计算机科学 ›› 2020, Vol. 47 ›› Issue (6A): 89-94.doi: 10.11896/JsJkx.190500089

• 人工智能 • 上一篇    下一篇

基于ECOC的多类代价敏感分类方法

吴崇明1, 王晓丹2, 薛爱军2, 来杰2   

  1. 1 西京学院商学院 西安 710123;
    2 空军工程大学防空反导学院 西安 710051
  • 发布日期:2020-07-07
  • 通讯作者: 王晓丹(afeu_w@163.com)
  • 作者简介:w_9887@163.com
  • 基金资助:
    国家自然科学基金(61876189,61273275,61703426)

Multiclass Cost-sensitive Classification Based on Error Correcting Output Codes

WU Chong-ming1, WANG Xiao-dan2, XUE Ai-Jun2 and LAI Jie2   

  1. 1 Business School,XiJing University,Xi’an 710123,China
    2 College of Air and Missile Defense,Air force Engineering University,Xi’an 710051,China
  • Published:2020-07-07
  • About author:WU Chong-ming, born in 1966, Ph.D, associate professor.Hismain research interests include machine learning and intelligent information processing.
    WANG Xiao-dan, born in 1966, Ph.D, professor.Her research interests include machine learning, pattern recognition.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China(61876189,61273275,61703426).

摘要: 研究了基于纠错输出编码实现多类代价敏感分类的方法,提出了一种新的将多类代价敏感分类问题分解为多个二类代价敏感分类问题的框架。为获得其中每个二类代价敏感基分类器的二类代价矩阵,提出了利用已知多类代价矩阵计算误分类代价的期望值的方法,给出了计算二类代价矩阵的通用计算公式。为验证所提方法的有效性,在人工和UCI数据集上将其与现有方法进行了比较,实验结果表明所提方法具有相似甚至更好的性能。

关键词: 多类代价矩阵, 多类代价敏感分类, 二类代价矩阵, 纠错输出编码

Abstract: Approach of multiclass cost-sensitive classification based on error correcting output codes is studied in this paper,and a new framework to decompose the complex multiclass cost-sensitive classification problem into a series of binary cost-sensitive classification problems is proposed.In order to obtain the binary cost matrix of each binary cost-sensitive base classifier,a method of computing the expected misclassification costs from the given multiclass cost matrix is proposed,and the general formula for computing the binary costs are given.Experimental results on artificial datasets and UCI datasets show that the proposed method has similar or even better performance in comparison with the existing methods.

Key words: Binary cost matrix, Error correcting output codes, Multiclass cost matrix, Multiclass cost-sensitive classification

中图分类号: 

  • TP391
[1] ALI S,MAJID A,JAVED S G,et al.Can-CSC-GBE:Developing Cost-sensitive Classifier with Gentleboost Ensemble for breast cancer classification using protein amino acids and imbalanced data.Computers In Biology and Medicine,2016,73:38-46.
[2] KIM Y J,BAIK B,CHO S.Detecting financial misstatements with fraud intention using multi-class cost-sensitive learning.Expert Systems With Applications,2016,62:32-43.
[3] ZHOU Z H,LIU X Y.On multi-class cost-sensitive learning .Computational Intelligence,2010,26(3):232-257.
[4] KULLUK S,ZBAKIR L,TAPKAN P Z,et al.Cost-sensitive meta-learning classifiers:MEPAR-miner and DIFACONN-miner.Knowledge-Based Systems,2016,98:148-161.
[5] ZHANG G Q,SUN H J,et al.Cost-sensitive dictionary learning for face recognition.Pattern Recognition,2016,60:613-629.
[6] JIANG L X.Cost-sensitive Bayesian network classifiers.Pattern Recognition Letters,2014,45:211-216.
[7] BEZ A,BIELZA C,LARRAAGA P.Cost-sensitive selective nave Bayes classifiers for predicting the increase of the h-index for scientific Journals.Neurocomputing,2014,135:42-52.
[8] CHEN Z,XIAO X Y,LI C S,et al.Real-time transient stability status prediction using cost-sensitive extreme learning machine.Neural Computing and Application,2016,27:321-331.
[9] ZHANG L,ZHANG D.Evolutionary Cost-Sensitive Extreme Learning Machine.IEEE Transactions on Nueral Networks and Learning Systems,2017,28(12):3045-3060.
[10] DIETTERICH T,BAKIRI G.Solving multiclass learning problems via error-correcting output codes.Journal of Artificial Intelligence Research,1995,34(2):263-268.
[11] LEI L,WANG X D.An Overview of Multi-Classification Based on Error-Correcting Output Codes.Acta Electronica Sinica,2014,42(9):1794-1800.
[12] BAI X L,NIWAS S I,LIN W S,et al.Learning ECOC code matrix for multiclass classification with application to Glaucoma diagnosis.Journal of Medical Systems,2016,40:78.
[13] LIU K H,ZENG Z H,NG V T Y.A hierarchical ensemble of ECOC for cancer classification based on multi-class microarray data.Information Sciences,2016,349-350:102-118.
[14] SANTHANAM V,MORARIU V I,HARWOOD D,et al.A nonparametricapproach to extending generic binary classifiersfor multi-classification.Pattern Recognition,2016,58(1):149-158.
[15] LIN H T.From ordinal ranking to binary classification.California Institute of Technology,2008.
[16] LANGFORD J,BEYGELZIMER A.Sensitive error correcting output codes.Lecture Note in Artificial Intelligence,2005,3559(1):158-172.
[17] LIN H T.Reduction from cost-sensitive multiclass classification to one-versus-one binary classification//JMLR:Workshop and Conference Proceedings,2014,39:371-386.
[18] ASUNCION A,NEWMAN D.School of Information and Computer Sciences//UCI machine learning repository.Irvine,CA,USA:University of California,2007.
[19] BEYGELZIMER A,LANGFORD J,RAVIKUMAR P.Errorcorrecting tournaments.http://arxiv.org/abs/0902.3176.
[20] TING K M.An instance-weighting method to induce cost-sensitive trees.IEEE Transactions on Knowledge and Data Engineering,2002,14(3):659-665.
[21] ZHANG L,ZHANG D.Evolutionary Cost-Sensitive Extreme Learning Machine.IEEE Transactions on Nueral Networks and learning Systems,2017,28(12):3045-3060.
[1] 梁辰,李成海.
一种新的半监督入侵检测方法
Novel Intrusion Detection Method Based on Semi-supervised Clustering
计算机科学, 2016, 43(5): 87-90. https://doi.org/10.11896/j.issn.1002-137X.2016.05.016
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!