Abstract
In this study we have developed a robust Support Vector Machines (SVM) scheme of classifying uncertain data. In SVM classification data uncertainty is not addressed efficiently. Furthermore, while traditional SVM methods use a single kernel for learning, multiple kernel schemes are being developed to incorporate a better understanding of all the data features. We combine the multiple kernel learning methods with the robust optimization concepts to formulate the SVM classification problem as a semi-definite programming (SDP) problem and develop its robust counterparts under bounded data uncertainties. We present some preliminary experimental results with some known datasets by introducing noise in the data. Initial analysis shows the robust SDP-SVM model improves classification accuracy for uncertain data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ben-Tal, A., Ghaoui, L.E., Nemirovski, A.S.: Robust Optimization. Princeton Series in Applied Mathematics. Princeton University Press, Princeton (2009)
Bhattacharyya, C., Shivaswamy, P.K., Smola, A.J.: A second order cone programming formulation for classifying missing data. In: Proceedings of Neural Information Processing Systems (NIPS04) (2004)
Bi, J., Zhang, T.: Support vector classification with input data uncertainty. In: Proceedings of Neural Information Processing Systems (NIPS04) (2004)
Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines: And Other Kernel-Based Learning Methods. Cambridge University Press, New York (2000)
Fisher, R.: The use of multiple measurements in taxonomic problems. Ann. Eugen. 7, 179–188 (1936)
Grant, M., Boyd, S.: CVX: Matlab software for disciplined convex programming, Version 1.21. http://cvxr.com/cvx/ (2010)
Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, Berlin (2003)
Lanckriet, G.R.G., Cristianini, N., Bartlett, P., Ghaoui, L.E., Jordan, M.I.: Learning the kernel matrix with semi-definite programming. J. Mach. Learn. Res. 5, 27–72 (2004)
Sigillito, V., Wing, S., Hutton, L., Baker, K.: Classification of radar returns from the ionosphere using neural networks. J. Hopkins APL Tech. Dig. 10, 262–266 (1989)
Trafalis, T.B., Alwazzi, S.A.: Support vector regression with noisy data: a second order cone programming approach. Int. J. Gen. Syst. 36, 237–250 (2007)
Trafalis, T.B., Gilbert, R.C.: Robust support vector machines for classification and computational issues. Optim. Methods Softw. 22, 187–198 (2007)
Vandenberghe, L., Boyd, S.: Semi-definite programming. SIAM Rev. 38, 49–95 (1996)
Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Wolberg, W., Mangasarian, O.: Multisurface method of pattern separation for medical diagnosis applied to breast cytology. Proc. Natl. Acad. Sci. 87, 9193–9196 (1990)
Acknowledgements
The authors would like to thank the reviewers for their valuable inputs and suggested edits. The work of the author Raghav Pant was funded by the Engineering and Physical Sciences Research Council, UK, under Programme Grant EP/I01344X/1. The work of the author Theodore B. Trafalis was conducted at National Research University Higher School of Economics and supported by RSF grant 14-41-00039.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Pant, R., Trafalis, T.B. (2015). SVM Classification of Uncertain Data Using Robust Multi-Kernel Methods. In: Migdalas, A., Karakitsiou, A. (eds) Optimization, Control, and Applications in the Information Age. Springer Proceedings in Mathematics & Statistics, vol 130. Springer, Cham. https://doi.org/10.1007/978-3-319-18567-5_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-18567-5_13
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-18566-8
Online ISBN: 978-3-319-18567-5
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)