摘要
通过不同决策类之间的比较首先寻找核属性,进而以核属性为基础构造不含核属性的布尔区分矩阵,并利用吸收律和去重操作简化区分矩阵;然后以区分矩阵为基础,采用类似关联规则挖掘的Apriori算法思想逐级寻找系统的所有约简。理论分析和实验表明算法是正确且有效率的。
First we search the core attributes by the comparison between different decisionmaking class, and then we construct discernible Boolean matrix without core attributes but based on core attributes, and use the absorption rules and deemphasis operation to simplify the dis cernible matrix, after that we take discernible matrix as the basis and use the thought of Apriori algorithm similar to association rule mining to find all reduction step by step. Theoretical analysis and experiments show that the algorithm is correct and efficient.
出处
《计算机应用与软件》
CSCD
北大核心
2012年第10期40-43,116,共5页
Computer Applications and Software
基金
国家自然科学基金项目(70861001)
广西自然科学基金项目(桂科自0991027)
关键词
布尔区分矩阵
属性约简
关联规则挖掘
APRIORI算法
并行计算
Discernible Boolean matrix Attribute reduction Association rule mining Apriori algorithm Parallel computing
