Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Data
This work addresses the challenge of building generalizable and high-performance activity classifiers for researchers and developers, though it is incremental as it applies existing self-supervised techniques to a new large dataset.
The study tackled the problem of limited labeled data for human activity recognition by applying self-supervised learning to a large unlabeled dataset of over 700,000 person-days of wearable sensor data, resulting in a model that outperformed baselines with F1 relative improvements ranging from 2.5% to 100% (median 18.4%) across seven benchmark datasets.
Advances in deep learning for human activity recognition have been relatively limited due to the lack of large labelled datasets. In this study, we leverage self-supervised learning techniques on the UK-Biobank activity tracker dataset--the largest of its kind to date--containing more than 700,000 person-days of unlabelled wearable sensor data. Our resulting activity recognition model consistently outperformed strong baselines across seven benchmark datasets, with an F1 relative improvement of 2.5%-100% (median 18.4%), the largest improvements occurring in the smaller datasets. In contrast to previous studies, our results generalise across external datasets, devices, and environments. Our open-source model will help researchers and developers to build customisable and generalisable activity classifiers with high performance.