摘要
为提高文本挖掘算法的运行速度,降低占用的内存空间,提出一种基于并行二进制免疫量子粒子群优化的特征选择方法.该方法采用二进制免疫量子粒子群优化搜索特征子集,利用并行算法来提高时间效率,从而较快地获得较具代表性的特征子集.实验结果表明该算法是有效的.
In order to enhance the operating speed and reduce the memory space occupied and filter out irrelevant or lower degree of features,a feature selection method based on the parallel binary immune quantum-behaved particle swarm optimization （PBIQPSO） is presented,which uses the binary immune quantum-behaved particle swarm optimization to select feature subsets and takes advantage of multiple computing nodes to enhance time efficiency,so can acquire quickly the feature subsets which are more representative.Experimental results show the effectiveness of the algorithm.
出处
《控制与决策》
EI
CSCD
北大核心
2010年第1期53-58,63,共7页
Control and Decision
基金
四川省科技计划项目(2008GZ0003)
四川省科技厅科技攻关项目(07GG006-019)
关键词
特征空间
特征选择
并行二进制免疫量子粒子群优化
Feature space
Feature selection
Parallel binary immune quantum-behaved particle swarm optimization （PBIQPSO）
