English

Transfer Learning for Activity Recognition in Mobile Health

Machine Learning 2020-07-15 v1 Human-Computer Interaction Machine Learning

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-23T17:03:36.172Z