April 2015


ACTIDOTE: ACTIvity measurement in persons with Disabilities using On-body and wheelchair-mounTed sEnsors

Physical inactivity has been identified as a major contributor to the exacerbation of physical illnesses. The WHO identified it as the fourth leading risk factor of global mortality after high blood pressure, tobacco use and high blood glucose. Therefore, in recent years, many actions against inactivity have come to the fore. For instance, diverse pedometer devices have been developed to help people reach certain physical activity goals, like walking 30 minutes per day.

However, an equivalent recommendation for disabled people using wheelchairs is missing and the few studies that have dealt with this issue concluded that commercial physical activity measurement devices are not appropriate for them.

This project has the objective of developing an appropriate physical activity measurement system for disabled people using wheelchairs, by exploiting on-body and wheelchair-mounted wireless sensors. This project will gather together the teams of Prof. Degache (Haute Ecole de Santé Vaud HESAV), expert in Human motricity and Handicap, and Prof. Perez-Uribe (Haute Ecole d'Ingénieure et de Gestion du Canton de Vaud), expert in Intelligent Data Analysis and Ubiquitous Computing.

The project will be divided into two phases.

During the first phase, we will use diverse configurations of motion sensors including accelerometers, gyroscopes and magnetometers to assess the physical activity of healthy people on a wheelchair. We will apply feature-extraction and machine learning techniques to the sensor readings in order to come-up with non-linear models matching the relationship between captured raw data and energy expenditure, provided as a reference by a portable metabolic cart. Diverse activities like resting, deskwork, and wheelchair propulsion along different surfaces and slopes will be considered.

During the second phase, we will evaluate our system with disabled patients suffering from Spinal Cord Injury, form T6 level.
Our approach is quite original, compared to the few studies having investigated the use of commercial sensor-based activity monitors with disabled people, in that we will use machine-learning nonlinear regression techniques to process and perform sensor fusion as well as diverse sensor configurations on both the user and the wheelchair.
The result of this project will be the ACTIDOTE system, a disabled-oriented physical activity measurement system capable of encouraging wheelchair users to use ACTIVITY as an ANTIDOTE to physical illness exacerbation.

The project's presentation given during the health-engineering event of October 1, 2015 named "Innovation serving public health" is available here in french : Actidote