Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (3): 164-164.

• 数据库与信息处理 • Previous Articles     Next Articles

A hybrid cluster algorithm based on generic algorithm and generic fuzzy clustring algorithm

  

  • Received:2006-05-22 Revised:1900-01-01 Online:2007-01-21 Published:2007-01-21

基于遗传算法和遗传模糊聚类的混聚类算法

张强 李淼   

  1. 中科院合肥智能机械研究所 吉林建筑工程学院计算机科学与工程系
  • 通讯作者: 张强

Abstract: Abstract:In order to dynamically get the number of cluster center C and the most optimal cluster sample. We construct a new algorithm based on generic algorithm and generic Fuzzy C-Means(called HGA-FGCM).This method gives a new object evaluation function, which takes into not only the scatter degree among clusters but also the compactness in the same cluster. Make use of the GA’s global optimal search ability; get the optimal clusters under the given number of cluster center C.

Key words: Fuzzy clustering, Generic algorithm, Fuzzy C-Means, Generic Fuzzy C-Means

摘要: 为了动态确定聚类数目C和该数目下的最优分类,本文构造出遗传算法和模糊遗传C均值聚类的混和聚类算法(HGA-FGCM),该方法构造了一个既考虑类与类之间的分散程度、又考虑同一类紧凑程度的目标评价函数;运用遗传算法的全局寻优能力,求得最佳聚类数下的最优聚类。

关键词: 模糊聚类, 遗传算法, 模糊C-均值, 遗传模糊C-均值