Self-Supervised PPG Representation Learning Shows High Inter-Subject Variability

Ramin Ghorbani*, Marcel J.T. Reinders, David M.J. Tax

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

1 Citation (Scopus)
83 Downloads (Pure)

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.

Original languageEnglish
Title of host publicationICMLT 2023 - Proceedings of 2023 8th International Conference on Machine Learning Technologies
PublisherAssociation for Computing Machinery (ACM)
Pages127-132
Number of pages6
ISBN (Electronic)9781450398329
DOIs
Publication statusPublished - 2023
Event8th International Conference on Machine Learning Technologies, ICMLT 2023 - Stockholm, Sweden
Duration: 10 Mar 202312 Mar 2023

Publication series

NameACM International Conference Proceeding Series

Conference

Conference8th International Conference on Machine Learning Technologies, ICMLT 2023
Country/TerritorySweden
CityStockholm
Period10/03/2312/03/23

Keywords

  • Autoencoder
  • Human Activity Recognition
  • Inter-Subject Variability
  • PPG Signal
  • Representation Learning
  • Self-Supervised Learning

Fingerprint

Dive into the research topics of 'Self-Supervised PPG Representation Learning Shows High Inter-Subject Variability'. Together they form a unique fingerprint.

Cite this