基于维分类的关联规则的元规则制导挖掘  

Metarule-guided mining of association rules based on classification of dimensions

作　　者：倪志伟[1,2] 周之强[1,2] 公维峰[1,2] 孟金华[1,2] 

机构地区：[1]合肥工业大学管理学院,合肥230009 [2]过程优化与智能决策教育部重点实验室,合肥230009

出　　处：《计算机工程与应用》2011年第30期140-143,147,共5页Computer Engineering and Applications

基　　金：国家高技术研究发展计划(863)No.2007AA04Z116;国家自然科学基金(No.70871033)~~

摘　　要：元规则制导的关联规则挖掘可以提高挖掘过程的效率和精确度,目前已经提出了许多关联规则的元规则制导挖掘算法,尤其是在关系数据库中;而在数据立方体上的元规则制导挖掘算法相对较少,且大多数是基于Apriori思想的算法,它们都存在冗余谓词搜索的问题。针对这种情况,提出了一种以元规则中维度的不同类型为依据的改进算法LRS,并在实验中证明了算法的有效性。Metarule-guided mining of association rules can improve the efficiency and accuracy of mining process.Currently many algorithms have been proposed,especially in relational databases.In the case of data cubes,many algorithms are proposed,and most of them are based on Apriori theory,which lead to the problem of redundant predicates searching.In view of this situation,this paper proposes an algorithm LRS according to different types of dimensions in the metarule,and the ex-periment results demonstrate the effectiveness of the proposed algorithm.

关 键 词：元规则 关联规则 数据立方体 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]