一种基于Rough Set理论的属性约简及规则提取方法  

An Approach for Attribute Reduction and Rule Generation Based on Rough Set Theory

作　　者：常犁云[1] 263.net 王国胤[1] 263.net[1,1] 吴渝 263.net[1,1] 

机构地区：[1]重庆邮电学院计算机科学与技术研究所

出　　处：《软件学报》1999年第11期1206-1211,共6页Journal of Software

基　　金：国家自然科学基金;重庆市应用基础研究基金

摘　　要：该文针对RoughSet理论中属性约简和值约简这两个重要问题进行了研究，提出了一种借助于可辨识矩阵（discernibilitymatrix）和数学逻辑运算得到最佳属性约简的新方法．同时，借助该矩阵还可以方便地构造基于RoushSet理论的多变量决策树．另外，对目前广泛采用的一种值约简策略进行了改进，最终使得到的规则进一步简化．In this paper, the authors discuss two important issues in rough set research which are attributereduction and value reduction. A new attribute reduction approach which can reach the best attribute reductionis presented based on discernibility matrix and logic computation. And a multivariate decision tree can be gotwith this method. Some improvements for a widely used value reduction method are also achieved in this paper.The complexity of acquired rule knowledge can be reduced effectively in this way.

关 键 词：ROUGHSET理论 属性约简 规则提取 数据库系统 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论] TP18[自动化与计算机技术—计算机科学与技术]