Intrinsic Mode Entropy for Nonlinear Discriminant Analysis

Hassan Amoud (1) , Hichem Snoussi (1) , David Hewson (1) , Michel Doussot (1) , Jacques Duchene (1)

1 LM2S - Laboratoire Modélisation et Sûreté des Systèmes

Several methods of measuring entropy of time series have been developed and applied on physiological signals in order to distinguish data sets according to their underlying nonlinear dynamics. These methods are not well adapted for studying the time series in different scales, in the presence of dominant local trends and low-frequency components. In this letter, intrinsic mode entropy (IMEn) is proposed as an entropy measure over multiple oscillation levels. Robustness to local trends is ensured with this new measure, enabling an efficient characterization of the underlying nonlinear dynamics of the time series considered. IMEn is obtained by computing the Sample Entropy (SampEn) of the cumulative sums of the intrinsic mode functions extracted by the empirical mode decomposition method. An example of an application of IMEn is then presented, with the method able to successfully discriminate between two groups of subjects (elderly versus control) for signals of postural stability

Domains: Signal and Image processing

Hassan Amoud, Hichem Snoussi, David Hewson, Michel Doussot, Jacques Duchene. Intrinsic Mode Entropy for Nonlinear Discriminant Analysis. IEEE Signal Processing Letters, 2007, 14 (5), pp.297-300. ⟨10.1109/LSP.2006.888089⟩. ⟨hal-02319985⟩