关联规则中FP树算法的研究与改进  

Research and improvement on FP-tree algorithm of association rule

作　　者：刘冲[1] 陈晓辉[1] 宋小小[1] 

机构地区：[1]桂林理工大学信息科学与工程学院,广西541004

出　　处：《网络安全技术与应用》2012年第10期53-55,共3页Network Security Technology & Application

摘　　要：传统的基于关联规则的FP-树算法在挖掘频繁项目集算法中应用很广,它在数据挖掘过程中不需要产生候选集,但是该FP-树算法在挖掘较大型数据库时运行速度慢、占用内存大或根本无法构造基于内存的FP-树。为了解决这些问题,本文提出了一种占用内存少、能满足大型数据库挖掘需求的改进的FP树算法。Traditional FP-tree algorithm based on association rules is very popular in the data mining from frequent itemsets,which needs no candidate itemset in data mining.However,it has disadvantages such as slower execution time,higher memory space occupation and sometimes FP-tree can not be made when mining large databases.To overcome these drawbacks,the dissertation proposes one new improved FP-tree algorithm which occupies less memory space and can meet the demands of large database mining.

关 键 词：数据挖掘 关联规则 FP-树 FP-树算法改进 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]