EAI Endorsed Transactions on Pervasive Health and Technology 17(12): e5

Research Article

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

Download12 downloads
  • @ARTICLE{10.4108/eai.7-9-2017.153067,
        author={Hector F. Satizabal and Alexandre Grillon and Andres Upegui and Gregoire Millet and Giacomo Picasso and Andres Perez-Uribe},
        title={ActiDote -- A wireless sensor-based system for self-tracking activity levels among manual wheelchair users},
        journal={EAI Endorsed Transactions on Pervasive Health and Technology},
        volume={17},
        number={12},
        publisher={EAI},
        journal_a={PHAT},
        year={2017},
        month={9},
        keywords={Activity recognition, energy expenditure monitoring, self-tracking, wheelchair},
        doi={10.4108/eai.7-9-2017.153067}
    }
    
  • Hector F. Satizabal
    Alexandre Grillon
    Andres Upegui
    Gregoire Millet
    Giacomo Picasso
    Andres Perez-Uribe
    Year: 2017
    ActiDote – A wireless sensor-based system for self-tracking activity levels among manual wheelchair users
    PHAT
    EAI
    DOI: 10.4108/eai.7-9-2017.153067
Hector F. Satizabal1, Alexandre Grillon1, Andres Upegui2, Gregoire Millet3, Giacomo Picasso3, Andres Perez-Uribe1,*
  • 1: Institute for Information and Communication Technologies, IICT. School of Engineering and Business of the Canton of Vaud, HEIG-VD. University of Applied Sciences and Arts of Western Switzerland, HES-SO.
  • 2: Institut d’ingénierie Informatique et des Télécommunications, InIT. Haute École du paysage, d’ingénierie et d’architecture de Genève, HEPIA. University of Applied Sciences and Arts of Western Switzerland, HES-SO.
  • 3: Institut des sciences du sport de l’Université de Lausanne, ISSUL. University of Lausanne, UNIL. Switzerland.
*Contact email: andres.perez-uribe@heig-vd.ch

Abstract

ActiDote –activity as an antidote– is a system for manual wheelchair users that takes advantage of wireless sensors to recognize activities of various intensity levels in order to allow self-tracking of the physical activity. 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 on classifying activity levels and assessing energy expenditure during wheelchair propulsion on ramps of di erent slopes and speeds. Our results indicate that it is possible to implement a system that uses the accelerometer of a smartphone as the only sensor in the wheelchair, i.e., by attaching it to the wheelchair frame. Additionally, the user might wear a smartwatch equipped with an accelerometer to enrich the system and enhance its performance.