快速挖掘频繁项目集算法  

Fast algorithm for mining frequent itemsets

作　　者：马丽生[1] 

机构地区：[1]滁州学院计算机科学与技术系,安徽滁州239000

出　　处：《计算机工程与设计》2009年第8期1903-1906,共4页Computer Engineering and Design

摘　　要：频繁项目集挖掘是数据挖掘领域最重要的基本问题之一,在分析已有算法的基础上,提出了一种能够快速挖掘频繁项目集的算法,对频繁项目集挖掘的搜索空间以及数据表示进行了优化,缩小搜索空间和数据表示的规模,减少计算项目集支持数的时间,提高算法的执行效率,实验结果表明,该算法在性能上优于FP-Growth算法。Frequent itemset mining is one of most important and fundamental data mining problems. Based on analyzing existent algorithm, a new algorithm for mining frequent itemsets, called FDFIA is presented. This algorithm uses a strategy which can reduce the search space, the size of FP-tree and the time of count. The new algorithm presented discovers frequent Itemsets which is faster than the previously developed algorithms. Comparative experiments show that the new algorithm outperforms the previously developed algorithms such as FP-Crrowth.

关 键 词：数据挖掘 频繁项目集 关联规则 频繁项目集树 频繁模式树 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]