[1]孟彩霞.频繁模式挖掘的约束算法[J].智能系统学报,2009,4(02):142-147.
 MENG Cai-xia.A frequent pattern mining algorithm based on constraints[J].CAAI Transactions on Intelligent Systems,2009,4(02):142-147.
点击复制

频繁模式挖掘的约束算法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第4卷
期数:
2009年02期
页码:
142-147
栏目:
出版日期:
2009-04-25

文章信息/Info

Title:
A frequent pattern mining algorithm based on constraints
文章编号:
1673-4785(2009)02-0142-06
作者:
孟彩霞
西安邮电学院计算机系,陕西西安710065
Author(s):
MENG Cai-xia
Department of Computer Science, Xi’an University of Posts & Telecommunications, Xi’an 710065,China
关键词:
频繁模式挖掘动态约束频繁项集最大频繁模式
Keywords:
frequent patterns mining dynamic constraints frequent item set maximal frequent pattern
分类号:
TP311
文献标志码:
A
摘要:
在频繁模式挖掘过程中能够动态改变约束的算法比较少.提出了一种基于约束的频繁模式挖掘算法MCFP.MCFP首先按照约束的性质来建立频繁模式树,并且只需扫描一遍数据库,然后建立每个项的条件树,挖掘以该项为前缀的最大频繁模式,并用最大模式树来存储,最后根据最大模式来找出所有支持度明确的频繁模式.MCFP算法允许用户在挖掘频繁模式过程中动态地改变约束.实验表明,该算法与iCFP算法相比是很有效的.
Abstract:
Most algorithms don’t allow users to dynamically change constraints in the process of mining frequent patterns. A new algorithm, constrainbased frequent patterns mining, was developed to provide frequent pattern mining with constraints. First, the algorithm constructs the FPtree (frequent pattern tree) according to the descending or ascending order of constraints, and in this process the database only needs to be scanned once. Secondly, the conditional tree of each item was established to mine maximal frequent pattern with this term as a prefix, and the maximal frequent patterns were stored. Finally, all frequent patterns with precise support degrees were discovered according to the maximal frequent patterns. The significance of this method is that this algorithm allows users to dynamically change constraints during the process. Experimental outcomes showed that the proposed algorithm is more efficient than the algorithm of iCFP.

参考文献/References:

[1]AGRAWAL R, SRIKANT R. Fast algorithms for mining association rules[C]//Proceedings 20th International Conference on VLDB.Morgan Kaufmann, 1994: 487499. 
[2]颜跃进, 李舟军, 陈火旺. 频繁项集挖掘算法[J]. 计算机科学, 2004,31(3):112114. 
 YAN Yuejin, LI Zhoujun, CHEN Huowang. Frequent item sets mining algorithms[J].Computer Science, 2004,31(3):112114.
[3]颜跃进, 李舟军, 陈火旺. 基于FPTree有效挖掘最大频繁项集[J]. 软件学报, 2005,16(2):215222.
YAN Yuejin, LI Zhoujun, CHEN Huowang. Efficiently mining of maximal frequent item sets based on FPTree[J]. Journal of Software,2005,16(2):21522.
[4]AGRAWAL R, IMIELINSKI T, SWAMI A. Mining association rules between sets of items in large database[C]//Proc of the ACM SIGMOD Conf on Management of Data.Washington, DC 1993: 207216. 
[5]SRIKANT R, AGRAWAL R. Mining sequential patterns: generalizations and performance improvements[C]// Proc of the 5th Int’1 Conf on Extending Database Technology. Berlin: SpringerVerlag, 1996: 317.
[6]PEI J, HAN J, PINTO H, et al. Mining sequential patterns efficiently by prefixprojected pattern growth[C]// The 17th Int’1 Conf on Data Engineering.Heidelberg, Germany, 2001:195201.
[7]BURDICK D, CALIMIM M, GEHRKE J. A maximal frequent itemset algorithm for transactional database[C]//Piscataway,NJ: IEEE Press, 2001: 443452.
[8]陆介平, 刘月波, 倪巍伟. 基于PrefixSpan的快速交互序列模式挖掘算法[J]. 东南大学学报:自然科学版, 2005, 35(5): 692696.
LU Jieping, LIU Yuebo, NI Weiwei. Fast interactive sequential pattern mining algorithm based on PrefixSpan[J]. Journal of Southeast University:Natural Science Edition, 2005, 35(5): 692696.
[9]ZHU Qunxiong, LIN Xiaoyong. Mining frequent patterns with incremental updating frequent pattern tree[C]//The 6th World Congress on Intelligent Control and Automation. Dalian,2006: 125128. 
[10]LENG Kaisong. Interactive constrained frequentpattern mining system[C]//Proc of the Int’1 Database Engineering and Applications Symposium (IDEAS’04). Los Alamitos, CA: IEEE Computer Society Press, 2004:4858.

备注/Memo

备注/Memo:
收稿日期:2008-12-16.
基金项目:陕西省自然科学基金资助项目(2004f283); 西安市科技创新支撑—应用发展研究计划资助项目(YF07024)
作者简介:
孟彩霞,女,1966年生,副教授,主要研究方向为数据库、数据挖掘等 .
 E-mail:mcxmcx@xiyou.edu.cn
更新日期/Last Update: 2009-05-04