of the best alternatives to handle the imbalanced datasets effectively.