摘要
针对现有的基于优势关系粗糙集的规则生成算法存在运行效率低的问题,提出了一种基于多个优势差别矩阵的规则生成算法,突出不同决策类之间的差别信息,在得到精简规则集的同时,能够提高规则生成效率.通过实验与其他规则生成算法加以比较,表明该算法在平均性能方面优于其他算法.
Dominance-based Rough Set Approach (DRSA) is different from the Classical Rough Set Approach (CRSA) because preference orders are taken into account in the domains of attributes and in the set of decision classes. A multi-dominance discernibility matrices based rule induction algorithm RIDDM is proposed. Constructing more than one dominance discernibility matrix can highlight the difference between two decision classes. The experimental results compared with other rule induction algorithms prove the effectiveness.
出处
《江南大学学报(自然科学版)》
CAS
2007年第6期686-689,共4页
Joural of Jiangnan University (Natural Science Edition)
基金
国家自然科学基金项目(60503022
60673043)
江苏省自然科学基金项目(BK2006117)
关键词
优势关系粗糙集
优势差别矩阵
规则生成
dominance-based rough set approach
dominance discernibility matrix
rule induction