Composite Recurrent Neural Networks for Long-Term Prediction of Highly-Dynamic Time Series Supported by Wavelet Decomposition

Even though it is known that chaotic time series cannot be accurately predicted, there is a need to forecast their behavior in may decision processes. Therefore several non-linear prediction strategies have been developed, many of them based on soft computing. In this chapter we present a new neural network architecutre, called Hybrid and based-onWavelet-Reconstructions Network (HWRN), which is able to perform recursive long-term prediction over highly dynamic and chaotic time series. HWRN is based on recurrent neural networks embedded in a two-layer neural structure, using as a learning aid, signals generated by wavelets coefficients obtained from the training time series. In the results reported here, HWRN was able to predict better than a feed-forward neural network and that a fully-connected, recurrent neural network with similar number of nodes. Using the benchmark known as NN5, which contains chaotic time series, HWRN obtained in average a SMAPE = 26% compared to a SMAPE = 61% obtained by a fully-connected recurrent neural network and a SMAPE = 49% obtained by a feed forward network. 1 To be published at “Soft Computing for Intelligent Control and Mobile Robotics,” Vol. 318/2011, pp.253-268, Castillo O, Janusz K and Pedrycz W. Editors, Springer-Verlag. DOI:10.1007/978-3-642-15534-5_16. 2 Pilar Gomez-Gil*, Angel Garcia-Pedrero* and Juan Manuel RamirezCortes**.