Expand description
Empirical mode decomposition, per channel (EMD) and multivariate (MEMD), on one sifting engine. Sources and choices are in docs/emd.md.
Structs§
- Ceemdan
- Complete ensemble EMD with adaptive noise, improved form (Colominas et al. 2014), each channel on its own. Mode k is r_{k−1} − ⟨M(r_{k−1} + ε·SD(r_{k−1})·E_k(w))⟩, so modes sum to the signal exactly.
- Eemd
- Ensemble EMD (Wu and Huang 2009), each channel on its own: the mean of EMDs of the signal
plus white noise with SD
noise_sd·SD(signal). Every trial takes at most ⌊log₂ n⌋ − 1 IMFs unless set, as Wu and Huang’s eemd.m; unlike it, a trial stops early once its residual no longer oscillates. Modes sum to the signal plus the mean noise, which shrinks with more trials. - Emd
- Empirical mode decomposition (Huang et al. 1998) of each channel on its own.
- Memd
- Multivariate EMD (Rehman and Mandic 2010): envelopes from projections of all channels along
num_directionsHammersley directions, so every channel gets the same IMFs.
Enums§
- Stop
- When sifting one mode stops.