基于遗传算法的图论聚类方法

基于遗传算法的图论聚类方法 Graph-Theoretical Clustering Method Based on Genetic Algorithms 张爱华 ZHANG Ai-hua 1 first-author 武汉大学数学与统计学院,湖北,武汉,430072 武汉大学数学与统计学院,湖北,武汉,430072 School of Mathematics and Statisics,Wuhan University School of Mathematics and Statisics,Wuhan University 针对传统图论聚类算法对初始聚类中心的敏感性以及聚类结果与样本输入次序等问题,提出了基于遗传算法进行图论聚类分析的基本原理和实现方法.实验结果表明,遗传算法应用于图论聚类分析能够搜索到更为精确的聚类中心值,其结果明显好于传统图论聚类算法. To solve the problem of sensitivity with the original clustering center and clustering results depended on the order of the input example in common graph-theoretical clustering algorithm,the basic rules and procedures of applying genetic algorithms to graph theoretical clustering analysis are studied.Computing results show that applying it to clustering can accurately locate the clustering centers and is superior to common graph-theoretical clustering algorithm. 遗传算法 聚类分析 图论 最小生成树 genetic algorithms cluster analysis graph theoretical minimum spanning tree TP18 2005-01-01 2021-04-01 S2