EMG-Based Automatic Gesture Recognition Using Robust Neural Networks (Extended version) - INRIA - Institut National de Recherche en Informatique et en Automatique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

EMG-Based Automatic Gesture Recognition Using Robust Neural Networks (Extended version)

Résumé

This paper introduces a novel approach for building a robust Automatic Gesture Recognition system based on Surface Electromyographic (sEMG) signals, acquired at the forearm level. Our main contribution is to propose new constrained learning strategies that ensure robustness against adversarial perturbations by controlling the Lipschitz constant of the classifier. We focus on positive neural networks for which accurate Lipschitz bounds can be derived, and we propose different spectral norm constraints offering robustness guarantees from a theoretical viewpoint. Experimental results on two distinct datasets highlight that a good trade-off in terms of accuracy and performance is achieved. We then demonstrate the robustness of our models, compared to standard trained classifiers in three scenarios, considering both white-box and black-box attacks.
Fichier principal
Vignette du fichier
Elsevier_Article__elsarticle__Template.pdf (1.99 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03751766 , version 1 (16-08-2022)
hal-03751766 , version 2 (17-02-2023)

Identifiants

  • HAL Id : hal-03751766 , version 1

Citer

Ana-Antonia Neacșu, Jean-Christophe Pesquet, Corneliu Burileanu. EMG-Based Automatic Gesture Recognition Using Robust Neural Networks (Extended version). 2022. ⟨hal-03751766v1⟩

Collections

GS-ENGINEERING
195 Consultations
125 Téléchargements

Partager

Gmail Facebook X LinkedIn More