Constellation, le dépôt institutionnel de l'Université du Québec à Chicoutimi

An open vibration and pressure platform for fall prevention with a reinforcement learning agent

Lafontaine Virgile, Lapointe Patrick, Bouchard Kevin, Gagnon Jean-Michel, Dallaire Mathieu, Gaboury Sébastien, da Silva Rubens A. et Beaulieu Louis-David. (2020). An open vibration and pressure platform for fall prevention with a reinforcement learning agent. Personal and Ubiquitous Computing,

Le texte intégral n'est pas disponible pour ce document.

URL officielle: http://dx.doi.org/doi:10.1007/s00779-020-01416-0

Résumé

The risk of falls among the elderly population is one that may lead to dire consequences. It can significantly affect the quality of life of the victims and even lead to their premature death. Many technological tools have been proposed in the literature to detect falls, but little effort has been done regarding their prevention. In this paper, our research team proposes an inexpensive open vibration platform equipped with pressure sensors. The platform is built from easily available electronic components to be used as a tool by physiotherapists in order to help them in their evaluation of the postural control of individuals at risk of postural imbalance. The platform has been built to be easily reproducible by the scientific community. Moreover, the computer code necessary to make it work is fully open source and can be used in any non-commercial applications. A first version of the platform was tested with 7 healthy human participants. A simple reinforcement learning agent was deployed and tested to automatically calibrate the vibration motors for optimal stimulation. The agent exploited computer vision to capture the data from a force platform commercially available and use it as ground truth. Finally, a second version of the platform was built and is presented in the paper. That version is currently being validated clinically with both healthy and impaired human participants. The preliminary data are presented in this paper.

Type de document:Article publié dans une revue avec comité d'évaluation
ISSN:1617-4909
Version évaluée par les pairs:Oui
Date:2020
Identifiant unique:10.1007/s00779-020-01416-0
Sujets:Sciences naturelles et génie > Sciences mathématiques > Informatique
Département, module, service et unité de recherche:Départements et modules > Département d'informatique et de mathématique
Mots-clés:sensors, vibration motors, force platform, postural control, reinforcement learning, technology for health
Déposé le:10 févr. 2021 18:53
Dernière modification:10 févr. 2021 18:53
Afficher les statistiques de telechargements

Éditer le document (administrateurs uniquement)

Creative Commons LicenseSauf indication contraire, les documents archivés dans Constellation sont rendus disponibles selon les termes de la licence Creative Commons "Paternité, pas d'utilisation commerciale, pas de modification" 2.5 Canada.

Bibliothèque Paul-Émile-Boulet, UQAC
555, boulevard de l'Université
Chicoutimi (Québec)  CANADA G7H 2B1
418 545-5011, poste 5630