bivariate Empirical Mode Decomposition, first algorithm
[IMF,NB_ITERATIONS]=cemdc_fix(T,X); [IMF,NB_ITERATIONS]=cemdc_fix([],X); [IMF,NB_ITERATIONS]=cemdc_fix(T,X,NB_ITERATIONS); [IMF,NB_ITERATIONS]=cemdc_fix(T,X,NB_ITERATIONS,MAX_IMFS); [IMF,NB_ITERATIONS]=cemdc_fix(T,X,NB_ITERATIONS,MAX_IMFS,NDIRS);
sampling times. If T=[], the signal is assumed uniformly sampled.1xN time instants
analyzed signal, 1xN signal data
number of sifting iterations to be performed to extract each IMF. If NB_ITERATIONS is empty or unspecified, 10 iterations are performed by default. Note: The effective number of sifting iterations might be less than NB_ITERATIONS for the last modes if the sifting process has to be stopped because of a lack of extrema.
maximum number of IMFs to be extracted. If MAX_IMFS is zero, empty or unspecified, the default behavior is to extract as many IMFs as possible.
number of directions used to compute the local mean. If unspecified, the default value is 4. TODO: the actual number of directions (according to [1]) is 2*NDIRS
intrinsic mode functions (IMFs) (last line = residual)
effective number of sifting iterations for each mode
cemdc_fix computes bivariate EMD, first algorithm [1] with NB_ITERATONS sifting iterations for each IMF
mean of boolean array {(mean_amplitude)/(envelope_amplitude) > THRESHOLD} < TOLERANCE
[1] G. Rilling, P. Flandrin, P. Gonçalves and J. M. Lilly.,
"Bivariate Empirical Mode Decomposition",
Signal Processing Letters (submitted)