Skip to main content
SpringerLink
Log in
Book cover

Brazilian Symposium on Artificial Intelligence

SBIA 1995: Advances in Artificial Intelligence pp 210–218Cite as

An automatic adaptive neurocomputing algorithm for time series prediction

  • Conference paper
  • First Online:

  • 138 Accesses

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 991))

Abstract

This work proposes a new algorithm called KNNN (k-nearest neighbours network) and demonstrates its use in a prediction task. The algorithm constructs estimators arranged in layers, using cross validation and kernel smoothing to achieve function approximation. Here it is compared to the back-propagation (with weight-elimination) algorithm in the prediction of future behavior of the benchmark sunspot series. The results show that KNNN can be applied successfully as an estimator.

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

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Granger, C.W.J. and Andersen, A.P.: An Introduction to Bilinear Time Series Models. Gottingen: Vandenhoek and Ruprecht, 1978.

    Google Scholar 

  2. Tong, H.: Nonlinear Time Series Analysis: A Dynamical Systems Approach. Oxford: Oxford University Press, 1990.

    Google Scholar 

  3. Garbor, D. et al.: A universal nonlinear filter, predictor and simulator which optimizes itself by a learning process. Proc. IEEE, 108B, 422–438 (1961).

    Google Scholar 

  4. Lapedes, A. and Farber, R.: Nonlinear Signal Processing Using Neural Networks; Prediction and System Modelling, 1987.

    Google Scholar 

  5. Ivakhnenko, A.G.: Polynomial Theory of Complex Systems. IEEE TSMC, SMC-1 (4), 364–378 (1971).

    Google Scholar 

  6. Härdle, W.: Applied Nonparametric Regression. Cambridge University Press, 1989.

    Google Scholar 

  7. Loftsgaarden, D.O. and Quesenberry, G.P.: A Nonparametric Estimate of a Multivariate Density Function. Annals of Mathematical Statistics, 1965.

    Google Scholar 

  8. Foukal, P.V.: The Variable Sun. Sci. Am, 1990.

    Google Scholar 

  9. Yule, G.U.: On a method of investigations periodicities in disturbed series with special reference to Wolfer's sunspot numbers. Philos. Trans. R. Soc. Lond. Ser. 1927.

    Google Scholar 

  10. Weigend, A.S., Huberman, B.A. and Rumelhart, D.E. Predicting the future: a connectionist approach. International Journal of Neural Systems, 1990.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Departamento de Engenharia de Sistemas, Pós-graduação em Sistemas e Computação, Instituto Militar de Engenharia, Brasil

    Emmanuel Passos & Romildo Valente

Authors
  1. Emmanuel Passos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Romildo Valente
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Jacques Wainer Ariadne Carvalho

Rights and permissions

Reprints and permissions

Copyright information

© 1995 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Passos, E., Valente, R. (1995). An automatic adaptive neurocomputing algorithm for time series prediction. In: Wainer, J., Carvalho, A. (eds) Advances in Artificial Intelligence. SBIA 1995. Lecture Notes in Computer Science, vol 991. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0034814

Download citation

  • DOI: https://doi.org/10.1007/BFb0034814

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-60436-5

  • Online ISBN: 978-3-540-47467-8

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation