基于超椭球支持向量机的兼类文本分类算法

计算机科学 ›› 2013, Vol. 40 ›› Issue (Z11): 98-100.

基于超椭球支持向量机的兼类文本分类算法

秦玉平,王祎,伦淑娴,王秀坤

渤海大学工学院锦州121013;渤海大学数理学院锦州121013;渤海大学新能源学院锦州121013;大连理工大学计算机科学与技术学院大连116024

出版日期:2018-11-16 发布日期:2018-11-16
基金资助:
本文受国家自然科学基金(60974071),辽宁省自然科学基金(201202003),辽宁省教育厅重点实验室项目(LS2010180)资助

Multi-label Text Classification Algorithm Based on Hyper Ellipsoidal SVM

QIN Yu-ping,WANG Yi,LUN Shu-xian and WANG Xiu-kun

Online:2018-11-16 Published:2018-11-16

摘要/Abstract

摘要： 提出一种基于超椭球支持向量机的多类文本分类算法。对每一类样本,利用超椭球支持向量机方法在特征空间求得一个超椭球,使其包含该类尽可能多的样本,同时将噪音点排除在外。分类时,利用待分类样本映射到每个超椭球球心的马氏距离确定其类别。在标准数据集Reuters 21578上的实验结果表明,该算法有效地提高了分类精度。

关键词: 超椭球支持向量机,兼类分类,马氏距离

Abstract: A new multi-label text classification algorithm based on hyper ellipsoidal support vector machines was proposed. To each class sample,the hyper ellipsoidal that includes as much the class samples as possible and push the outlier samples away is trained in the featuer space. For the sample to be classified,the mahalanobis distance from the sample mapping to the center of each hyper ellipsoidal were used to decide the sample classs. The results of the experiment show that the proposed algorithm has a higher classification accuracy.

Key words: Hyper ellipsoidal SVM,Multi-label classification,Mahalanobis distance

秦玉平,王祎,伦淑娴,王秀坤. 基于超椭球支持向量机的兼类文本分类算法[J]. 计算机科学, 2013, 40(Z11): 98-100. https://doi.org/

QIN Yu-ping,WANG Yi,LUN Shu-xian and WANG Xiu-kun. Multi-label Text Classification Algorithm Based on Hyper Ellipsoidal SVM[J]. Computer Science, 2013, 40(Z11): 98-100. https://doi.org/

参考文献

[1] Vapnik V.The Nature of Statistical Learning Theory[M].New York:Springer,1995
[2] Joachims T.Text Categorization with Support Vector Ma-chines:Learning with Many Relevant Feature[A]∥Procee-dings of ECML-98,10th European Conference on Machine Learning[C].Berlin:Springer,1998:137-142
[3] 孙晋文,肖建国.基于SVM的中文文本分类反馈学习技术的研究[J].控制与决策,2004,9(8):927-930
[4] Bennett K P.Combining Support Vector and Mathematical Programming Methods for Classification[A]∥Advances in Kernel Methods:Support Vector Learning[C].Cambridge,MA:MIT press,1999:307-326
[5] Krebel U G.Pairwise Classification and Support Vector Ma-chines[A]∥Advances in Kernel Methods:Support Vector Learning[C].Cambridge,MA:MIT press,1999:255-268
[6] Platt J C,Cristianini N,Shawe-Taylor J.Large Margin DAGs for multiclass classification[A]∥Advances in Neural Information Processing Systems[C]．Cambridge,MA:MIT Press,2000:547-553
[7] 王晔,黄上滕.基于支持向量机的文本兼类标注[J].计算机工程与应用,2006,2(2):182-185
[8] 秦玉平,王秀坤,王春立.基于超球支持向量机的兼类文本分类算法研究[J].计算机工程与应用,2008,4(19):166-168
[9] 秦玉平,陈一荻,王春立,等.一种新的兼类文本分类方法[J].计算机科学,2011,38(11):204-205
[10] Wei X K,Huang G B.Mahalanobis Eillpsoidal Learning Machine for One Class Classification[C]∥International Conference on Machine Learning and Cybernetics．2007:3528-3533
[11] 李永新,薛贞霞.最大间隔椭球形多类分类算法[J].计算机工程,2010,6(7):185-189
[12] 李建民,李永新,薛贞霞.基于马氏椭球学习机的监督野点探测[J].计算机工程与应用,2009,5(13):200-210

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed