基于准频繁项目集的关联规则挖掘  

Associaton Rules Mining Based on Supposed Frequent Itemsets

作　　者：赵旭俊[1] 闫宏印[1] 吴广平[1] 董晓丽[1] 

机构地区：[1]太原理工大学计算机学院,山西太原030024

出　　处：《太原理工大学学报》2005年第4期412-415,共4页Journal of Taiyuan University of Technology

摘　　要：为减少关联规则挖掘中数据库扫描次数,提出了一种基于准频繁项目集的关联规则挖掘算法———SupposedFrequent,同时给出了候选频繁项目集的产生函数———BGen.最后通过实验证明:在给定最好的准频繁项目集的条件下,只需扫描数据库两次就能产生全部的频繁项目集。For reducing the number of I/O passes required, we devise an association rules mining algorithm based on supposed frequent itemsets SupposedFrequent. We also present a function BGen, which generates candidate itemsets. The experiments prove that in the best cases, only two passes are sufficient to discover all the frequent itemsets irrespective of the size of the biggest ones.

关 键 词：关联规则 准频繁项目集 覆盖率 长频繁项目集 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]