Clinically oriented use of wearables for diagnosis, monitoring and individualized exercise prescription. Data-driven classification and modeling of human activity from raw inertial and accelerometric signals.

Objectives

1. Wearable technology in primary care for personalized exercise medicine

2. Activity recognition from thigh, wrist and upper-body accelerometry

3. Feature engineering versus end-to-end learning on inertial data

4. Context inference in IMU sensing

5. Compression and efficient processing of biomedical/physiological signals