eHealth 360°. International Summit on eHealth, Budapest, Hungary, June 14-16, 2016, Revised Selected Papers

Research Article

A Wireless Sensor-Based System for Self-tracking Activity Levels Among Manual Wheelchair Users

Download
244 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-49655-9_31,
        author={Alexandre Grillon and Andres Perez-Uribe and Hector Satizabal and Laurent Gantel and David Silva Andrade and Andres Upegui and Francis Degache},
        title={A Wireless Sensor-Based System for Self-tracking Activity Levels Among Manual Wheelchair Users},
        proceedings={eHealth 360°. International Summit on eHealth, Budapest, Hungary, June 14-16, 2016, Revised Selected Papers},
        proceedings_a={EHEALTH360},
        year={2017},
        month={1},
        keywords={Self-tracking Wheelchair Handicap Wireless sensors Wearables Machine learning},
        doi={10.1007/978-3-319-49655-9_31}
    }
    
  • Alexandre Grillon
    Andres Perez-Uribe
    Hector Satizabal
    Laurent Gantel
    David Silva Andrade
    Andres Upegui
    Francis Degache
    Year: 2017
    A Wireless Sensor-Based System for Self-tracking Activity Levels Among Manual Wheelchair Users
    EHEALTH360
    Springer
    DOI: 10.1007/978-3-319-49655-9_31
Alexandre Grillon,*, Andres Perez-Uribe,*, Hector Satizabal,*, Laurent Gantel,*, David Silva Andrade,*, Andres Upegui,*, Francis Degache,*
    *Contact email: alexandre.grillon@heig-vd.ch, andres.perez-uribe@heig-vd.ch, hector-fabio.satizabal-mejia@heig-vd.ch, laurent.gantel@hesge.ch, david.dasilva-andrade@hesge.ch, andres.upegui@hesge.ch, francis.degache@hesav.ch

    Abstract

    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.