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

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.