On modified EMD: Selective extrema analysis

The Empirical Mode Decomposition (EMD) algorithm was introduced as the first step of the Hilbert-Huang Transform, proposed by Huang et al. (1998). EMD decomposes a signal into so-called Intrinsic Mode Functions (IMFs) in a systematic way. Since then, various versions of EMD have been developed, addressing weaknesses of the original EMD procedure and aiming to optimize the original algorithm in a number of ways. This paper proposes to use selective extrema analysis while generating IMFs with two goals. One is to reduce/control the number of IMFs a signal is decomposed into with a small decomposition error, and second is to make EMD insensitive to small variations in the analyzed signal. The proposed algorithm is applied to a gait signal and shown to consistently yield two IMFs, even in the presence of small disturbances.