Transfer Learning for Activity Recognition in Mobile Health
Yuchao Ma, Andrew Thomas Campbell, Diane J. Cook, John Lach, Shwetak Patel, Thomas Ploetz, Majid Sarrafzadeh, Donna Spruijt‐Metz, Hassan G Ghasemzadeh · arXiv (Cornell University) · 2020
While activity recognition from inertial sensors holds potential for mobile health, differences in sensing platforms and user movement patterns cause performance degradation. Aiming to address these challenges, we propose a transfer learning framework, TransFall, for sensor-based activity recognition. TransFall's design contains a two-tier data transformation, a label estimation layer, and a model generation layer to recognize activities for the new scenario. We validate TransFall analytically and empirically.