Work

Transfer Learning for Activity Recognition in Mobile Health

Year: 2020

Type: preprint

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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2007.06062

Authors: Ma, Yuchao, Campbell, Andrew T., Cook, Diane J., Lach, John, Patel, Shwetak N., Ploetz, Thomas, Sarrafzadeh, Majid, Spruijt-Metz, Donna, Ghasemzadeh, Hassan

Language: English

Topic: Context-Aware Activity Recognition Systems

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W3041347553

Cites: 3

Cited by: 3

Related to: 10