A Hybrid Clustering Method Using Genetic Algorithm with New Variation Operators

The clustering problem under the criterion of minimum sum of squares is a non-convex and non-linear program, which possesses many locally optimal values, resulting that its solution often being stuck at locally optimal values and therefore cannot converge to global optima solution. In this paper, we introduce several new variation operators for the proposed hybrid genetic algorithm for the clustering problem. The novel mutation operator, called Clustering Regional Mutation, exchanges neighboring centers and a simple onepoint crossover. The proposed algorithm identifies proper clustering. The experimental results are given to illustrate the effectiveness of the new genetic algorithm.