基于粗糙集规则提取算法的研究及应用

Research and Application Based on Rough Sets Rule Extraction Algorithm

针对中医胸痹(即冠心病)诊断规则的获取,采用基于粗糙集理论的规则提取方法。首先进行连续属性的离散化,生成基于决策的知识表达系统。然后利用属性约简的改进算法对决策表进行属性约简,找出诊断结果的核属性,综合考虑属性对约简的增益和属性在剩余属性集中的重要性,给出了衡量属性重要性程度的一个准则。随后进行属性值约简,获取诊断规则。本算法并用VC++和SQL Server 2000实现。

In view of Chinese medicine chest arthromyodynia（the coronary heart disease） rule extraction, we use the rule extraction algorithm based on rough sets theory. Firstly, the discretization of continuous attributes is carried out to generate the knowledge expressive system based on decision. Secondly, we make attribute reduction on decision table with improved algorithm of attribute reduction, and find out cores attribute for diagnosis result. Meanwhile, we propose a criterion for measuring attributes importance, which considers both the gain for the reduction and the importance in the remaining attributes. Finally, the value reduction is carried to get the diagnosis rules. The algorithm has been realized by VC＋＋ and SQL Server 2000.