基于概念格的多值属性关联规则挖掘

计算机科学 ›› 2014, Vol. 41 ›› Issue (3): 267-271.

基于概念格的多值属性关联规则挖掘

郭晓波,赵书良,王长宾,赵娇娇,刘军丹

河北师范大学数学与信息科学学院石家庄050024;河北师范大学数学与信息科学学院石家庄050024;河北师范大学数学与信息科学学院石家庄050024;河北师范大学数学与信息科学学院石家庄050024;河北师范大学数学与信息科学学院石家庄050024

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受河北省科学技术研究与发展计划项目(072435158D,09213515D,09213575D),河北师范大学硕士基金(201102002)资助

Multi-valued Attribute Association Rules Mining Based on Concept Lattice

GUO Xiao-bo,ZHAO Shu-liang,WANG Chang-bin,ZHAO Jiao-jiao and LIU Jun-dan

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 针对传统关联规则挖掘算法不利于用户选择关键数据进行分析、无法处理多值属性数据及效率低下等问题,提出了基于KAF因子和CHF因子的Apriori改进算法来进行多值属性关联规则挖掘,运用概念格理论对多值属性数据进行了重新定义和分类；建立了数据挖掘参数调整机制,以提高算法挖掘效率,方便用户选择关键属性值进行规则挖掘分析。结合某省全员人口数据对算法进行了具体实现和分析。实验结果表明,算法性能具有较大提高。

关键词: 多值属性,概念格,关联规则,Apriori 中图法分类号TP391.1文献标识码A

Abstract: Considering the problems aroused by the traditional association rules mining algorithms which are lack of efficient data selection mechanism for users,especially not conducive to deal with multi-valued attribute data,this paper presented the redefinition and classification of multi-valued attribute data by using conceptual lattice,proposed an improvement of Apriori algorithm based on the KAF factor and the CHF factor to mine multi-valued attribute association rules and established a complete mining parameters adjustment mechanism acting very well in improving the speed and efficiency of mining,which is convenient for users to select key attribute values to mine and analyze rules while improving speed and mining algorithm efficiency．At the end of this paper,we illustrated the advantages of these new methods with the help of experimental data obtained from demographic data of a province,and the realistic application analysis and experimental results turn out that the improved mining algorithm has a better performance.

Key words: Multi-valued attribute,Concept lattice,Association rules,Apriori

郭晓波,赵书良,王长宾,赵娇娇,刘军丹. 基于概念格的多值属性关联规则挖掘[J]. 计算机科学, 2014, 41(3): 267-271. https://doi.org/

GUO Xiao-bo,ZHAO Shu-liang,WANG Chang-bin,ZHAO Jiao-jiao and LIU Jun-dan. Multi-valued Attribute Association Rules Mining Based on Concept Lattice[J]. Computer Science, 2014, 41(3): 267-271. https://doi.org/

参考文献

[1] Wang D X,Xie Q．Analysis of association rule mining on quanti-tative concept lattice [C]∥Artificial Intelligence and Computational Intelligence,LNCS7530．Berlin:Springer-Verlag,2012:142-149
[2] Bay Vo,Bac Le．Interestingness measures for association rules:combination between lattice and hash tables [J]．Expert Systems with Applications,2011,38(9):11630-11640
[3] Srikant R,Agrawal R．Mining quantitative association rules in large relational table [C]∥SIGMOD’96Proceedings of the 1996ACM SIGMOD International Conference on Management of Data．New York:ACM 1996:1-12 (下转第309页)(上接第271页)
[4] Li D C,Zhang M．A new approach of self-adaptive discretization to enhance the Apriori quantitative association rule mining [C]∥ISDEA’12:Proceedings of the 2012Second International Conference on Intelligent System Design and Engineering Application．Washington,DC:IEEE Computer Society,2012:44-47
[5] Prakash S,Parvathi R．Qualitative approach for quantitative association rule mining using fuzzy rule set [J]．Journal of Computational Information Systems,2011,17(6):1879-1885
[6] Mao Yu-xing,Chen Tong-bin,Shi Bo-le．Efficient method formining multiple-Level and generalized association rules [J].Journal of Software,2011,22(12):2965-2980
[7] Lee Y Y C,Hong T P,Chen C H．Mining generalized association rules with quantitative data under multiple support constraints [C]∥ICCCI’10:Proceedings of the Second international conference on Computational collective intelligence:technologies and applications．Berlin:Springer Verlag,2010:224-231
[8] Alatas B,Akin E,Karci A．MODENAR:multi-objective differential evolution algorithm for mining numeric association rules [J]．Applied Soft Computing,2008,8(1):646-656
[9] Pachón álvarez V,Mata Vázquez J．An evolutionary algorithmto discover quantitative association rules from huge databases without the need for an a priori discretization [J]．Export Systems with Applications,2012,39(1):585-593
[10] Martínez-Ballesteros M,Riquelme J．Analysis of measures ofquantitative association rules [C]∥HAIS’11:Proceedings of the 6th international conference on Hybrid artificial intelligent systems．Berlin:Springer Verlag,2011(6679):319-326
[11] Shaharanee I N M,Hadzic F,Dillon T S．Interestingness mea-sures for association rules based on statistical validity [J]．Knowledge-Based Systems,2011,24(3):386-392
[12] Ganter B,Wille R．Formal concept analysis:mathematical foundations [M]．Berlin:Springer Verlag,1999
[13] Gugisch R．Many-valued context analysis using descriptions [C]∥ICCS2001:Conceptual Structures:Broadening the Base Conceptual Structures:Broadening the Base Lecture Notes in Computer Science．Berlin:Springer-Verlag,2001:157-168
[14] Nguyen T T,Hui S C,Chang K．A lattice-based approach formathematical search using formal concept analysis [J]．Expert Systems with Applications,2012,39(5):5820-5828
[15] Ourida B B S,Wafa T．Formal concept analysis based association rules extraction [J]．International Journal of Computer Science Issues,2011,8(4):490-497
[16] Gély A,Medina R,Nourine L．Representing lattices using many-valued relations [J]．Information Sciences,2009,9(16):2729-2739

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed