Robust Functional Statistics applied to Probability Density Function Shape screening of sEMG data

Abstract : 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.
Type de document :
Communication dans un congrès
36th Annual International IEEE EMBS Conference, Aug 2014, Chicago, United States. pp.2213-2216, 2014, 36th Annual International IEEE EMBS Conference Proceedings. <10.1109/EMBC.2014.6944058.>
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01242503
Contributeur : Hervé Rix <>
Soumis le : samedi 12 décembre 2015 - 19:11:23
Dernière modification le : lundi 12 septembre 2016 - 16:24:26

Identifiants

Collections

Citation

Sofiane Boudaoud, Hervé Rix, Mariam Al Harrach, Frédéric Marin. Robust Functional Statistics applied to Probability Density Function Shape screening of sEMG data. 36th Annual International IEEE EMBS Conference, Aug 2014, Chicago, United States. pp.2213-2216, 2014, 36th Annual International IEEE EMBS Conference Proceedings. <10.1109/EMBC.2014.6944058.>. <hal-01242503>

Partager

Métriques

Consultations de la notice

67