基于佳点集遗传算法的聚类技术  

Clustering techniques based on good point-set genetic algorithm

作　　者：苏守宝[1] 刘仁金[1] 

机构地区：[1]皖西学院计算机科学与技术系

出　　处：《计算机应用》2005年第3期643-645,共3页journal of Computer Applications

摘　　要：提出了两种基于佳点集遗传算法的聚类新方法GAmeans和HgaMeans,适用于不同数据库下的聚类挖掘。GAmeans可用于发现指定簇数的聚类中心,具有对初始数据的弱依赖性、收敛快、精度高并可避免早熟的特点;而混合方法HgaMeans是利用k means对GAmeans聚类结果的进一步提炼,实验表明它具有更好的聚类质量和综合性能。This paper proposed two new approaches, GAmeans and HgaMeans, using good point-set genetic algorithm to cluster data in data mining for various databases. GAmeans could be used to find the centroid of specified number of clusters, characterized as inferior sensitivity to initial data, quick convergence, high accuracy and removal of premature. The hybrid algorithm HgaMeans used k-means to refine the clusters formed by GAmeans. Experiments show that the hybrid method has better clustering quality and general performance.

关 键 词：聚类 佳点集 遗传算法 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]