Inputs Selection for Artificial Neural Networks for Multivariate time Series

Z.H. Ashour* and H.A. Fayed

Department of Engineering Mathematics and Physics, Cairo University, Cairo (Egypt).

DOI : http://dx.doi.org/10.13005/msri/060102

ABSTRACT:

A new method in selecting the inputs of the neural networks for multivariate time series is proposed. The input and output time series are analyzed and suitable mathematical models are built in the input-output model parametric representation. The inputs to the best input-output models are chosen as the inputs to the neural network model. The estimates from different models are then combined to obtain an unbiased estimate of the output series. The resulting combined neural network model is used in forecasting the bench marking gas furnace multivariate time series. The new developed procedure outperformed previously used forecasting techniques.

KEYWORDS: Artificial neural networks; inputs Selection; multivariate time series

Copy the following to cite this article: Ashour Z. H, Fayed H. A. Inputs Selection for Artificial Neural Networks for Multivariate time Series. Mat.Sci.Res.India;6(1)

Copy the following to cite this URL: Ashour Z. H, Fayed H. A. Inputs Selection for Artificial Neural Networks for Multivariate time Series. Mat.Sci.Res.India;6(1). Available from: http://www.materialsciencejournal.org/?p=3400

---

This work is licensed under a Creative Commons Attribution 4.0 International License.