11th International Conference on Body Area Networks

Research Article

Activity Level Assessment of Wheelchair Users Using Smart Cushion

  • @INPROCEEDINGS{10.4108/eai.15-12-2016.2267668,
        author={Congcong Ma and Raffaele Gravina and Wenfeng Li and Yu Zhang and Qimeng Li and Giancarlo Fortino},
        title={Activity Level Assessment of Wheelchair Users Using Smart Cushion},
        proceedings={11th International Conference on Body Area Networks},
        keywords={activity level assessment smart cushion wheelchair users posture sequences hamming weight},
  • Congcong Ma
    Raffaele Gravina
    Wenfeng Li
    Yu Zhang
    Qimeng Li
    Giancarlo Fortino
    Year: 2017
    Activity Level Assessment of Wheelchair Users Using Smart Cushion
    DOI: 10.4108/eai.15-12-2016.2267668
Congcong Ma1, Raffaele Gravina2, Wenfeng Li1,*, Yu Zhang1, Qimeng Li2, Giancarlo Fortino2
  • 1: Wuhan University of Technology
  • 2: University of Calabria
*Contact email: liwf@whut.edu.cn


A large majority of worldwide population, such as office workers and long journey vehicle drivers, spends lot of time everyday in sedentary activities. In this paper, we specifically focus on the assessment of different levels of wheelchair users' activity. The postures that wheelchair users assume during daily activities hide valuable information that can reveal their wellness and general health condition.

Aiming at mining such underlying information, we propose a hamming weight based algorithm to assess the activity level from sitting posture sequences. Using a smart cushion placed on the wheelchair, we can monitor users' postures. Postures sequence is transformed into binary value vector segments in order to reduce the computation load. The algorithm can detect three levels of activity (stationary, moderate or hyperactivity) with high accuracy. The proposed method could be embedded into several potential applications such as health estimation of sitting subjects, activity statistics, and detection of abnormal activities.