Self-supervised learning for human activity recognition using 700,000 person-days of wearable data.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 38609437.
- Also identified by DOI 10.1038/s41746-024-01062-3 and PMC identifier 11015005.
- Licence recorded as CC BY.
- The licence permits redistribution, so the abstract is shown in full and the full text is available from the publisher.
Abstract
Accurate physical activity monitoring is essential to understand the impact of physical activity on one's physical health and overall well-being. However, advances in human activity recognition algorithms have been constrained by the limited availability of large labelled datasets. This study aims to leverage recent advances in self-supervised learning to exploit the large-scale UK Biobank accelerometer dataset-a 700,000 person-days unlabelled dataset-in order to build models with vastly improved generalisability and accuracy. Our resulting models consistently outperform strong baselines across eight benchmark datasets, with an F1 relative improvement of 2.5-130.9% (median 24.4%). More importantly, in contrast to previous reports, our results generalise across external datasets, cohorts, living environments, and sensor devices. Our open-sourced pre-trained models will be valuable in domains with limited labelled data or where good sampling coverage (across devices, populations, and activities) is hard to achieve.