npj Digital Medicine · 2024 · 119 citations · 37 references
ComputingComputer ScienceData ScienceComputer VisionData MiningMachine LearningAction RecognitionActivity PatternsDeep LearningPattern RecognitionSelf-supervised LearningWearable Health TechnologiesActivity MonitoringActivity RecognitionHuman Activity RecognitionSelf-supervised Policy LearningSelf-supervised Representation LearningSelf-supervised Time Series ClassificationWearable Sensor Data
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.
37
Momentum Contrast for Unsupervised Visual Representation Learning
Kaiming He, Haoqi Fan, Yuxin Wu et al. · 2020 · 12K citations
UMAP: Uniform Manifold Approximation and Projection
Leland McInnes, John Healy, Nathaniel Saul et al. · The Journal of Open Source Software · 2018 · 9.6K citations · Full text