Activity recognition of wheelchair users based on sequence feature in time-series
Congcong Ma, Raffaele Gravina, Qimeng Li, Yu Zhang, Wenfeng Li, Giancarlo Fortino · 2017
Mobility impaired individuals need the wheelchair to support their independent life, so monitor activities performed on the wheelchair can provide significant insights on their general health status. Activity recognition related to healthy people is a well established research area; however, only few works addressed this problem for wheelchair users. This paper proposes a novel approach based on dynamic Bayesian networks to recognize physical activities performed on a wheelchair. We equipped the wheelchair seat with a pressure detection unit and attached two inertial measurement units on the user's wrists. We focus on common basic activities and specifically, to experimentally evaluate our method, we defined four dynamic activities (moving forward, moving backward, moving left-circle, moving right-circle) and two static activities (left-right swing, forward-backward swing). Data is collected using a smart wheelchair system we developed in previous research. Firstly, we generate the posture sequence from the pressure signals and detect the raw acceleration data from inertial measurement units; then, we fuse the posture sequence and inertial features to detect the postural-based activities. Results shows that our proposed method can achieve an overall classification accuracy of 91.88%.