Robust Functional Statistics applied to Probability Density Function Shape screening of sEMG data
Résumé
Recent studies pointed out possible shape
modifications of the Probability Density Function (PDF) of
surface electromyographical (sEMG) data according to several
contexts like fatigue and muscle force increase. Following this
idea, criteria have been proposed to monitor these shape
modifications mainly using High Order Statistics (HOS)
parameters like skewness and kurtosis. In experimental
conditions, these parameters are confronted with small sample
size in the estimation process. This small sample size induces
errors in the estimated HOS parameters restraining real-time
and precise sEMG PDF shape monitoring. Recently, a
functional formalism, the Core Shape Model (CSM), has been
used to analyse shape modifications of PDF curves. In this
work, taking inspiration from CSM method, robust functional
statistics are proposed to emulate both skewness and kurtosis
behaviors. These functional statistics combine both kernel
density estimation and PDF shape distances to evaluate shape
modifications even in presence of small sample size. Then, the
proposed statistics are tested, using Monte Carlo simulations,
on both normal and Log-normal PDFs that mimic observed
sEMG PDF shape behavior during muscle contraction.
According to the obtained results, the functional statistics seem
to be more robust than HOS parameters to small sample size
effect and more accurate in sEMG PDF shape screening
applications.