摘要
本文通过对PSO算法模型和分类模型的分析,提出了应用多群体PSO算法实现分类规则的方法。这种方法将c(c≥2)类问题看成是c个两类问题,应用c个微粒群表示c类规则,每个微粒群应用PSO算法实现对连续变量空间的分类。最后,在五个数据集上的实验结果表明了此方法的可行性和有效性,并与C4.5算法的结果进行了比较。
A new approach for classification rules using multi-particle swarm is proposed.In this way,the c（c≥2） classification problem is taken as c two-class problems,and c class rules are expressed by c particle swarms, and classfication rules with the continuous variable space is finished by the PSO algorithm.Experimental results on 5 data sets show its efficiency and feasibility and are compared with the C4.5 results.
出处
《计算机工程与科学》
CSCD
2007年第1期94-96,125,共4页
Computer Engineering & Science
基金
教育部重点科研项目(204018)
关键词
PSO算法
分类规则
混合编码
PSO algorithm
classification rule
hybrid code
