Journal of Zhejiang University SCIENCE C

, Volume 14, Issue 9, pp 722–732 | Cite as

Primal least squares twin support vector regression

Article

Abstract

The training algorithm of classical twin support vector regression (TSVR) can be attributed to the solution of a pair of quadratic programming problems (QPPs) with inequality constraints in the dual space. However, this solution is affected by time and memory constraints when dealing with large datasets. In this paper, we present a least squares version for TSVR in the primal space, termed primal least squares TSVR (PLSTSVR). By introducing the least squares method, the inequality constraints of TSVR are transformed into equality constraints. Furthermore, we attempt to directly solve the two QPPs with equality constraints in the primal space instead of the dual space; thus, we need only to solve two systems of linear equations instead of two QPPs. Experimental results on artificial and benchmark datasets show that PLSTSVR has comparable accuracy to TSVR but with considerably less computational time. We further investigate its validity in predicting the opening price of stock.

Key words

Twin support vector regression Least squares method Primal space Stock prediction 

CLC number

TP18 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Boser, B.E., Guyon, I.M., Vapnik, V.N., 1992. A Training Algorithm for Optimal Margin Classifiers. Proc. 5th Annual Workshop on Computational Learning Theory, p.144–152. [doi:10.1145/130385.130401]CrossRefGoogle Scholar
  2. Chen, Z.Y., Fan, Z.P., 2012. Distributed customer behavior prediction using multiplex data: a collaborative MK-SVM approach. Knowl.-Based Syst., 35:111–119. [doi:10. 1016/j.knosys.2012.04.023]CrossRefGoogle Scholar
  3. Cong, H.H., Yang, C.F., Pu, X.R., 2008. Efficient Speaker Recognition Based on Multi-class Twin Support Vector Machines and GMMs. IEEE Conf. on Robotics, Automation and Mechatronics, p.348–352. [doi:10.1109/RAMECH.2008.4681433]Google Scholar
  4. Ding, S.F., Qi, B.J., 2012. Research of granular support vector machine. Artif. Intell. Rev., 38(1):1–7. [doi:10.1007/s10462-011-9235-9]CrossRefGoogle Scholar
  5. Ding, S.F., Su, C.Y., Yu, J.Z., 2011. An optimizing BP neural network algorithm based on genetic algorithm. Artif. Intell. Rev., 36(2):153–162. [doi:10.1007/s10462-011-9208-z]CrossRefGoogle Scholar
  6. Huang, H.J., Ding, S.F., 2012. A novel granular support vector machine based on mixed kernel function. Int. J. Dig. Cont. Technol. Its Appl., 6(20):484–492. [doi:10.4156/jdcta.vol6.issue20.52]Google Scholar
  7. Jayadeva, Khemchandani, R., Chandra, S., 2007. Twin support vector machines for pattern classification. IEEE Trans. Pattern Anal. Mach. Intell., 29(5):905–910. [doi:10.1109/TPAMI.2007.1068]CrossRefGoogle Scholar
  8. Liu, Y., Yang, J., Li, L., Wu, W., 2012. Negative effects of sufficiently small initial weights on back-propagation neural networks. J. Zhejiang Univ.-Sci. C (Comput. & Electron.), 13(8):585–592. [doi:10.1631/jzus.C1200008]CrossRefGoogle Scholar
  9. Mangasarian, O.L., Wild, E.W., 2006. Multisurface proximal support vector machine classification via generalized eigenvalues. IEEE Trans. Pattern Anal. Mach. Intell., 28(1): 69–74. [doi:10.1109/TPAMI.2006.17]CrossRefGoogle Scholar
  10. Moraes, R., Valiati, J.F., Neto, W.P.G., 2013. Document-level sentiment classification: an empirical comparison between SVM and ANN. Exp. Syst. Appl., 40(2):621–633. [doi:10.1016/j.eswa.2012.07.059]CrossRefGoogle Scholar
  11. Osuna, E., Freund, R., Girosi, F., 1997. An Improved Training Algorithm for Support Vector Machines. Proc. IEEE Workshop on Neural Networks for Signal Processing, p.276–285. [doi:10.1109/NNSP.1997.622408]Google Scholar
  12. Pan, H., Zhu, Y.P., Xia, L.Z., 2013. Efficient and accurate face detection using heterogeneous feature descriptors and feature selection. Comput. Vis. Image Understand., 117(1):12–28. [doi:10.1016/j.cviu.2012.09.003]CrossRefGoogle Scholar
  13. Peng, X.J., 2010a. Primal twin support vector regression and its sparse approximation. Neurocomputing, 73(16–18): 2846–2858. [doi:10.1016/j.neucom.2010.08.013]CrossRefGoogle Scholar
  14. Peng, X.J., 2010b. TSVR: an efficient twin support vector machine for regression. Neur. Networks, 23(3):365–372. [doi:10.1016/j.neunet.2009.07.002]CrossRefGoogle Scholar
  15. Platt, J.C., 1999. Using Analytic QP and Sparseness to Speed Training of Support Vector Machines. In: Kearns, M., Solla, S., Cohn, D. (Eds.), Advances in Neural Information Processing Systems 11. MIT Press, Cambridge, MA, p.557–563.Google Scholar
  16. Suykens, J.A.K., van de Walle, J., 2001. Optimal control by least squares support vector machines. Neur. Networks, 14(1):23–35. [doi:10.1016/S0893-6080(00)00077-0]CrossRefGoogle Scholar
  17. Vapnik, V.N., 1995. The Nature of Statistical Learning Theory. Springer-Verlag, New York. [doi:10.1007/978-1-4757-2440-0]CrossRefMATHGoogle Scholar
  18. Wu, J.X., 2012. Efficient HIK SVM learning for image classification. IEEE Trans. Image Process., 21(10):4442–4453. [doi:10.1109/TIP.2012.2207392]MathSciNetCrossRefGoogle Scholar
  19. Xu, X.Z., Ding, S.F., Shi, Z.Z., Zhu, H., 2012. A novel opti-mizing method for RBF neural network based on rough set and AP clustering algorithm. J. Zhejiang Univ.-Sci. C (Comput. & Electron.), 13(2):131–138. [doi:10.1631/jzus.C1100176]CrossRefGoogle Scholar
  20. Zhang, X.S., Gao, X.B., Wang, Y., 2009. Twin support vector machines for MCs detection. J. Electron. (China), 26(3): 318–325. [doi:10.1007/s11767-007-0211-0]CrossRefGoogle Scholar
  21. Zhong, P., Xu, Y.T., Zhao, Y.H., 2012. Training twin support vector regression via linear programming. Neur. Comput. Appl., 21(2):399–407. [doi:10.1007/s00521-011-0525-6]CrossRefGoogle Scholar

Copyright information

© Journal of Zhejiang University Science Editorial Office and Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.School of Computer Science and TechnologyChina University of Mining and TechnologyXuzhouChina
  2. 2.Key Lab of Intelligent Information Processing, Institute of Computing TechnologyChinese Academy of SciencesBeijingChina

Personalised recommendations