Advertisement

k-Nearest-Neighbor by Differential Evolution for Time Series Forecasting

  • Erick De La Vega
  • Juan J. Flores
  • Mario Graff
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8857)

Abstract

A framework for time series forecasting that integrates k-Nearest-Neighbors (kNN) and Differential Evolution (DE) is proposed. The methodology called NNDEF (Nearest Neighbor - Differential Evolution Forecasting) is based on knowledge shared from nearest neighbors with previous similar behaviour, which are then taken into account to forecast. NNDEF relies on the assumption that observations in the past similar to the present ones are also likely to have similar outcomes. The main advantages of NNDEF are the ability to predict complex nonlinear behavior and handling large amounts of data. Experiments have shown that DE can optimize the parameters of kNN and improve the accuracy of the predictions.

Keywords

Time Series Forecasting Prediction k-Nearest-Neighbor Differential Evolution 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Baldi, P., Brunak, S.: Bioinformatics: the machine learning approach. MIT press (2001)Google Scholar
  2. 2.
    Barker, T.: Pro Data Visualization Using R and JavaScript. Apress (2013)Google Scholar
  3. 3.
    Brookwell, P.J., Davis, R.A.: Introduction to Time Series and Forecasting. Springer (2002)Google Scholar
  4. 4.
    Casdagli, M.: Nonlinear prediction of chaotic time series. Physica D: Nonlinear Phenomena 35(3), 335–356 (1989)CrossRefzbMATHMathSciNetGoogle Scholar
  5. 5.
    Cowpertwait, P.S., Metcalfe, A.V.: Introductory Time Series with R. Springer (2009)Google Scholar
  6. 6.
    Douglas, C., Montgomery, C.L.J., Kulahci, M.: Introduction To Time Series Analysis and Forecasting. Wiley-Interscience (2008)Google Scholar
  7. 7.
    Dragomir Yankov, D.D., Keogh, E.: Ensembles of nearest neighbor forecasts. ECMIL 1, 545–556 (2006)Google Scholar
  8. 8.
    Farmer, J.D., Sidorowich, J.J.: Predicting chaotic time series. Physical Review Letters 59(8), 845 (1987)CrossRefMathSciNetGoogle Scholar
  9. 9.
    Gebhard Kirchgssner, J.W., Hassler, U.: Introduction To Modern Time Series Analysis. Springer (2013)Google Scholar
  10. 10.
    Grassberger, P., Procaccia, I.: Characterization of strange attractors. Physical Review Letters 50(5), 346 (1983)CrossRefMathSciNetGoogle Scholar
  11. 11.
    Guckenheimer, J., Williams, R.F.: Structural stability of lorenz attractors. Publications Mathématiques de l’IHÉS 50(1), 59–72 (1979)CrossRefzbMATHMathSciNetGoogle Scholar
  12. 12.
    Lampinen, J., Zelinka, I.: Mixed integer-discrete-continuous optimization by differential evolution-part 1: the optimization method. In: Czech Republic. Brno University of Technology. Citeseer (1999)Google Scholar
  13. 13.
    Leven, R., Koch, B.: Chaotic behaviour of a parametrically excited damped pendulum. Physics Letters A 86(2), 71–74 (1981)CrossRefGoogle Scholar
  14. 14.
    Troncoso Lora, A., Riquelme, J.C., Martínez Ramos, J.L., Riquelme Santos, J.M., Gómez Expósito, A.: Influence of kNN-based load forecasting errors on optimal energy production. In: Pires, F.M., Abreu, S.P. (eds.) EPIA 2003. LNCS (LNAI), vol. 2902, pp. 189–203. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  15. 15.
    Maguire, L.P., Roche, B., McGinnity, T.M., McDaid, L.: Predicting a chaotic time series using a fuzzy neural network. Information Sciences 112(1), 125–136 (1998)CrossRefzbMATHGoogle Scholar
  16. 16.
    Palit, A.K., Popovic, D.: Computational Intelligence in Time Series Forecasting. Springer (2005)Google Scholar
  17. 17.
    Pecora, L.M., Carroll, T.L.: Synchronization in chaotic systems. Physical Review Letters 64(8), 821 (1990)CrossRefzbMATHMathSciNetGoogle Scholar
  18. 18.
    Rabiner, L.R., Gold, B.: Theory and application of digital signal processing, vol. 777, p. 1. Prentice-Hall, Inc., Englewood Cliffs (1975)Google Scholar
  19. 19.
    Rainer Storn, K.P., Lampinen, J.: Differential Evolution A Practical Aproach to Global Optimization. Springer, Berlin (2005)Google Scholar
  20. 20.
    Shumway, R.H., Stoffer, D.S.: Time Series Analysis and its Applications. Springer (2011)Google Scholar
  21. 21.
    Sorjamaa, A., Lendsasse, A.: Time series prediction using dir-rec strategy. In: ESANN Proceedings-European Symposium on ANN’s (2006)Google Scholar
  22. 22.
    Storn, R., Price, K.: Differential evolution- a simple and efficient heuristic for global optimization over continuous spaces. Global Optimization 11, 341–359 (1995)CrossRefMathSciNetGoogle Scholar
  23. 23.
    Weigend, A.S., Gershenfeld, N.A.: Results of the time series prediction competition at the santa fe institute. In: IEEE International Conference on Neural Networks, pp. 1786–1793. IEEE (1993)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Erick De La Vega
    • 1
  • Juan J. Flores
    • 1
  • Mario Graff
    • 1
  1. 1.División de Estudios de Posgrado, Facultad de Ingeniería EléctricaUniversidad Michoacana de San Nicolás de HidalgoMoreliaMéxico

Personalised recommendations