摘要
提出了基于微粒群的聚类分析的三种算法,并对某化工厂的7018组18维数据进行聚类分析,通过适应度函数大小,收敛性能等因素的分析判定各种算法的优缺点,从而从理论上和实际上验证本算法的有效性。
Three cluster analysis algorithms based on Particle Swarm Optimization(PSO) are introduced in this paper,which are used to analyze 7018 groups of 18-dimension data from a chemical plant. By the factors of fitness function measure and astringency,we can analyze and determine the advantages and disadvantages of the three algorithms,and validate the PSO-based cluster analysis method in theory and practice.
出处
《科技信息》
2009年第1期428-429,414,共3页
Science & Technology Information
关键词
微粒群优化算法
数据挖掘
聚类分析
Particle Swarm Optimization（PSO）
data mining
cluster analysis
