关联规则挖掘算法及优化策略研究  

Survey of the Algorithms on Association Rule Mining

作　　者：左向科[1] 邢永康[1] 王嵘 

机构地区：[1]重庆大学计算机科学与技术学院,重庆400030 [2]重庆军代局驻江津地区军代室,重庆402264

出　　处：《微处理机》2009年第5期101-104,共4页Microprocessors

基　　金：国家自然科学基金青年基金资助(编号60403009)

摘　　要：关联规则挖掘是数据库中知识发现研究的热点课题,有着广泛的应用领域。通过对关联规则中快速开采算法的研究分析,首先把已有的关联规则挖掘算法分为了两大类:传统类型的关联规则挖掘算法和多关系关联规则挖掘算法;重点分析基本类型算法,并提出各种改进的优化策略;然后对各类代表性算法进行了描述,分析和对比;最后,对尚存在的问题进行了分析和总结。Discovery of association rules is a very hot topic in data mining research which has been very applicable and useful in many areas.This paper summarized these problems.First,classifying existing algorithms into two categories：traditional association rule mining algorithm and multirelational association rule mining algorithm.And analysising fundamental type algorithm,proposing the improved various optimization strategy;Then described the main techniques used in several typical algorithms,and also made comparison and analysis among them. Finally, pointing out some issues unsolved in this area.

关 键 词：数据挖掘 关联规则 APRIORI算法 频繁项集 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]