Novel crossover and mutation operation in Genetic Algorithm for clustering

In this paper we propose a Genetic Algorithm-based clustering technique called GMC that produces high-quality chromosomes in the initial population. The proposed technique also introduces two phases of crossover operation with extensive chromosomes generation aiming to produce high-quality offspring chromosomes and prevent degeneracy. The proposed technique also introduces three steps of mutation operation in order to improve chromosome quality. GMC uses a probabilistic selection approach in order to gradually improve the chromosomes quality of a population. We compare the proposed technique GMC with five existing techniques on 10 publicly available data sets in terms of two well-known evaluation criteria: Silhouette Coefficient and DB Index. Our experimental results demonstrate statistically significant superiority of GMC over the existing techniques, and the effectiveness of the proposed components.