| 摘要: |
| 该文针对Rough Set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（discernibility matrix）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Rough Set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. |
| 关键词: Rough Set理论，属性约简，值约简，多变量决策树. |
| DOI： |
| 分类号: |
| 基金项目:本文研究得到国家自然科学基金和重庆市应用基础研究基金资助. |
|
| An Approach for Attribute Reduction and Rule Generation Based on Rough Set Theory |
|
CHANG Li-yun,WANG Guo-yin,WU Yu
|
| Abstract: |
| In this paper, the authors discuss two important issues in rough set research which are attribute reduction and value reduction. A new attribute reduction approach which can reach the best attribute reduction is presented based on discernibility matrix and logic computation. And a multivariate decision tree can be got with 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. |
| Key words: Rough set theory, attribute reduction, value reduction, multivariate decision tree. |
