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

Towards a real-time error detection within a smart home by using activity recognition with a shoe-mounted accelerometer

Vandewynckel Julien, Otis Martin J.-D., Bouchard Bruno, Ménélas Bob-Antoine-Jerry et Bouzouane Abdenour. (2013). Towards a real-time error detection within a smart home by using activity recognition with a shoe-mounted accelerometer. Procedia Computer Science, 19, p. 516-523.

[thumbnail of Towards a real-time error detection within a smart home by using activity recognition with a shoe-mounted accelerometer.pdf]
Prévisualisation
PDF - Version publiée
929kB

URL officielle: http://dx.doi.org/doi:10.1016/j.procs.2013.06.069

Résumé

Taking care of the elders constitutes a major issue in the western societies. Smart homes appear to be a socially and economically viable solution. They consist in habitats augmented with sensors and actuators enabling to achieve activity recognition and to provide assistive services to a resident. Stationary aspect of sensors used in most smart homes makes the concept difficult to deploy in existing homes, and involves a high cost. In this paper, we propose an inexpensive non-vision-based system ably to recognize, in real-time, activities and errors of a resident. This proposed recognition system is based on a shoe equipped with a single sensor: a three-axis accelerometer and on a statetransition algorithmic approach using fuzzy logic. We have examined the learning data as frequency distributions, where the probability histograms have been directly interpreted as fuzzy set. We conducted experiments of the system in our smart home by simulating (multiple times) several scenarios based on a morning routine. These scenarios were based on clinical data gathered in a previous experiment We obtained promising results showing that the proposed activity and error recognition system are highly effective.

Type de document:Article publié dans une revue avec comité d'évaluation
Volume:19
Pages:p. 516-523
Version évaluée par les pairs:Oui
Date:2013
Sujets:Sciences naturelles et génie > Génie > Génie informatique et génie logiciel
Département, module, service et unité de recherche:Départements et modules > Département des sciences appliquées > Module d'ingénierie
Mots-clés:Healthcare systems, mobile computing, wearables sensors, ubiquitous computing
Déposé le:08 mai 2017 22:48
Dernière modification:08 mai 2017 22:48
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