Stress classification with in-ear heartbeat sounds
The final system demonstrates the viability of robust stress recognition with only in-ear heartbeat sounds, which could expand the capabilities of hearing devices used to address conditions related to stress and noise. The proposed data augmentation method effectively identified and addressed artifact-related biases, which could broadly be applied to improve robustness of biosignal monitoring with machine learning.
Authors
- Alain Vinet (ORCID: https://orcid.org/0000-0003-2474-5827)
- Bérangère Villatte
- Jérémie Voix (ORCID: https://orcid.org/0000-0002-0097-4054)
- Danielle Benesch (ORCID: https://orcid.org/0000-0002-2002-2325)
- Rachel Bouserhal (ORCID: https://orcid.org/0000-0003-0460-5798)
- Sylvie Hébert (ORCID: https://orcid.org/0000-0003-0214-3884)
Institutions
- Université du Québec à Montréal (CA)
- Hôpital du Sacré-Cœur de Montréal (CA)
- Centre for Interdisciplinary Research in Music Media and Technology (CA)
- École de Technologie Supérieure (CA)
Publication Details
- Journal
- Computers in Biology and Medicine
- Published
- 2024-12-31
- DOI
- https://doi.org/10.1016/j.compbiomed.2024.109555
- Citations
- 3
- Primary Topic
- Non-Invasive Vital Sign Monitoring
- Type
- article
- Field-Weighted Citation Impact
- 0.55
Funders
- Centre for Interdisciplinary Research in Music Media and Technology
- Deutscher Akademischer Austauschdienst
- Mitacs
- Natural Sciences and Engineering Research Council of Canada