TY - GEN
T1 - Self-Supervised PPG Representation Learning Shows High Inter-Subject Variability
AU - Ghorbani, Ramin
AU - Reinders, Marcel J.T.
AU - Tax, David M.J.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
KW - Autoencoder
KW - Human Activity Recognition
KW - Inter-Subject Variability
KW - PPG Signal
KW - Representation Learning
KW - Self-Supervised Learning
UR - http://www.scopus.com/inward/record.url?scp=85167840922&partnerID=8YFLogxK
U2 - 10.1145/3589883.3589902
DO - 10.1145/3589883.3589902
M3 - Conference contribution
AN - SCOPUS:85167840922
T3 - ACM International Conference Proceeding Series
SP - 127
EP - 132
BT - ICMLT 2023 - Proceedings of 2023 8th International Conference on Machine Learning Technologies
PB - Association for Computing Machinery (ACM)
T2 - 8th International Conference on Machine Learning Technologies, ICMLT 2023
Y2 - 10 March 2023 through 12 March 2023
ER -