一种基于遗传算法的K-means聚类算法

A K-means clustering algorithm based on genetic algorithm

传统K-means算法对初始聚类中心的选取和样本的输入顺序非常敏感,容易陷入局部最优。针对上述问题,提出了一种基于遗传算法的K-means聚类算法GKA,将K-means算法的局部寻优能力与遗传算法的全局寻优能力相结合,通过多次选择、交叉、变异的遗传操作,最终得到最优的聚类数和初始质心集,克服了传统K-means算法的局部性和对初始聚类中心的敏感性。

Traditional K-means algorithm is sensitive to selecting initial clustering centers and input sequence, it is easy to get into the local best. In view of the above-mentioned problems, this paper proposes a K-means clustering algorithm（GKA） based on genetic algorithm. It combines local optimization of K-means algorithm with global optimization of genetic algorithm. By multiple selection, crossover and mutation, it can get optimal clustering number and initial centroid collection. So it overcomes the locality of traditional K-means algorithm and sensitivity of initial clustering centers.