快速更新频繁闭合项目集算法  

Fast Updating Algorithm of Frequent Closed Itemsets

作　　者：杨萍[1] 李立乡 杨明[1] 

机构地区：[1]南京师范大学数学与计算机学院,南京210097 [2]南京高等职业技术学校,南京210019

出　　处：《计算机工程与应用》2006年第36期148-151,共4页Computer Engineering and Applications

基　　金：国家自然科学基金资助项目(70371015);江苏省自然科学基金资助项目(BK2005135);江苏省高校自然科学研究项目基金资助项目(05KJB520066)

摘　　要：频繁闭合项目集集可惟一确定频繁项目集完全集且数量小得多,然而有关频繁闭合项目集的更新还不多见。为此,提出快速更新频繁闭合项目集算法—FUAFCI(Fast Updating Algorithm of Frequent Closed Itemsets),该算法主要考虑最小支持度发生变化时频繁闭合项目集的更新情况。FUAFCI在最坏的情况下仅须扫描各局部数据库一遍,且利用CLOSET+的项目集合并、子项目集修剪以及子集检验等优化策略及已挖掘的结果,可确保对频繁闭合项目集进行高效的更新。验结果表明,FUAFCI算法是有效可行的。The set of frequent closed itemsets determines exactly the complete set of all frequent itemsets and is usually much smaller than the laster.Yet very little work has been done for updating of frequent closed itemsets.Therefore, in this paper,we introduce an fast updating algorithm of frequent closed itemsets-FUAFCI,which considers the updating of frequent closed itemsets when dynamically adjusting minimum support measure threshold.In worse case,FUAFCI only scans transaction database once,Moreover,using the previously mined frequent closed itemsets and the item merging,item skipping,sub-itemset pruning methods,and so on in CLOSET＋,FUAFCI can obviously improves updating efficiency of frequent closed itemsets.Experimental results show that FUAFCI algorithm is efficient and effective.

关 键 词：数据挖掘 频繁闭合项目集 更新 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]