Print Email Facebook Twitter Self-Supervised PPG Representation Learning Shows High Inter-Subject Variability Title Self-Supervised PPG Representation Learning Shows High Inter-Subject Variability Author Ghorbani, R. (TU Delft Pattern Recognition and Bioinformatics) Reinders, M.J.T. (TU Delft Pattern Recognition and Bioinformatics) Tax, D.M.J. (TU Delft Pattern Recognition and Bioinformatics) Date 2023 Abstract With the progress of sensor technology in wearables, the collection and analysis of PPG signals are gaining more interest. Using Machine Learning, the cardiac rhythm corresponding to PPG signals can be used to predict different tasks such as activity recognition, sleep stage detection, or more general health status. However, supervised learning is often limited by the amount of available labeled data, which is typically expensive to obtain. To address this problem, we propose a Self-Supervised Learning (SSL) method with a pretext task of signal reconstruction to learn an informative generalized PPG representation. The performance of the proposed SSL framework is compared with two fully supervised baselines. The results show that in a very limited label data setting (10 samples per class or less), using SSL is beneficial, and a simple classifier trained on SSL-learned representations outperforms fully supervised deep neural networks. However, the results reveal that the SSL-learned representations are too focused on encoding the subjects. Unfortunately, there is high inter-subject variability in the SSL-learned representations, which makes working with this data more challenging when labeled data is scarce. The high inter-subject variability suggests that there is still room for improvements in learning representations. In general, the results suggest that SSL may pave the way for the broader use of machine learning models on PPG data in label-scarce regimes. Subject AutoencoderHuman Activity RecognitionInter-Subject VariabilityPPG SignalRepresentation LearningSelf-Supervised Learning To reference this document use: http://resolver.tudelft.nl/uuid:22142e58-d187-4279-8817-f5ca120ee0a4 DOI https://doi.org/10.1145/3589883.3589902 Publisher Association for Computing Machinery (ACM) ISBN 9781450398329 Source ICMLT 2023 - Proceedings of 2023 8th International Conference on Machine Learning Technologies Event 8th International Conference on Machine Learning Technologies, ICMLT 2023, 2023-03-10 → 2023-03-12, Stockholm, Sweden Series ACM International Conference Proceeding Series Part of collection Institutional Repository Document type conference paper Rights © 2023 R. Ghorbani, M.J.T. Reinders, D.M.J. Tax Files PDF 3589883.3589902.pdf 805.08 KB Close viewer /islandora/object/uuid:22142e58-d187-4279-8817-f5ca120ee0a4/datastream/OBJ/view