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.
出处
《计算机工程与应用》
CSCD
北大核心
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)