决策树剪枝加强的关联规则分类方法

doi:10.3778/j.issn.1002-8331.2206-0476

摘要/Abstract

摘要： 传统关联规则挖掘在面临分类决策问题时，易出现非频繁规则遗漏、预测精度不高的问题。为得到正确合理且更为完整的规则，提出了一种改进方法DT-AR（decision tree-association rule algorithm），利用决策树剪枝策略对关联规则集进行补充。该方法利用FP-Growth（frequent pattern growth）算法得到关联规则集，利用C4.5算法构建后剪枝决策树并提取分类规则，在进行置信度迭代筛选后与关联规则集取并集修正，利用置信度作为权重系数采取投票法进行分类。实验结果表明，与传统关联规则挖掘和决策树剪枝方法相比，该方法得到的规则在数据集分类结果上更准确。

关键词: 数据挖掘, 决策树剪枝, 关联规则分类, 数据分类

Abstract: Solving the problem of mining rules assisting decision making with traditional association rule comes along with omission of infrequent rules and the low prediction accuracy usuallily. In order to obtain more correct, reasonable and complete rules, a method, DT-AR（decision tree-association rule algorithm） is proposed, which supplements the association rule set by decision tree pruning strategy. Firstly, the method gets the association rule set by FP-Growth（frequent pattern growth）. And then it constructs the post pruning decision tree and extracts classification rules. After iterative confidence filtering, it makes corrections to the association rule set to take the union with the classification rule set. Finally, it makes data classification by voting method, with the conifidence as the weight. The experimental results show that the rules of DT-AR get more accurate results in the prediction compared with the method of association rule and decision tree pruning.

Key words: data mining, decision tree pruning, association rule classification, data classification

范劭博, 张中杰, 黄健. 决策树剪枝加强的关联规则分类方法[J]. 计算机工程与应用, 2023, 59(5): 87-94.

FAN Shaobo, ZHANG Zhongjie, HUANG Jian. Association Rule Classification Method Strengthened by Decision Tree Pruning[J]. Computer Engineering and Applications, 2023, 59(5): 87-94.

参考文献

[1] AGRAWAL R，IMIELINSKI T，SWAMI A.Database mining：a performance perspective[J].IEEE Transactions on Knowledge and Data Engineering，1993（6）：914-925.
[2] 周志华.机器学习[M].北京：清华大学出版社，2016：75-83.
ZHOU Z H.Maching learning[M].Beijing：Tsinghua University Press，2016：75-83.
[3] LIU B，HSU W，MA Y.Integrating classification and association rule mining[C]//Fourth International Conference on Knowledge Discovery and Data Mining，New York，1998：80-86.
[4] SIVANANTHAM S，MOHANRAJ V，SURESH Y，et al.Rule precision index classifier：an associative classifier with a novel pruning measure for intrusion detection[J].Personal and Ubiquitous Computing，2021：1-9.
[5] JM A，BKA B.A compact and understandable associative classifier based on overall coverage[J].Procedia Computer Science，2020，170：1161-1167.
[6] MABU S，GOTOH S，OBAYASHI M，et al.A random-forests-based classifier using class association rules and its application to an intrusion detection system[J].Artificial Life & Robotics，2016，21（3）：371-377.
[7] 王玲，李树林，吴璐璐.基于定量关联规则树的分类及回归预测算法[J].工程科学学报，2016，38（6）：886-892.
WANG L，LI S L，WU L L.Categorization and regression algorithm based on the quantitative association rule tree[J].Chinese Journal of Engineering，2016，38（6）：886-892.
[8] 崔巍，贾晓琳，樊帅帅，等.一种新的不均衡关联分类算法[J].计算机科学，2020，47（S1）：488-493.
CUI W，JIA X L，FAN S S，et al.New associative classification algorithm for imbalanced data[J].Computer Science，2020，47（S1）：488-493.
[9] 翟悦，李楠，于文武.基于扩展概念格的带约束关联分类规则挖掘方法[J].大连交通大学学报，2021，42（4）：88-93.
ZHAI Y，LI N，YU W W.Constrained association rule classification approach based on extended concept lattice[J].Journal of Dalian Jiaotong University，2021，42（4）：88-93.
[10] 佟玉军，李煜，陈文实，等.一个改进的分类关联规则挖掘算法[J].辽宁工业大学学报（自然科学版），2011，31（5）：287-290.
TONG Y J，LI Y，CHEN W S，et al.Improved class association rule mining algorithm[J].Journal of Liaoning University of Technology（Natural Science Edition），2011，31（5）：287-290.
[11] MAHDI M A，HOSNY K M，ELHENAWY I.FR-Tree：a novel rare association rule for big data problem[J].Expert Systems with Applications，2022，187：1-12.
[12] SANZ J，SESMA-SARA M，BUSTINCE H.A fuzzy association rule-based classifier for imbalanced classification problems[J].Information Sciences，2021，577（4）：266-279.
[13] DUDA P，JAWORSKI M，PIETRUCZUK L，et al.A novel application of Hoeffding’s inequality to decision trees construction for data streams[C]//2014 International Joint Conference on Neural Networks（IJCNN），Beijing，2014：3324-3330.
[14] 张珏，田建学，董婷.一种基于代价敏感集成决策树的不平衡数据分类方法研究[J].榆林学院学报，2021，31（2）：53-55.
ZHANG Y，TIAN J X，DONG T.Research on cost senstive decision tree for imbalanced data[J].Journal of Yulin University，2021，31（2）：53-55.
[15] 赵宁杰，李雪飞.基于bagging思想的决策树分类算法研究[J].北京服装学院学报（自然科学版），2020，40（3）：43-48.
ZHAO N J，LI X F.Research on decision tree classification algorithm based on the idea of bagging[J].Journal of Beijing Institute of Fashion Technology（Natural Science Edition），2020，40（3）：43-48.
[16] 段化娟，尉永清，刘培玉，等.一种面向不平衡分类的改进多决策树算法[J].广西师范大学学报（自然科学版），2020，38（2）：72-80.
DUAN H J，WEI Y Q，LIU P Y，et al.An improved multi-decision tree algorithm for imbalanced classification[J].Journal of Guangxi Normal University（Natural Science Edition），2020，38（2）：72-80.