一种有效的负频繁项集挖掘方法An efficient method for negative frequent itemsets mining
董祥军;马亮;
摘要(Abstract):
目前负关联规则研究的主要形式是左右两边项集全正或者全负,如(a1a2)■┐(b1b2)、┐(a1a2)#(b1b2),但有时形如a1┐a2■b1┐b2的负关联规则能够提供更多的决策信息,然而要挖掘这样的负关联规则需要先挖掘形如a1┐a2■b1┐b2的负频繁项集。为此,本文提出了一个有效的方法来挖掘这样的负频繁项集。该方法包含一个有效的负候选项集生成算法,和仅利用正频繁项集有关信息来计算负候选项集支持度的方法,而不用再次扫描数据库。实验表明了提出方法的有效性。
关键词(KeyWords): 正频繁项集;负频繁项集;支持度;负关联规则
基金项目(Foundation): 山东省优秀中青年科学家奖励基金项目(2006BS01017)
作者(Author): 董祥军;马亮;
Email:
DOI:
参考文献(References):
- [1]X.Wu,C.Zhang,and S.Zhang.Efficient Mining of both Positiveand Negative Association Rules[J].ACM Transactions onInformation Systems,2004,(22):381-405.
- [2]X.Dong,Z.Niu,X.Shi,X.Zhang.Mining Both Positive andNegative Association Rules from Frequent and Infrequent Itemsets[A].Proceedings of theThird International Conference onAdvanced Data Mining and Applications(ADMA 2007)[C].Harbin,China,August 6-8,2007.Lecture Notes in ComputerScience 4632,Springer 2007.122-133.
- [3]M.L.Antonie,O.Zaiane.Mining Positive and Negative AssociationRules:An Approach for Confined Rules[A].Proceedings of 8thEuropean Conference on Principles and Practice of KnowledgeDiscovery in Databases(PKDD04)[C].LNCS 3202,Springer-Verlag Berlin Heidelberg,Pisa,Italy,2004.27-38.
- [4]Y.Zhang,C.Wang and Z.Xiong.Improved algorithm of miningassociation rules with negative items[J].Computer Engineeringand Applications,2008,44(20):169-171.
- [5]Y.Zhang,Z.Xiong,C.Wang and C.Liu.Study on association ruleswith negative items based on bit string[J].Control and Decision,2010,(25):37-42.
- [6]B.Yuan,L.Chen and Y.Jin.Mining of negative frequent patternsin databases[J].Computer Engineering and Applications,2010,46(8):117-119.
- [7]X.Li,Y.Liu,J.Peng,and Z.Wu.The extended association rulesand atom association rules[J].Journal of computer research anddevelopment,2002,(39)12:1740-1750.
文章评论(Comment):
|
||||||||||||||||||
|