Hybrid deep learning and empirical mode decomposition model for time series applications

摘要

Time series forecasting is important in many aspects of our lives, since it can be used to deal with the uncertainty to further support the decision making. Despite many advanced methodologies have been proposed, modelling the underlying relationship between past and future conditions is still a challenge. In this research, we develop a novel time series forecasting model which can effectively predict future conditions in a timely fashion. A time series has nonlinear and nonstationary characteristics which make prediction using statistical or computational intelligent methods a difficult task. Therefore, a hybrid deep learning and empirical mode decomposition model, namely EMD–SAE, for multistep ahead forecasting is proposed to predict the traffic flow and random time series. The performances of the proposed model are compared and discussed. This paper shows the potential of hybridizing the deep learning and empirical mode decomposition to the ordinary time series forecasting approach, and the experimental results suggest that the proposed EMD–SAE is reliable, suitable and a promising method for time series forecasting.