A New Approach to Empirical Mode Decomposition Based on Akima Spline Interpolation Technique
Muhammad Ali, Dost Muhammad Khan, Imran Saeed, Huda M. Alshanbari
Abstract
The objective of this research work is to extend the scope of empirical mode decomposition (EMD) algorithm, as an efficient tool to decompose the nonlinear and non-stationary time series. For EMD to be widely applicable, the extension utilizes both clean and noisy data sets. When constructing upper and lower envelopes, the proposed algorithm utilizes the Akima spline interpolation technique rather than a cubic spline. The proposed EMD is called Akima-EMD, which is used to identify non-informative fluctuations in the signal, such as noise, outliers, and ultra-high frequency components, and to breakdown the clean and chaotic data into various components avoiding distortion. It has been shown through the synthetic as well as real-world time series data analysis that the proposed method successfully extracts noise in the form of the first IMF from the data.