A New Direct Multi-step Ahead Prediction Model Based on EMD and Chaos Analysis

The direct multi-step ahead prediction model,which employs observation values and does not depend on the result of single-step prediction,provides more accurate prediction than indirect model.But in this case,the model could be asked to learn various object functions.In this paper,a hybrid model is presented based on empirical mode decomposition(EMD)and chaos analysis.The model employs EMD to decompose the original sequences into many basic modal partitions which can significantly represent potential information of original time series.And chaos features of those data sequences can be used to design DRNN.By these means,the model can be improved to learn various objective functions.And then,more precious prediction can be obtained.Finally,a benchmark time series is tested to display the advantage of this model.

[1]  Hualou Liang,et al.  Empirical mode decomposition: a method for analyzing neural data , 2005, Neurocomputing.

[2]  K. Coughlin,et al.  11-Year solar cycle in the stratosphere extracted by the empirical mode decomposition method , 2004 .

[3]  The fractal research and predicating on the times series of sunspot relative number , 1999 .

[4]  He Guo.  A STUDY ON FORECASTING FOR TIME SERIES BASED ON WAVELET ANALYSIS , 2002 .

[5]  J. Suykens,et al.  Learning a simple recurrent neural state space model to behave like Chua's double scroll , 1995 .

[6]  S. Loutridis.  Instantaneous energy density as a feature for gear fault detection , 2006 .

[7]  Amir B. Geva,et al.  ScaleNet-multiscale neural-network architecture for time series prediction , 1998, IEEE Trans. Neural Networks.

[8]  Min Han,et al.  Prediction of chaotic time series based on the recurrent predictor neural network , 2004, IEEE Transactions on Signal Processing.

[9]  Amir F. Atiya,et al.  Multi-step-ahead prediction using dynamic recurrent neural networks , 2000, Neural Networks.

[10]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[11]  Jacques Lemoine,et al.  Empirical mode decomposition synthesis of fractional processes in 1D- and 2D-space , 2005, Image Vis. Comput..

[12]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[13]  David E. Rumelhart,et al.  Predicting the Future: a Connectionist Approach , 1990, Int. J. Neural Syst..

[14]  Peter Tiño,et al.  Learning long-term dependencies in NARX recurrent neural networks , 1996, IEEE Trans. Neural Networks.

[15]  Skander Soltani,et al.  On the use of the wavelet decomposition for time series prediction , 2002, ESANN.