基于改进关联分类的两次学习方法

J4 ›› 2014, Vol. 36 ›› Issue (07): 1398-1403.

基于改进关联分类的两次学习方法

黄再祥，周忠眉，何田中

(漳州师范学院计算机科学与工程系，福建漳州 363000)

收稿日期:2012-10-31 修回日期:2013-04-03 出版日期:2014-07-25 发布日期:2014-07-25
基金资助:
国家自然科学基金资助项目（61170129）；福建省自然科学基金资助项目（2013J01259）

A double learning method based on
the improved associative classification

HUANG Zaixiang,ZHOU Zhongmei,HE Tianzhong

(Department of Computer Science and Engineering,Zhangzhou Normal University,Zhangzhou 363000,China)

Received:2012-10-31 Revised:2013-04-03 Online:2014-07-25 Published:2014-07-25

摘要/Abstract

摘要：

关联分类通常产生大量的分类规则，导致在分类新实例时经常产生规则冲突问题。针对这种规则冲突问题，提出了一种基于改进关联分类的两次学习框架。利用频繁且互关联的项集产生分类规则改进关联分类算法，有效减少了规则数。应用改进的关联分类算法产生的一级规则一次性分离出训练集中规则冲突的所有实例。然后，在冲突实例上应用改进的关联分类算法进行第二次学习得到二级规则。分类新实例时，首先利用第一级规则进行分类。如果出现规则冲突，则利用第二级规则分类该实例。实验结果表明，基于改进关联分类的两次学习方法降低了规则冲突比率，并且显著提高了分类准确率。

关键词: 数据挖掘, 关联分类, 两次学习, 规则冲突

Abstract:

Associative classification usually generates numerous rules, resulting in rule conflicts in stage of classification. To address this problem, a double learning method based on the improved associative classification is proposed. The improved associative classification reduces the number of rules significantly by discovering the frequent and mutual associated itemsets. All training conflict instances in training set are separated by applying the first level rules generated by the improved associative classification. Then, the second level rule set is induced by applying the improved associative classification on the conflict instances. When classifying a new instance, the first level rule set is applied. If the rules are not consistent with the instance, the second rules set is used to classify this instance. The experimental results show that the double learning method based on the improved associative classification can improve the classification accuracy effectively.

Key words: data mining;associative classification;double learning;conflict rules

黄再祥，周忠眉，何田中. 基于改进关联分类的两次学习方法[J]. J4, 2014, 36(07): 1398-1403.

HUANG Zaixiang,ZHOU Zhongmei,HE Tianzhong. A double learning method based on
the improved associative classification [J]. J4, 2014, 36(07): 1398-1403.

参考文献

［1］Liu B, Hsu W, Ma Y. Integrating classification and association rule mining［C］∥Proc of the 4th International Conference on Knowledge Discovery and Data Mining (KDD’98), 1998:8086.
［2］Cheng H, Yan X, Han J, et al. Direct discriminative pattern mining for effective classification［C］∥Proc of the 20th International Conference on Knowledge Discovery and Data Mining (ICDE’08), 2008:169178.
［3］Wu Jianhua,Shen Junyi,Fang Jiapei.An associative classification algorithm by distilling effective rules［J］. Journal of Xi’an Jiaotong University, 2009,43(4):2225.(in Chinese)
［4］Jiang Yuanchun, Liu Yezheng, Liu Xiao, et al. Integrating classification capability and reliability in associative classification:A βstronger model ［J］. Expert Systems with Applications, 2010, 37(5):39533961.
［5］Simon G, Kumar V, Li P. A simple statistical model and association rule filtering for classification［C］∥Proc of the 17th International Conference on Knowledge Discovery and Data Mining (KDD’11), 2011:823831.
［6］Yu K, Wu X, Ding W. Causal associative classification［C］∥Proc of the 11th International Conference on Data Mining (ICDM’11), 2011:914923.
［7］Li Xueming, Yang Yang, Qin Dongxia, et al. Associative classification based on closed frequent itemsets［J］. Journal of University of Electronic Science and Technology of China,2012，41(1):104109.(in Chinese)
［8］Agrawal R, Srikant R. Fast algorithms for mining association rules［C］∥Proc of the 20th International Conference on Very Large Data Bases (VLDB’94), 1994:487499.
［9］Li W, Han J, Pei J. CMAR:Accurate and efficient classification based on multiple classassociation rules［C］∥Proc of the 1st International Conference on Data Mining, 2001:369376.
［10］Han J, Pei J, Yin Y. Mining frequent patterns without candidate generation［C］∥Proc of the 2000 ACM SIGMOD International Conference on Management of Data, 2000:112.
［11］Yin X, Han J. CPAR:Classification based on predictive association rules［C］∥Proc of the SIAM International Conference on Data Mining (SDM’03), 2003:331335.
［12］Thabtah F.A review of associative classification mining ［J］. The Knowledge Engineering Review, 2007, 22(1):3765.
［13］Antonie M,Zaiane O,Holte R.Learning to use a learned model:A twostage approach to classification［C］∥Proc of the 6th International Conference on Data Mining, 2006:3342.
［14］Shekhawat P, Dhande S. A classification technique using associative classification［J］. International Journal of Computer Applications, 2011, 20(5):2028.
［15］Lindgren T,Bostrm H.Resolving rule conflicts with double induction［C］∥Proc of the 5th International Symposium on Intelligent Data Analysis, 2003:6067.
［16］Omiecinski E R. Alternative interest measures for mining associations in databases［J］. IEEE Transactions on Knowledge and Data Engineering, 2003, 15(1):5769.
［17］Zhao Y, Karypis G. Criterion functions for document clustering:Experiments and analysis［R］. Technical Report #0140,Ninneapolis:University of Minnesota, 2001.
［18］Thabtah F A, Cowling P, Peng Y. MMAC:A new multiclass, multilabel associative classification approach［C］∥Proc of the 4th International Conference on Data Mining (ICDM’04), 2004:217224.
附中文参考文献：
［3］武建华，沈钧毅，方加沛. 提取有效规则的关联分类算法［J］. 西安交通大学学报，2009，43(4):2225.
［7］李学明，杨阳，秦东霞，等. 基于频繁闭项集的新关联分类算法ACCF［J］. 电子科技大学学报，2012，41(1):104109.

[1]	雷轩, 程光, 张玉健, 郭靓, 张付存. 基于电力网络态势感知平台的告警信息关联分析[J]. 计算机工程与科学, 2023, 45(07): 1197-1208.
[2]	王晨宇, 温浩珉, 郭晟楠, 林友芳, 万怀宇, . 面向快递员揽收到达时间预测的多任务深度时空网络[J]. 计算机工程与科学, 2023, 45(01): 136-144.
[3]	程小刚, 郭韧, 周长利, . 基于理性密码学的分布式隐私保护数据挖掘框架[J]. 计算机工程与科学, 2022, 44(10): 1781-1787.
[4]	王文涛, 马慧芳, 舒跃育, 贺相春. 基于上下文表示的知识追踪方法[J]. 计算机工程与科学, 2022, 44(09): 1693-1701.
[5]	刘云, 肖添. 网络日志数据中条件因果挖掘算法的优化研究[J]. 计算机工程与科学, 2021, 43(09): 1584-1590.
[6]	文凯, 许萌萌, 张许红, . 基于列表结构的加权可擦除项集挖掘算法[J]. 计算机工程与科学, 2021, 43(09): 1676-1683.
[7]	熊中敏, 汪博, 陶然, 郑宗生, 陈明, . 一种基于主属性判定的关联规则挖掘约简算法[J]. 计算机工程与科学, 2021, 43(04): 738-745.
[8]	藏润强, 左美云, 郭鑫鑫. 基于Doc2Vec和BiLSTM的老年患者疾病预测研究[J]. 计算机工程与科学, 2020, 42(12): 2273-2279.
[9]	何望1,2，林果园1,2. 基于FP-Growth改进算法的云服务器故障数据分析[J]. 计算机工程与科学, 2020, 42(05): 770-775.
[10]	谭胜昔，贾金萍，赵斌，吉根林. 动态空间网络中的黑洞模式挖掘算法[J]. 计算机工程与科学, 2020, 42(02): 325-333.
[11]	周忠眉1,2,李家辉1,2. 基于各类支持度阈值独立挖掘的关联改进算法[J]. 计算机工程与科学, 2019, 41(11): 2088-2094.
[12]	何登平1，2，3，何宗浩1,2，李培强1,2. 基于Spark的并行化高效用项集挖掘算法[J]. 计算机工程与科学, 2019, 41(10): 1723-1730.
[13]	陈胜发，贾瑞玉. 基于密度权重Canopy的改进K-medoids算法[J]. 计算机工程与科学, 2019, 41(10): 1823-1828.
[14]	何登平1,2,3，何宗浩1,2. 基于R-list的Top-K高效用项集挖掘算法[J]. 计算机工程与科学, 2019, 41(07): 1318-1324.
[15]	陈倩,刘云,高钰莹. 并行动态位向量频繁闭合序列模式挖掘算法[J]. 计算机工程与科学, 2018, 40(10): 1717-1725.