一种整合粒子群优化和K-均值的数据聚类算法  

A Clustering Algorithm Integrating Particle Swarm Optimization and K-Means Algorithm

作　　者：徐辉[1] 李石君[2] 

机构地区：[1]广西财经学院计算机与信息管理系,广西南宁530003 [2]武汉大学计算机学院,湖北武汉430072

出　　处：《山西大学学报（自然科学版）》2011年第4期518-523,共6页Journal of Shanxi University(Natural Science Edition)

基　　金：国家自然科学基金(60970018)

摘　　要：针对K-均值聚类算法存在的不足,提出了一种新的整合粒子群优化算法(PSO)和K-均值算法的聚类算法.在新算法中,首先结合使用粒子群优化算法和K-均值算法搜索全局最优解的位置,然后再用K-均值算法在全局最优解附近的局部空间内快速寻找最优聚类中心.通过对4个数据集的实验测试,将此算法与K-均值算法、基于粒子群的K-均值算法进行了比较.实验结果表明,新算法的聚类质量比后两个算法更优.For the shortcomings of K-means clustering algorithm,a new clustering algorithm is introduced,and it integrates particle swarm optimization(PSO) and K-means algorithm.In the new algorithm,it first uses particle swarm optimization and K-means algorithm to search global optimum location,and then K-means algorithm is used for rapidly finding optimal cluster centers in the global optimal solution space.After testing four data sets of experiment,the algorithm is compared with the K-means algorithm,particle swarm-based K-means algorithm.The experimental results show that the quality of the new clustering algorithm is better than latter two algorithms.

关 键 词：数据聚类 K-均值 粒子群优化 

分 类 号：N55[自然科学总论]