Data Augmentation, Multimodality, Subject and Activity Specificity Improve Wearable Electrocardiogram Denoising with Autoencoders

João Saraiva, João Saraiva, João Saraiva, Mariana Abreu, Mariana Abreu, Ana Carmo, Ana Carmo, Ana Fred, Ana Fred, Hugo Plácido da Silva, Hugo Plácido da Silva

2023

Abstract

Event detection based on biosignals continuously acquired by wearable devices has become an emergent topic. Particularly, real-time event detection with the electrocardiogram (ECG) has been explored to monitor heart conditions and epileptic seizures in the ambulatory. However, ECG acquired in the ambulatory is much more prone to noise and artifacts, due to the dynamic nature of these environments. Therefore, real-time and robust ECG denoising methods are crucial if event detection is meant to succeed. Denoising autoencoders (DAEs) are studied as robust and fast methods to attenuate ECG noise and artifacts. ECG data augmentation techniques are shown to effectively improve the performance of such a deep learning method. Activity and subject specific models are shown to output better ECG denoised estimates, than non-specific ones. And using accelerometry (ACC) as noise reference exemplifies how biosignal multimodality improves ECG attenuation of muscle and motion artifacts. Therefore, this work establishes effective design techniques to be considered when engineering ECG deep learning models.

Paper Citation

in Harvard Style

Saraiva J., Abreu M., Carmo A., Fred A. and Plácido da Silva H. (2023). Data Augmentation, Multimodality, Subject and Activity Specificity Improve Wearable Electrocardiogram Denoising with Autoencoders. In Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - Volume 4: BIOSIGNALS; ISBN 978-989-758-631-6, SciTePress, pages 133-145. DOI: 10.5220/0011883400003414

in Bibtex Style

@conference{biosignals23,
author={João Saraiva and Mariana Abreu and Ana Carmo and Ana Fred and Hugo Plácido da Silva},
title={Data Augmentation, Multimodality, Subject and Activity Specificity Improve Wearable Electrocardiogram Denoising with Autoencoders},
booktitle={Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - Volume 4: BIOSIGNALS},
year={2023},
pages={133-145},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011883400003414},
isbn={978-989-758-631-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - Volume 4: BIOSIGNALS
TI - Data Augmentation, Multimodality, Subject and Activity Specificity Improve Wearable Electrocardiogram Denoising with Autoencoders
SN - 978-989-758-631-6
AU - Saraiva J.
AU - Abreu M.
AU - Carmo A.
AU - Fred A.
AU - Plácido da Silva H.
PY - 2023
SP - 133
EP - 145
DO - 10.5220/0011883400003414
PB - SciTePress