基于FIUT结构增量式频繁项集挖掘  

INCREMENTAL MINING OF FREQUENT ITEMSETS USING FIUT STRUCTURE

作　　者：寇香霞[1] 任永功[1] 宋奎勇[1] 

机构地区：[1]辽宁师范大学计算机与信息技术学院,辽宁大连116029

出　　处：《计算机应用与软件》2012年第7期105-108,共4页Computer Applications and Software

基　　金：教育部留学回国人员科研启动基金项目;辽宁省科技计划项目(2008216014);辽宁省教育厅高等学校科研基金项目(L2010229);大连市优秀青年科技人才基金项目(2008J23JH026)

摘　　要：增量式频繁项集挖掘是当前研究的热点,基于FP-Growth的Pre-FUFP算法有效处理了频繁模式的更新,但需递归遍历FP-tree,导致效率较低。提出Pre-FIUT算法,引入频繁超度量树结构,提高了获得频繁项集挖掘效率;基于FIUT的Pre-FIUT可通过查看频繁超度量树叶子结点的支持度确定频繁项集,并与次频繁项集概念相结合进行增量式频繁项集挖掘。实验表明,Pre-FIUT算法能快速扫描和更新数据,合理利用内存,精确获得频繁项集。Incremental mining of frequent itemsets is a focus in current researches. Pre-FUFP algorithm, which is based on FP-Growth, effectively deals with the updates of frequent pattern, but the mining process needs to recursively traverse the FP-tree, which results in Bow efficiency. In this paper we propose the Pre-FIUT algorithm, introduce the frequent items uhrametric tree structure, have improved the frequent itemsets efficiency; Pre-FIUT is based on FIUT method, it can determine the frequent itemsets by checking the support of leave nodes of frequent uhrametric tree, as well as combines the pre-large itemset concept to conduct incremenlal mining of frequent itemsets. Experimental results show that the proposed approach can scan and update data quickly, use memory muelh more reasonable, and get the frequent itemsets precisely.

关 键 词：FIUT 数据挖掘 频繁项集 次频繁项集 Pre-FIUT算法 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]