Nonstationary regression with support vector machines | Neural Computing and Applications Skip to main content
Springer Nature Link
Log in

Nonstationary regression with support vector machines

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

In this work, we introduce a method for data analysis in nonstationary environments: time-adaptive support vector regression (TA-SVR). The proposed approach extends a previous development that was limited to classification problems. Focusing our study on time series applications, we show that TA-SVR can improve the accuracy of several aspects of nonstationary data analysis, namely the tasks of modelling and prediction, input relevance estimation, and reconstruction of a hidden forcing profile.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Notes

  1. Here we employ linear SVRs but, as usual, kernels can be used to produce nonlinear predictors if needed. In fact, in all of our examples we use a Gaussian kernel.

References

  1. Alippi C, Roveri M (2008) Just-in-time adaptive classifiers-part I: detecting nonstationary changes. IEEE Trans Neural Netw 19(7):1145–1153

    Article  Google Scholar 

  2. Andrawis RR, Atiya AF, El-Shishiny H (2011) Forecast combinations of computational intelligence and linear models for the NN5 time series forecasting competition. Int J Forecast 27(3):672–688

    Article  Google Scholar 

  3. Bartlett PL, Ben-Dabid S, Kulkarni SR (2000) Learning changing concepts by exploiting the structure of change. Mach Learn 41(2):153–174

    Article  MATH  Google Scholar 

  4. Ben Taieb S, Bontempi G, Atiya AF, Sorjamaa A (2012) A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition. Expert Syst Appl 39(8):7067–7083

    Article  Google Scholar 

  5. Camci F, Chinnam R (2008) General support vector representation machine for one-class classification of non-stationary classes. Pattern Recognit 41(10):3021–3034

    Article  MATH  Google Scholar 

  6. Cao L, Tay F (2001) Financial forecasting using support vector machines. Neural Comput Appl 10(2):184–192

    Article  MATH  Google Scholar 

  7. Cao L, Tay F (2004) Support vector machine with adaptive parameters in financial time series forecasting. IEEE Trans Neural Netw 14(6):1506–1518

    Article  Google Scholar 

  8. Cao Y, Tung W, Gao J, Protopopescu V, Hively L (2004) Detecting dynamical changes in time series using the permutation entropy. Phys Rev E 70(4):046217

    Article  MathSciNet  Google Scholar 

  9. Casdagli M (1989) Nonlinear prediction of chaotic time series. Phys D Nonlinear Phenom 35(3):335–356

    Article  MATH  MathSciNet  Google Scholar 

  10. Chang MW, Lin CJ, Weng RC (2002) Analysis of nonstationary time series using support vector machines. In: Pattern recognition with support vector machines, SVM 2002, LNCS 2388, Springer, pp 239–255

  11. Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, Cambridge

    Book  Google Scholar 

  12. Drucker H, Burges C, Kaufman L, Smola A, Vapnik V (1997) Support vector regression machines. In: NIPS 9, advances in neural information processing systems, Citeseer, pp 155–161

  13. Ghazikhani A, Monsefi R, Yazdi HS (2013) Online cost-sensitive neural network classifiers for non-stationary and imbalanced data streams. Neural Comput Appl 23(5):1283–1295

    Article  Google Scholar 

  14. Gotelli A, Ellison N (2006) Forecasting extinction risk with nonstationary matrix models. Ecol Appl 16(1):51–61

    Article  Google Scholar 

  15. Grinblat G, Uzal C, Ceccatto H, Granitto P (2011) Solving non-stationary classification problems with coupled support vector machines. IEEE Trans Neural Netw 22(1):27–51

    Article  Google Scholar 

  16. Grinblat G, Uzal C, Granitto P (2013) Abrupt change detection with one-class time-adaptive support vector machines. Expert Syst Appl 40(18):7242–7249

    Article  Google Scholar 

  17. Guyon I, Weston S, Barnhill S, Vapnik V (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46(1–3):389–422

    Article  MATH  Google Scholar 

  18. Ikeda K (1979) Multiple-valued stationary state and its instability of the transmitted light by a ring cavity system. Opt Commun 30(2):257–261

    Article  Google Scholar 

  19. Koychev I (2000) Gradual forgetting for adaptation to concept drift. In: Proceedings of ECAI 2000 Workshop Current Issues in Spatio-Temporal Reasoning, pp 101–106

  20. Li L, Yang Z, Wang B, Kitsuregawa M (2007) Dynamic adaptation strategies for long-term and short-term user profile to personalize search. In: Dong G, Lin X, Wang W, Yang Y, Yu JX (eds) Advances in data and web management. Lecture notes in computer science, vol 4505. Springer, Berlin, Heidelberg, pp 228–240

  21. Narwaria M, Lin W (2010) Objective image quality assessment based on support vector regression. IEEE Trans Neural Netw 21(3):515–519

    Article  Google Scholar 

  22. Pang S, Song L, Kasabov N (2011) Correlation-aided support vector regression for forex time series prediction. Neural Comput Appl 20(8):1193–1203

    Article  Google Scholar 

  23. Pelletier L, Almhana J, Choulakian V (2004) Adaptive filtering of spam. In: IEEE Communication Networks and Services Research, 2004, Proceedings of the Second Annual Conference, pp 218–224

  24. Pereira Salazar DS, Leitao Adeodato PJ, Lucena Arnaud A (2014) Continuous dynamical combination of short and long-term forecasts for nonstationary time series. IEEE Trans Neural Netw Learn Syst 25(1):241–246

    Article  Google Scholar 

  25. Platt J (2000) Fast training of support vector machines using sequential minimal optimization. In: Schölkopf B, Burges CJC, Smola AJ (eds) Advances in Kernel methods: support vector learning. MIT Press, Cambridge, MA, pp 185–208

  26. Schreiber T (1997) Detecting and analyzing nonstationarity in a time series using nonlinear cross predictions. Phys Rev Lett 78(5):843–846

    Article  Google Scholar 

  27. Shi Y-Z, Wang S-T, Wang J, Deng Z-H (2013) Fast classification for non stationary large scale data sets using minimal enclosing ball. Control Decis 28:1065–1072

    Google Scholar 

  28. Smola A, Schölkopf B (2004) A tutorial on support vector regression. Stat Comput 14(3):199–222

    Article  MathSciNet  Google Scholar 

  29. Stark J (1999) Delay embeddings for forced systems. I. deterministic forcing. J Nonlinear Sci 9:255–332

    Article  MATH  MathSciNet  Google Scholar 

  30. Summers D, Cranford J, Healey B (2000) Chaos in periodically forced discrete-time ecosystem models. Chaos Solitons Fractals 11(14):2331–2342

    Article  MATH  MathSciNet  Google Scholar 

  31. Susnjak T, Barczak ALC, Hawick KA (2012) Adaptive cascade of boosted ensembles for face detection in concept drift. Neural Comput Appl 21(4):671–682

    Article  Google Scholar 

  32. Széliga M, Verdes P, Granitto P, Ceccatto H (2003) Modelling nonstationary dynamics. Phys A Stat Mech Appl 327(1–2):190–194

    Article  MATH  Google Scholar 

  33. Tay F, Cao L (2002) \(\varepsilon \)-descending support vector machines for financial time series forecasting. Neural Process Lett 15(2):179–195

    Article  MATH  Google Scholar 

  34. Verdes PF, Granitto PM, Ceccatto HA (2006) Overembedding method for modelling nonstationary systems. Phys Rev Lett 96(11):118701. doi:10.1103/PhysRevLett.96.118701

    Article  Google Scholar 

  35. Verdes PF, Granitto PM, Navone HD, Ceccatto HA (2001) Nonstationary time-series analysis: accurate reconstruction of driving forces. Phys Rev Lett 87(12):124101. doi:10.1103/PhysRevLett.87.124101

    Article  Google Scholar 

  36. Wong WK, Xia M, Chu WC (2010) Adaptive neural network model for time-series forecasting. Eur J Oper Res 207(2):807–816

    Article  MATH  MathSciNet  Google Scholar 

  37. Wu C, Ho J, Lee D (2004) Travel-time prediction with support vector regression. IEEE Trans Intell Transp Syst 5(4):276–281

    Article  Google Scholar 

Download references

Acknowledgments

The authors acknowledge partial support from ANPCyT.

Author information

Authors and Affiliations

  1. CIFASIS, French Argentine International Center for Information and Systems Sciences, UAM (France)/UNR-CONICET (Argentina), Bv. 27 de Febrero 210 Bis, S2000EZP, Rosario, Argentina

    Guillermo L. Grinblat, Lucas C. Uzal, Pablo F. Verdes & Pablo M. Granitto

Authors
  1. Guillermo L. Grinblat
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lucas C. Uzal
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Pablo F. Verdes
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Pablo M. Granitto
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Pablo M. Granitto.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Grinblat, G.L., Uzal, L.C., Verdes, P.F. et al. Nonstationary regression with support vector machines. Neural Comput & Applic 26, 641–649 (2015). https://doi.org/10.1007/s00521-014-1742-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-014-1742-6

Keywords

Search

Navigation