Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
A new method of monitoring physical activity that is able to detect walking upstairs using a miniature gyroscope attached to the shank is presented. Wavelet transformation, in conjunction with a simple kinematics model, was used to detect toe-off, heel-strike and foot-flat, as well cycles corresponding to stair ascent. To evaluate the system, three studies were performed. The method was first tested on 10 healthy young volunteer subjects in a gait laboratory where an ultrasonic motion system was used as a reference system. In the second study, the system was tested on three hospitalized elderly people to classify walking upstairs from walking downstairs and flat walking. In the third study, monitoring was performed on seven patients with peripheral vascular disease for 60 min during their daily physical activity. The first study revealed a close relationship between the ambulatory and the reference systems. Compared to the reference system, the ambulatory system had an overall sensitivity and specificity of 98% and 97%, respectively. In the second study, the ambulatory system also showed a very high sensitivity (> 94%) in identifying a 50 stairs ascent from walking on the flat and walking downstairs. Finally, compared with visual surveillance, we observed a relatively high accuracy in identifying 196 walking upstairs cycles through daily physical activity in the third study. Our results demonstrated a reliable technique of measuring walking upstairs during physical activity. (c) 2004 Elsevier B.V. All rights reserved.
Kamiar Aminian, Anisoara Ionescu, Gaëlle Prigent, Francesca Salis