A wireless sensor-based system for self-tracking activity levels among manual wheelchair users

Grillon, Alexandre (School of Management and Engineering Vaud, HES-SO // University of Applied Sciences Western Switzerland ; University of Applied Sciences and Arts of Western Switzerland (HES-SO), Delémont, Switzerland) ; Perez-Uribe, Andrès (School of Management and Engineering Vaud, HES-SO // University of Applied Sciences Western Switzerland ; University of Applied Sciences and Arts of Western Switzerland (HES-SO), Delémont, Switzerland) ; Satizabal, Hector F. (School of Management and Engineering Vaud, HES-SO // University of Applied Sciences Western Switzerland ; University of Applied Sciences and Arts of Western Switzerland (HES-SO), Delémont, Switzerland) ; Gantel, Laurent (School of Engineering, Architecture and Landscape (hepia), HES-SO // University of Applied Sciences Western Switzerland ; University of Applied Sciences and Arts of Western Switzerland (HES-SO), Delémont, Switzerland) ; Da Silva Andrade, David (School of Engineering, Architecture and Landscape (hepia), HES-SO // University of Applied Sciences Western Switzerland ; University of Applied Sciences and Arts of Western Switzerland (HES-SO), Delémont, Switzerland) ; Upegui, Andres (School of Engineering, Architecture and Landscape (hepia), HES-SO // University of Applied Sciences Western Switzerland ; University of Applied Sciences and Arts of Western Switzerland (HES-SO), Delémont, Switzerland) ; Degache, Francis (HESAV Haute Ecole de Santé Vaud, HES-SO Haute école spécialisée de Suisse occidentale) ; University of Applied Sciences and Arts of Western Switzerland (HES-SO), Delémont, Switzerland)

ActiDote —activity as an antidote— is a system for manual wheelchair users that uses wireless sensors to recognize activities of various intensity levels in order to allow self-tracking while providing motivation. In this paper, we describe both the hardware setup and the software pipeline that enable our system to operate. Laboratory tests using multi-modal fusion and machine learning reveal promising results attaining a F1-score classification performance of 0.97 on five different wheelchair-based activities belonging to four intensity levels. Finally, we show that such a low cost system can be used for an easy self-monitoring of physical activity levels among manual wheelchair users.


Keywords:
Faculty:
Ingénierie et Architecture
Santé
School:
HEPIA - Genève
HEIG-VD
HESAV
Institute:
IICT - Institut des Technologies de l'Information et de la Communication
inIT - Institut d'Ingénierie Informatique et des Télécommunications
Unité de recherche en santé, HESAV
Publisher:
Cham, Springer
Date:
2016-12
Cham
Springer
Pagination:
pp. 229-240
Published in:
eHealth 360° : Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
Series Statement:
LNICST, vol. 181
DOI:
ISSN:
1867-8211
ISBN:
978-3-319-49654-2
Appears in Collection:



 Record created 2020-07-10, last modified 2020-07-14


Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)