Gait Recognition for Human-Exoskeleton System in Locomotion Based on Ensemble Empirical Mode Decomposition
Algorithm 1
EEMD for IMF extraction.
Input: Original gait signal
Output:
(1)
For different N noisy signals ,, we generate different and calculate its corresponding decomposing results, . This means we extract IMFs for N trials for different noisy signals .
(2)
fordo
(3)
Calculate for the original signal .
(4)
fordo
(5)
Check SD to see whether meets two conditions of IMF which is (1) in the whole dataset, the number of extrema and the number of zero crossings must either equal or differ at most by one; (2) at any point, the mean value of the envelope defined by the local maxima and the envelope defined by the local minima is zero.
(6)
while ( or )do
(7)
where is the upper envelope of which is a cubic spline line connecting all the local maxima of and is the lower envelope of which is a cubic spline line connecting all the local minima of
