基于疫苗提取及免疫优化的粗糙集属性约简  

Attribute reduction method of rough sets based on bacterin extraction and immune optimum

作　　者：徐雪松[1] 章兢[1] 贺庆[2] 何昭晖[1] 王炼红[1] 

机构地区：[1]湖南大学电气与信息工程学院,长沙410082 [2]中南大学信息科学与工程学院,长沙410083

出　　处：《控制与决策》2008年第5期497-502,共6页Control and Decision

基　　金：国家自然科学基金重点项目(60634020);教育部博士点基金项目(20060532026)

摘　　要：针对约简属性组合的爆炸问题,将RS属性核参数作为先验信息的免疫疫苗引入抗体编码,概率性对种群接种疫苗.将属性集合的分类近似标准作为抗体适应度,通过在免疫克隆选择过程中引入聚类竞争机制,提高抗体群分布的多样性及亲和力成熟,从而获得多个属性约简及最小约简的平衡.实验结果表明,这种粗糙集属性约简方法对于多维条件属性集是快速且有效的.Aiming at the problem of large scales of attribute reduction, a prior knowledge of attribute kernel as bacterins is introduced to antibody coding and the population is vaccinated in a stochastic way. The classification approximation quality is taken as the antibody affinity , then a cluster and competition mechanism is applied in clonal selection process to enhance the diversity of antibody and affinity maturation. Minimum reductions and more reductions of the rough sets are obtained. Experimental results show that the approach＇is effective and quick in solving attribute reduction, and has a remarkable quality of the global convergence reliability and convergence velocity.

关 键 词：克隆选择 粗糙集 属性约简 数据挖掘 

分 类 号：TP182[自动化与计算机技术—控制理论与控制工程]