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.
@article{arxiv.2007.06062,
title = {Transfer Learning for Activity Recognition in Mobile Health},
author = {Yuchao Ma and Andrew T. Campbell and Diane J. Cook and John Lach and Shwetak N. Patel and Thomas Ploetz and Majid Sarrafzadeh and Donna Spruijt-Metz and Hassan Ghasemzadeh},
journal= {arXiv preprint arXiv:2007.06062},
year = {2020}
}