摘要
利用粗糙集理论中属性核与不可分辨关系给出了属性约简和数据过滤算法,去除信息系统中与决策无关的冗余信息.在简化的信息系统基础上用传统算法构造决策树,并利用由粗糙集理论推出的极小、极大化学习方法对决策树规则进行极小、极大化处理.最后给出了一个最简分类规则集生成算法.
Based on attribute core and equivalent relation in rough set theory, an attribute reduction and data filtering algorithm to delete redundant information in information system. On the basis of new compact information system decision trees are built for decision tree rules. The notion of minimal rule and maximal rule are addressed in the light of the notion of reduction from rough set and are used to deal with decision tree rules . An algorithm to gain minimal classing rule set is proposed at the end of the paper.
出处
《哈尔滨工程大学学报》
EI
CAS
CSCD
2002年第5期87-91,共5页
Journal of Harbin Engineering University
