Radial Basis Function Nets for Time Series Prediction

DOI

10.2991/ijcis.2009.2.2.6How to use a DOI?

Keywords

NARX Architecture, Radial basis function networks, Ensemble predictors, Multi-step prediction

Abstract

This paper introduces a novel ensemble learning approach based on recurrent radial basis function networks (RRBFN) for time series prediction with the aim of increasing the prediction accuracy. Standing for the base learner in this ensemble, the adaptive recurrent network proposed is based on the nonlinear autoregressive with exogenous input model (NARX) and works according to a multi-step (MS) prediction regime. The ensemble learning technique combines various MS- NARX-based RRBFNs which differ in the set of controlling parameters. The evaluation of the approach includes a discussion on the performance of the individual predictors and their combination.

Copyright

© 2009, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - JOUR
AU  - Abdelhamid Bouchachia
PY  - 2009
DA  - 2009/06/01
TI  - Radial Basis Function Nets for Time Series Prediction
JO  - International Journal of Computational Intelligence Systems
SP  - 147
EP  - 157
VL  - 2
IS  - 2
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.2009.2.2.6
DO  - 10.2991/ijcis.2009.2.2.6
ID  - Bouchachia2009
ER  -