基于不平衡数据的特征选择算法研究

doi:10.19678/j.issn.1000-3428.0059373

摘要/Abstract

摘要： 不平衡分类问题广泛存在于医疗、经济等领域，对于不平衡数据集分类，特别是高维数据分类时，有效的特征选择算法至关重要。然而多数特征选择算法未考虑特征协同的影响，导致分类性能下降。对FAST特征选择算法进行改进，并考虑特征的协同作用，提出一种新的特征选择算法FSBS。运用AUC对特征进行评估，以相互增益衡量协同作用大小，选出有效特征，进而对不平衡数据进行分类。实验结果表明，该算法能有效地选择特征，尤其在特征数量较少的情况下可保持较高的分类准确率。

关键词: 特征选择, 不平衡数据, FSBS算法, 特征协同, 分类准确率

Abstract: The problem of unbalanced classification widely exists in medical,economic and other fields.Research shows that for the classification of unbalanced data sets,especially when the data is high-dimensional,an effective feature selection algorithm is crucial.However,most feature selection algorithms do not consider the impact of feature synergy,resulting in a decrease in classification performance.Considering the synergy of features,this paper proposes a new feature selection algorithm,FSBS,on the basis of the improved FAST feature selection algorithm.This algorithm employs AUC to evaluate the features,and the mutual gain is used to measure the magnitude of synergy.Then the effective features are selected and the unbalanced data are classified.Experimental results show that the proposed algorithm can effectively select features and improve the classification performance,especially when the number of features is small.

Key words: feature selection, unbalanced data, FSBS algorithm, feature synergy, classification accuracy

中图分类号:

TP18

王俊红, 赵彬佳. 基于不平衡数据的特征选择算法研究[J]. 计算机工程, 2021, 47(11): 100-107.

WANG Junhong, ZHAO Binjia. Research on Feature Selection Algorithms Based on Unbalanced Data[J]. Computer Engineering, 2021, 47(11): 100-107.

http://www.ecice06.com/CN/Y2021/V47/I11/100

图/表 10

20211113143705

20211113143708

20211113143711

20211113143714

20211113143717

20211113143720

20211113143725

20211113143728

20211113143732

20211113143735

参考文献

[1] LI J,LIU H.Challenges of feature selection for big data analytics[J].IEEE Intelligent Systems,2017,32(2):9-15.
[2] BOLON-CANEDO V,SANCHEZ-MARONO N,ALONSO-BETANZOS A.Feature selection for high dimensional data[J].Progress in ArtificialIntelligence,2016,5(2):65-75.
[3] DESSÌ N,PES B.Similarity of feature selection methods:an empirical study across data intensive classification tasks[J].Expert Systems with Applications,2015,42(10):4632-4642.
[4] 初蓓,李占山,张梦林,等.基于森林优化特征选择算法的改进研究[J].软件学报,2018,29(9):2547-2558. CHU B,LI Z S,ZHANG M L,et al.Research on improvements of feature selection using forest optimizationalgorithm[J].Journal of Software,2018,29(9):2547-2558.(in Chinese)
[5] 于巧,姜淑娟,张艳梅,等.分类不平衡对软件缺陷预测模型性能的影响研究[J].计算机学报,2018,41(4):809-824. YU Q,JIANG S J,ZHANG Y M,et al.The impact study of class imbalance on the performance of software defect prediction models[J].Chinese Journal of Computers,2018,41(4):809-824.(in Chinese)
[6] HUANG X,ZOU Y,WANG Y,et al.Cost-sensitive sparse linear regression for crowd counting with imbalanced training data[C]//Proceedings of International Conference on Multimedia and Expo.Washington D.C.,USA:IEEE Press,2016:1-6.
[7] FORMAN G.An extensive empirical study of feature selection metrics for text classification[J].Journal of Machine Learning Research,2003,3(2):1289-1305.
[8] CHEN X,WASIKOWSKI M.Fast:a roc-based feature selection metric for small samples and imbalanced data classificationproblems[C]//Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2008:124-132.
[9] SUN Z,BEBIS G,MILLER R H,et al.Object detection using feature subset selection[J].Pattern Recognition,2004,37(11):2165-2176.
[10] SOMOL P,PUDIL P,KITTLER J,et al.Fast branch &bound algorithms for optimal feature selection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(7):900-912.
[11] WUTZL B,LEIBNITZ K,RATTAY F,et al.Genetic algorithms for feature selection when classifying severe chronic disorders of consciousness[J].PloSone,2019,14(7):1265-1278.
[12] 李元香,项正龙,张伟艳.模拟退火算法的弛豫模型与时间复杂性分析[J].计算机学报,2020,43(5):796-811. LI Y X,XIANG Z L,ZHANG W Y.A relaxation model and time complexity analysis for simulated annealing algorithm[J].Chinese Journal of Computers,2020,43(5):796-811.(in Chinese)
[13] GHIMATGAR H,KAZEMI K,HELFROUSH M S,et al.An improved feature selection algorithm based on graph clustering and ant colony optimization[J].Knowledge Based Systems,2018,159:270-285.
[14] IMOLA F.A survey of dimension reduction techniques[J].Neoplasia,2002,7(5):475-485.
[15] KIRA K,RENDELL L A.Feature selection problem:traditional methods and a new algorithm[C]//Proceedings of the 20th National Conference on Artificial Intelligence.San Jose,USA:AAAI Press,1992:129-134.
[16] KONONENKO I.Estimating attributes:analysis and extensions of RELIEF[C]//Proceedings of European Conference on Machine Learning.Berlin,Germany:Springer,1994:171-182.
[17] 张振海,李士宁,李志刚,等.一类基于信息熵的多标签特征选择算法[J].计算机研究与发展,2013,50(6):1177-1184. ZHANG Z H,LI S N,LI Z G,et al.Multi-label feature selection algorithm based on information entropy[J].Journal of Computer Research and Development,2013,50(6):1177-1184.(in Chinese)
[18] PÁRRAGA-VALLE J,GARCÍA-BERMÚDEZ R,ROJAS F,et al.Evaluating mutual information and chi-square metrics in text features selection process:a study case applied to the text classification in PubMed[C]//Proceedings of International Work-Conference on Bioinformatics and Biomedical Engineering.Berlin,Germany:Springer,2020:636-646.
[19] NAGPAL A,SINGH V.Feature selection from high dimensional data based on iterative qualitative mutual information[J].Journal of Intelligent and Fuzzy Systems,2019,36(6):5845-5856.
[20] CHAWLA N V,BOWYER K W,HALL L O,et al.SMOTE:synthetic minority over-sampling technique[J].Journal of Artificial Intelligence Research,2002,16(1):321-357.
[21] ARIDAS C K,KARLOS S,KANAS V G,et al.Uncertainty based under-sampling for learning naive Bayes classifiers under imbalanced data sets[J].IEEE Access,2020,7:2122-2133.
[22] ZHANG S.Decision tree classifiers sensitive to heterogeneous costs[J].Journal of Systems and Software,2012,85(4):771-779.
[23] LOYOLAGONZALEZ O,MARTINEZTRINIDAD J F,CARRASCOOCHOA J A,et al.Cost-sensitive pattern-based classification for class imbalance problems[J].IEEE Access,2019,7:60411-60427.
[24] ABDOH S F,RIZKA M A,MAGHRABY F A,et al.Cervical cancer diagnosis using random forest classifier with SMOTE and feature reduction techniques[J].IEEE Access,2018,5:59475-59485.
[25] SUN J,LEE Y,LI H,et al.Combining B&B-based hybrid feature selection and the imbalance-oriented multiple-classifier ensemble for imbalanced credit risk assessment[J].Technological & Economic Development of Economy,2015,21(3):351-378.
[26] BIAN J,PENG X,WANG Y,et al.An efficient cost-sensitive feature selection using chaos genetic algorithm for class imbalance problem[J].Mathematical Problems in Engineering,2016(10):1-9.
[27] MOAYEDIKIA A,ONG K,BOO Y L,et al.Feature selection for high dimensional imbalanced class data using harmony search[J].Engineering Applications of Artificial Intelligence,2017,57:38-49.
[28] GUYON I,ELISSEEFF A.An introduction to variable and feature selection[J].Journal of Machine Learning Research,2003,3(6):1157-1182.
[29] JAKULIN A,BRATKO I.Testing the significance of attribute interactions[C]//Proceedings of the 21st IEEE International Conference on Machine Learning.Washington D.C.,USA:IEEE Press,2004:409-416.
[30] JAKULIN A.Attribute interactions in machine learning[D].[S.1.]:University of Ljubljana,2003.

选择文件类型/文献管理软件名称

选择包含的内容