Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (16): 140-142.DOI: 10.3778/j.issn.1002-8331.2010.16.041

• 数据库、信号与信息处理 • Previous Articles     Next Articles

MLFI:New method for maximum length frequent itemsets mining

ZHANG Zhong-ping,GUO Jing,HAN Li-xia   

  1. Department of Information Science and Engineering,Yanshan University,Qinhuangdao,Hebei 066004,China
  • Received:2008-11-21 Revised:2009-02-25 Online:2010-06-01 Published:2010-06-01
  • Contact: ZHANG Zhong-ping


张忠平,郭 静,韩丽霞   

  1. 燕山大学 信息科学与工程学院,河北 秦皇岛 066004
  • 通讯作者: 张忠平

Abstract: After the current definition of the maximum length frequent itemsets mining problem is understood and its many practical applications are explored,an FP-tree-based algorithm is proposed for the mining problem.Maximum length frequent itemsets are mined while traversing the FP-tree in the algorithm.There is only an initial FP-tree.Theoretic analysis and experiments show that the algorithm accelerates the speed to traverse the tree and improves the mining efficiency.

Key words: data mining, frequent itemsets, maximum length frequent itemsets, FP-tree

摘要: 在理解现有的最大长度频繁项集挖掘问题的定义,探索最大长度频繁项集的几个具体应用后,提出了一种新的基于FP-tree(Frequent Pattern tree)结构的最大长度频繁项集挖掘方法——MLFI算法。该算法仅对初始的FP-tree实现遍历操作,从而完成对最大长度频繁项集的挖掘。在算法整个执行过程中,仅用到了一棵初始的FP-tree。理论分析和实验证明,该算法加快了挖掘速度,提高了挖掘效率。

关键词: 数据挖掘, 频繁项集, 最大长度频繁项集, 频繁模式树

CLC Number: