摘要
数据库关联规则挖掘是数据挖掘研究中一个重要研究课题,但该方法本身存在不足,对于大型数据库,可能产生数以千计的规则,使用户感到无所适从。本文提出对关联规则进行分类的思想,并给出了基于数据统计特性的带兴趣度的关联规则挖掘算法GRMiner和IRMiner,算法实现简单,分析表明该算法是有效的。
The association rule mining of database is one of the important research fields in data mining, but the most current mining algorithm has obvious defects: a mass of rules confuse users and the traditional apriori algorithm maybe mining many paradoxical rules from the transaction database. This paper bought foward the idea about classified association rules, and put forward the algorithm based on the statistical specialty of the data with interest measure. The result of experiment analysis show the algorithm is effective and easy to be realized.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2003年第4期494-499,共6页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金(No.69933010)
