基于Apriori算法的改进算法  

Improved algorithm based on Apriori algorithm

作　　者：郭健美[1] 宋顺林[1] 李世松[1] 

机构地区：[1]江苏大学计算机学院,江苏镇江212013

出　　处：《计算机工程与设计》2008年第11期2814-2815,2820,共3页Computer Engineering and Design

基　　金：江苏省产业信息化重点基金项目(1633000004)。

摘　　要：关联规则挖掘是数据挖掘研究的一项重要内容。为了快速挖掘关联规则,分析了挖掘关联规则的Apriori算法,并在此基础上给出了一种改进的算法:NApriori算法,利用频繁1项集重新组织事务数据库来挖掘关联规则,此方法仅需扫描数据库2次,且避免了Apriori算法繁琐的连接和删除步骤,实验结果表明此方法比Apriori算法有更好的性能。Mining association roles is one of the most important topics in data mining. In order to mine association roles quickly, the Apriori algorithm is analyzed, and in this foundation one kind of improved algorithm is proposed which is called NApriofi algorithm. In order to mine association rules, it used frequent 1 itemset to reorganize the transaction database. It only needed two times of scanning, and had avoided the tedious connection step and the deletion step of the Apriori algorithm. The experiment indicates that this method has a better performance compared to the Apriori algorithm.

关 键 词：数据挖掘 关联规则 频繁项集 事务数据库 最小支持数 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]