A personalized exercise trainer for the elderly
Article type: Research Article
Authors: Bleser, Gabriele; | Steffen, Daniel | Weber, Markus | Hendeby, Gustaf; | Stricker, Didier | Fradet, Laetitia | Marin, Frédéric | Ville, Nathalie | Carré, Francois
Affiliations: German Research Center for Artificial Intelligence, Department Augmented Vision, Kaiserslautern, Germany. {daniel.steffen,markus.weber,didier.stricker}@dfki.de | Swedish Defence Research Agency (FOI), Department Sensor Informatics, Linköping, Sweden. gustaf.hendeby@foi.se | Linköping University, Department of Electrical Engineering, Linköping, Sweden. hendeby@isy.liu.se | Université de Technologie de Compiègne, UMR CNRS 7338 Biomécanique et Bioingénérie, Compiègne, France. {laetitia.fradet,frederic.marin}@utc.fr | CIC-IT Inserm 804, Rennes, France. {nathalie.ville,francois.carre}@univ-rennes2.fr
Note: [] Corresponding author. E-mail: gabriele.bleser@dfki.de.
Abstract: Regular and moderate physical activity practice provides many physiological benefits. It reduces the risk of disease outcomes and is the basis for proper rehabilitation after a severe disease. Aerobic activity and strength exercises are strongly recommended in order to maintain autonomy with ageing. Balanced activity of both types is important, especially to the elderly population. Several methods have been proposed to monitor aerobic activities. However, no appropriate method is available for controlling more complex parameters of strength exercises. Within this context, the present article introduces a personalized, home-based strength exercise trainer designed for the elderly. The system guides a user at home through a personalized exercise program. Using a network of wearable sensors the user's motions are captured. These are evaluated by comparing them to prescribed exercises, taking both exercise load and technique into account. Moreover, the evaluation results are immediately translated into appropriate feedback to the user in order to assist the correct exercise execution. Besides the direct feedback, a major novelty of the system is its generic personalization by means of a supervised teach-in phase, where the program is performed once under supervision of a physical activity specialist. This teach-in phase allows the system to record and learn the correct execution of exercises for the individual user and to provide personalized monitoring. The user-driven design process, the system development and its underlying activity monitoring methodology are described. Moreover, technical evaluation results as well as results concerning the usability of the system for ageing people are presented. The latter has been assessed in a clinical study with thirty participants of 60 years or older, some of them showing usual diseases or functional limitations observed in elderly population.
Keywords: Physical activity monitoring, elderly, home-based rehabilitation, HCI, wearable sensors, health promotion, strength exercises, personalization, ambient assisted living
DOI: 10.3233/AIS-130234
Journal: Journal of Ambient Intelligence and Smart Environments, vol. 5, no. 6, pp. 547-562, 2013
