An efficient approach for unsupervised fuzzy clustering based on grouping evolution strategies

Fuzzy data clustering plays an important role in practical use and has become a prerequisite step for decision-making in fuzzy environment. In this paper we propose a new algorithm, called FuzzyGES for unsupervised fuzzy clustering based on adaptation of the recently proposed Grouping Evolution Strategy (GES). To adapt GES for fuzzy clustering we devise a fuzzy counterpart of the grouping mutation operator typically used in GES, and employ it in a two phase procedure to generate a new clustering solution. Unlike conventional clustering algorithms which should get the number of clusters as an input, FuzzyGES tries to determine the true number of clusters as well as providing the optimal cluster centroids after several iterations. The proposed approach is validated through using several data sets and results are compared with those of fuzzy c-means algorithm, particle swarm optimization algorithm (PSO), differential evolution (DE) and league championship algorithm (LCA). We also investigate the performance of FuzzyGES through using different cluster validity indices. Our results indicate that FuzzyGES is fast and provides acceptable results in terms of both determining the correct number of clusters and the accurate cluster centroids.

► Developing the fuzzy version of the recently proposed GES algorithm.
► Investigating the application of the proposed algorithm to unsupervised fuzzy data clustering.
► The algorithm has the ability of using structural knowledge of the problem.
► The algorithm exhibits rather a constant behavior.
► The algorithm is more reliable than fuzzy c-means, PSO, DE and LCA.