Data clustering using multi-objective hybrid evolutionary algorithm

This paper proposes a multi-objective evolution strategy (ES) hybridized with a k-means algorithm to address a data clustering problem whose objective is minimizing both clustering error and cluster number. Contrary to the conventional data clustering problem with a predetermined number of clusters, the bi-objective problem considered in this study has a set of clustering solutions whose cluster numbers are different from one another. This enables to secure the best clustering result that fits specific needs without restricting the cluster number. To find the solution set, the hybrid ES evolves a population of solution candidates each of which represents a variable number of cluster centroids. While evolving the population, special ES operators dedicated to the bi-objective clustering problem are used. Whenever the hybrid ES creates a new set of cluster centroids, it is fine-tuned by the k-means algorithm. The experiment results show that the hybrid ES outperforms the conventional ES and KMA.