This article presents a newly proposed selection process for genetic algorithms on a class\nof unconstrained optimization problems. The k-means genetic algorithm selection process (KGA)\nis composed of four essential stages: clustering, membership phase, fitness scaling and selection.\nInspired from the hypothesis that clustering the population helps to preserve a selection pressure\nthroughout the evolution of the population, a membership probability index is assigned to each\nindividual following the clustering phase. Fitness scaling converts the membership scores in a range\nsuitable for the selection function which selects the parents of the next generation. Two versions\nof the KGA process are presented: using a fixed number of clusters K (KGAf) and via an optimal\npartitioning Kopt (KGAo) determined by two different internal validity indices. The performance of\neach method is tested on seven benchmark problems.
Loading....