The Semi-Supervised SVM Classification Algorithm Based on Two-Stage Learning

TAO Xinmin; CAO P; ong; SONG Shaoyu

Volume 41 Issue 1

Feb. 2012

Turn off MathJax

Article Contents

Abstract

References

INFORMATION AND CONTROL > 2012 > 41(1): 7-13.

TAO Xinmin, CAO P, ong, SONG Shaoyu. The Semi-Supervised SVM Classification Algorithm Based on Two-Stage Learning[J]. INFORMATION AND CONTROL, 2012, 41(1): 7-13.

Citation:

TAO Xinmin, CAO P, ong, SONG Shaoyu. The Semi-Supervised SVM Classification Algorithm Based on Two-Stage Learning[J]. INFORMATION AND CONTROL, 2012, 41(1): 7-13.

Citation:

TAO Xinmin, CAO P, ong, SONG Shaoyu. The Semi-Supervised SVM Classification Algorithm Based on Two-Stage Learning[J]. INFORMATION AND CONTROL, 2012, 41(1): 7-13.

PDF (1261 KB)

The Semi-Supervised SVM Classification Algorithm Based on Two-Stage Learning

College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China

More Information

Received Date: December 28, 2010
Revised Date: July 11, 2011
Published Date: February 19, 2012

Graphical Abstract

Abstract

Abstract

A semi-supervised support vector machine(semi-supervised SVM) classification algorithm is proposed based on two-stage learning.A graph-based label propagation algorithm is used to provide initial pseudo labels for the unlabeled samples.Andκ-nearest graph is applied to distinguishing and removing the possible noisy samples.Then the denoised samples are inputted into the support vector machine(SVM) as labeled samples,so that the global information of the whole samples can be utilized by SVM when it is used in the training to improve the classification accuracy.The experiment results show that compared with other semi-supervised learning algorithms,the proposed method improves classification performance and is of higher robustness in the case of fewer labeled training samples.
- SVM(support vector machine),
- semi-supervised,
- two-stage learning,
- pseudo label

FullText(HTML)

References (12)

References

[1]	韩立群.人工神经网络教程[M].第1版.北京:北京邮电大学出版,2006:185-194.Han L Q.The course of artificial neural networks[M].1st ed.Beijing:Beijing University of Posts and Telecommunications Press,2006:185-194.
[2]	Joachims T.Transductive inference for text classification using support vector machines[C]//Proceedings of the 16th International Conference on Machine Learning.New York,USA:ACM,1999:200-209.
[3]	Ting K M,Zhu L.Boosting support vector machines successfully[M]//Lecture Notes in Computer Science:vol.5519.Berlin,Germany:Springer-Verlag,2009:509-518.
[4]	Belkin M,Niyogi P.Manifold regularization[J].Machine Learning Research,2006,7(8):31-42.
[5]	Cortes C,Vapnik V.Support vector networks[J].Machine Learning,1995,7(3):273-297.
[6]	Zhu X J.Semi-supervised learning literatures survey[D].Wisconsin,USA:University of Wiscinsin-Madison,2005.
[7]	Zhu X,Ghahramani Z,Lafferty J.Semi-supervised learning using Gaussian fields and harmonic functions[C]//Proceedings of the Twentieth International Conference on Machine Learning.Piscataway,N J,USA:IEEE,2003:912-919.
[8]	Monroy I,Benitez R,Escudero G,et al.A semi-supervised approach to fault diagnosis for chemical processes[J].Computers and Chemical Engineering,2010,34(5):631-642.
[9]	Li C L,Wu C G.A new semi-supervised support vector machine learning algorithm based on active learning[C]//Proceedings of the 2010 2nd International Conference on Future Computer and Communication.Piscataway,NJ,USA:IEEE,2010:3638-3641.
[10]	Zhu X,Ghahramani Z.Learning from labeled and unlabeled data with label propagation[D].Pennsylvania,USA:Carnegie Mellon University,2002.
[11]	Johnson R,Zhang T.On the effectiveness of Laplacian normalization for graph semi-supervised learning[J].Machine Learning Research,2007,8(1):1489-1517.
[12]	Gong Y C,Chen C L.Semi-supervised method for gene expression data classification with Gaussian fields and harmonic functions[C]//Proceedings of the 19th International Conference on Pattern Recognition.Piscataway,NJ,USA:IEEE,2008:2217-2220.