Single-Step-Ahead and Multi-Step-Ahead Prediction with Evolutionary Artificial Neural Networks

  • Víctor Manuel Landassuri-Moreno
  • Carmen L. Bustillo-Hernández
  • José Juan Carbajal-Hernández
  • Luis P. Sánchez Fernández
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8258)


In recent years, Evolutionary Algorithms (EAs) have been remarkably useful to improve the robustness of Artificial Neural Networks (ANNs). This study introduces an experimental analysis using an EAs aimed to evolve ANNs architectures (the FS-EPNet algorithm) to understand how neural networks are evolved with a steady-state algorithm and compare the Single-step-ahead (SSP) and Multiple-step-ahead (MSP) methods for prediction tasks over two test sets. It was decided to test an inside-set during evolution and an outside-set after the whole evolutionary process has been completed to validate the generalization performance with the same method (SSP or MSP). Thus, the networks may not be correctly evaluated (misleading fitness) if the single SSP is used during evolution (inside-set) and then the MSP at the end of it (outside-set). The results show that the same prediction method should be used in both evaluation sets providing smaller errors on average.


evolutionary algorithms artificial neural networks EANNs singlestep- ahead prediction multi-step-ahead prediction 


  1. 1.
    Stanley, K., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)CrossRefGoogle Scholar
  2. 2.
    Bullinaria, J.: Understanding the emergence of modularity in neural systems. Cognitive Science 31(4), 673–695 (2007)CrossRefGoogle Scholar
  3. 3.
    Yao, X., Liu, Y.: A new evolutionary system for evolving artificial neural networks. IEEE Transactions on Neural Networks 8(3), 694–713 (1997)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Cholewo, T., Zurada, J.: Sequential network construction for time series pre¬diction. International Conference on Neural Networks 4, 2034–2038 (1997)Google Scholar
  5. 5.
    Bishop, M.: Neural Networks for Pattern Recognition. Oxford University Press (1995)Google Scholar
  6. 6.
    Yao, X.: Evolving artificial neural networks. Proceedings of the IEEE 87(9), 1423–1447 (1999)CrossRefGoogle Scholar
  7. 7.
    Bullinaria, A.: Evolving neural networks: Is it really worth the effort? In: Proceedings of the European Symposium on Artificial Neural Networks, Evere, Belgium: d-side, pp. 267–272 (2005)Google Scholar
  8. 8.
    Landassuri, V., Bullinaria, J.: Feature selection in evolved artificial neural networks using the evolutionary algorithm EPNet. In: Proceedings of the 2009 UK Workshop on Computational Intelligence, UKCI ’2009. University of Nottingham, Nottingham (2009)Google Scholar
  9. 9.
    Belaire, J., Contreras, D.: Recurrence plots in non-linear time series analysis: Free software. Journal of Statistical Software 7(9) (2002)Google Scholar
  10. 10.
    Rojas, I., Pomares, H., Bernier, J., Ortega, J., Pino, B., Pelayo, F., Prieto, A.: Time series analysis using normalized pg-rbf network with regression weights. Neurocomputing 42(1-4), 267–285 (2002)CrossRefzbMATHGoogle Scholar
  11. 11.
    Gholipour, A., Araabi, B., Lucas, C.: Predicting chaotic time series using neural and neurofuzzy models: A comparative study. Neural Processing Letters 24(3), 217–239 (2006)CrossRefGoogle Scholar
  12. 12.
    Müller, K., Smola, A., Rätsch, G., Schökopf, B., Kohlmorgen, J., Vapnik, V.: Using support vector machines for time series prediction, pp. 243–253 (1999)Google Scholar
  13. 13.
    Müller, K.R., Smola, A., Rätsch, G., Schölkopf, B., Kohlmorgen, J., Vapnik, V.: Predicting time series with support vector machines. In: Gerstner, W., Hasler, M., Germond, A., Nicoud, J.-D. (eds.) ICANN 1997. LNCS, vol. 1327, pp. 999–1004. Springer, Heidelberg (1997)Google Scholar
  14. 14.
    Dudul, S.: Prediction of a Lorenz chaotic attractor using two-layer perceptron neural network. Applied Soft Computing 5(4), 333–355 (2005)CrossRefGoogle Scholar
  15. 15.
    Guerra, F., Dos, S.: Multi-step ahead nonlinear identification of Lorenz’s chaotic system using radial basis neural network with learning by clus¬tering and particle swarm optimization. Chaos, Solitons & Fractals 35(5), 967–979 (2008)CrossRefzbMATHGoogle Scholar
  16. 16.
    Lorenz, E.: Deterministic non periodic flow. Journal of Atmospheric Science 20, 130–141 (1963)CrossRefGoogle Scholar
  17. 17.
    Hansen, L.P., Hodrick, R.J.: Forward Exchange Rates as Optimal Predictors of Future Spot Rates: An Econometric Analysis. Journal of Political Economy 88(5), 829–853 (1980)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Víctor Manuel Landassuri-Moreno
    • 1
  • Carmen L. Bustillo-Hernández
    • 2
  • José Juan Carbajal-Hernández
    • 2
  • Luis P. Sánchez Fernández
    • 2
  1. 1.Mexico Valley University Center (CUUAEM-VM) – Autonomous University of the State of MexicoEstado de MéxicoMéxico
  2. 2.Center of Computer ResearchNational Polytechnic InstituteMéxico D.F.México

Personalised recommendations