基于FP树的多最小支持度广义关联规则挖掘算法  

Generalized Association Rule Mining Algorithm with Multiple Minimum Supports Based on Frequent Pattern Tree

作　　者：佘俊胜[1] 黄战[1] 李亚丹[1] 

机构地区：[1]暨南大学计算机科学系,广东广州510632

出　　处：《小型微型计算机系统》2007年第12期2212-2215,共4页Journal of Chinese Computer Systems

摘　　要：采用MIS-tree结构保存频繁模式的信息提出了基于频繁模式增长挖掘原型的CFP-tax算法,该算法可避免候选集的生成和高代价的数据库扫描并能高效地找出数据库中所有频繁项集.基于虚拟数据集对算法的性能进行了评估,结果表明CFP-tax算法比经典的MMS-Cumulate算法性能有显著的提高.A generalized association rule with multiple minimum supports mining algorithm based on pattern growth mining paradigm called CFP-tax, is proposed by employing the MIS-tree to store the information about frequent patterns, which avoids candidate generation and costly database scans and efficiently finds all the frequent item sets in the database. The performance of the algorithm is evaluated based on synthetic datasets, and the results show that our algorithm significantly outperforms the classic MMS_Cumulate algorithm.

关 键 词：数据挖掘 广义关联规则 多最小支持度 频繁模式树 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]