计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (4): 143-145.DOI: 10.3778/j.issn.1002-8331.2009.04.040

• 数据库、信号与信息处理 • 上一篇    下一篇

改进的频繁项集挖掘算法

朱彦霞1,张雪萍2,王家耀1,2   

  1. 1.河南工业大学 信息工程学院,郑州 450001
    2.解放军信息工程大学 测绘学院,郑州 450052
  • 收稿日期:2008-08-05 修回日期:2008-10-31 出版日期:2009-02-01 发布日期:2009-02-01
  • 通讯作者: 朱彦霞

Improved algorithm for mining frequent item sets

ZHU Yan-xia1,ZHANG Xue-ping2,WANG Jia-yao1,2   

  1. 1.College of Information Science and Engineering,Henan University of Technology,Zhengzhou 450001,China
    2.College of Surveying and Mapping,PLA Information Engineering University,Zhengzhou 450052,China
  • Received:2008-08-05 Revised:2008-10-31 Online:2009-02-01 Published:2009-02-01
  • Contact: ZHU Yan-xia

摘要: 频繁项集挖掘是数据挖掘中的一个重要研究课题。在分析Apriori算法与FP-growth 算法特点的基础上,提出了一种改进的频繁项集挖掘算法,即索引生成频繁项集算法IGFA。IGFA算法基于Apriori算法并通过 “索引二元组”生成候选集,减免了候选集的大量冗余,实验及结果分析表明该算法有效提高了频繁项集的挖掘效率。

关键词: 数据挖掘, 关联规则, 频繁项集, 索引二元数组

Abstract: Mining frequent itemsets is an important research topic in Data Mining.This paper discussed the characteristics of Apriori algorithm and FP-growth algorithm and proposed an improved algorithm IGFA(Index-binary array Generate Frequent itemsets Algorithm) based on Apriori algorithm.The number of candidates can be reduced greatly by using an index array which based on the binary group.Analysis and experiments show that mining frequent itemsets by IGFA have been proved efficiently.

Key words: data mining, association rule, frequent itemsets, indexed binary array