快速挖掘全局最大频繁项目集  

Fast Mining of Global Maximum Frequent Itemsets

作　　者：陆介平[1] 杨明[1] 孙志挥[1] 鞠时光[2] 

机构地区：[1]东南大学计算机科学与工程系,江苏南京210096 [2]江苏大学计算机科学与通信工程学院,江苏镇江212013

出　　处：《软件学报》2005年第4期553-560,共8页Journal of Software

基　　金：国家自然科学基金;江苏省自然科学基金~~

摘　　要：挖掘最大频繁项目集是多种数据挖掘应用中的关键问题.现行可用的最大频繁项目集挖掘算法大多基于单机环境,针对分布式环境下的全局最大频繁项目集挖掘尚不多见.若将基于单机环境的最大频繁项目集挖掘算法运用于分布式环境,或运用分布式环境下的全局频繁项目集挖掘算法来挖掘全局最大频繁项目集,均会产生大量的候选频繁项目集,且网络通信代价高.为此,提出了快速挖掘全局最大频繁项目集算法FMGMFI(fast mining globalmaximum frequent itemsets),该算法采用FP-tree存储结构,可方便地从各局部FP-tree的相关路径中得到项目集的频度,同时采用自顶向下和自底向上的双向搜索策略,可有效地降低网络通信代价.实验结果表明,FMGMF算法是有效、可行的.Mining maximum frequent itemsets is a key problem in data mining field with numerous important applications. The existing algorithms of mining maximum frequent itemsets are based on local databases, and very little work has been done in distributed databases. However, using the existing algorithms for the maximum frequent itemsets or using the algorithms proposed for the global frequent itemsets needs to generate a lots of candidate itemsets and requires a large amount of communication overhead. Therefore, this paper proposes an algorithm for fast mining global maximum frequent itemsets (FMGMFI), which can conveniently get the global frequency of any itemset from the corresponding paths of every local FP-tree by using frequent pattern tree and require far less communication overhead by the searching strategy of bottom-up and top-down. Experimental results show that FMGMFI is effective and efficient.

关 键 词：分布式数据库 数据挖掘 频繁模式树 全局最大频繁项目集 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]