Time Series Preprocessing and Forecasting Based on EMD
Guo Chen Feng, Peng Shang, Xue Jiao Wang · Applied Mechanics and Materials · 2013
In this paper we pay attention to the preprocessing of time series and its application. We apply Empirical Mode Decomposition (EMD) to decompose three kinds of series into their components in order to study the data and forecast more efficiently. We try to unite EMD analysis and autoregressive integrated moving average processes (ARIMA) into a new forecasting technique which we call EMD-ARIMA. We find that our method is extraordinarily close to the original data.