基于粗集理论的约简算法  

Research of Reduced Algorithm Based on Rough Set Theory

作　　者：李雄飞[1] 谢忠时[1] 李晓堂[1] 李军[2] 

机构地区：[1]吉林大学计算机科学与技术学院,吉林长春130025 [2]长春理工大学数学系,吉林长春130025

出　　处：《吉林大学学报（工学版）》2003年第1期82-87,共6页Journal of Jilin University:Engineering and Technology Edition

基　　金：国家自然科学基金资助项目(60275726);吉林省自然科学基金资助项目(19990528)

摘　　要：在基于属性重要性和基于分辨矩阵两种算法的基础上,提出了一种同时满足属性重要性和频度的启发式约简算法RedFreSigni。该算法的基本思想是:以属性的核为基础,把核和用户偏好集同时作为属性近似约简的一部分,以频度作为选择属性的启发信息可同时生成计算属性的频度信息与不可分辨矩阵,减少了计算时间。在此基础上进而提出了基于规则支持度和置信度的决策挖掘算法,该算法能有效提取出用户感兴趣的规则。In this paper,we present a heuristic reduced algorithm,denoted RedFreSigni,that satisfies the attribute significance and attribute frequency at same time.This algorithm is based on the algorithms of attribute significance and resolution matrix.It takes the attribute′s core and user′s preference set as part of the attribute reduction,and using frequency as the heuristic information of attribute selection,and creating the frequency information of calculation attributes and undistinguishable matrix simultaneously,so the calculating time is reduced.Accordingly,a decision mining algorithm is presented which is based on rulesupport and confidence.Users can extract the useful rules effectively by using this algorithm.

关 键 词：约简算法 粗集理论 核 属性重要性 属性频度 分辨矩阵 数据挖掘 关联规则 知识表达 决策规则 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构] TP18[自动化与计算机技术—计算机科学与技术]