The Enhanced Ensemble Empirical Mode Decomposition for Analyzing Non Linear and Non Stationary Signals

Abstract

In this paper an algorithm of Enhanced Ensemble Empirical Mode Decomposition (EEEMD) is presented. Empirical Mode Decomposition (EMD) is an adaptive algorithm used for analyzing non linear and non stationary data which works by breaking the signal into a number of amplitude and frequency modulated (AM/FM) zero mean signals which are termed as Intrinsic Mode Functions(IMFs).but EMD experiences “Mode mixing” problem To overcome this problem Ensemble Empirical Mode Decomposition (EEMD) was proposed. The EEMD approach performs the EMD over an ensemble of original signal consists of sifting an ensemble of white noise added signal and treats the mean as the final true result. This approach will put an end to EMD mode mixing problem, however EEMD produced results does not satisfy the strict definition of IMF. To overcome this drawback, in the method here proposed, a unique residue is computed by adding noise at each stage of decomposition to obtain each IMF. The resulting decomposition is complete, with a numerically negligible error. Two examples are presented: a discrete Dirac delta function and an electrocardiogram signal. When compared with EEMD the new method here presented needs lesser number of iterations, thereby reducing the computational cost and an exact signal reconstruction, which is not possible with EEMD.