Mehrban, Malahat H. K., Voix, Jérémie et Bouserhal, Rachel E..
2024.
« Classification of breathing phase and path with in-ear microphones ».
Sensors, vol. 24, nº 20.
Prévisualisation |
PDF
Voix-J-2024-29804.pdf - Version publiée Licence d'utilisation : Creative Commons CC BY. Télécharger (1MB) | Prévisualisation |
Résumé
In recent years, the use of smart in-ear devices (hearables) for health monitoring has gained popularity. Previous research on in-ear breath monitoring with hearables uses signal processing techniques based on peak detection. Such techniques are greatly affected by movement artifacts and other challenging real-world conditions. In this study, we use an existing database of various breathing types captured using an in-ear microphone to classify breathing path and phase. Having a small dataset, we use XGBoost, a simple and fast classifier, to address three different classification challenges. We achieve an accuracy of 86.8% for a binary path classifier, 74.1% for a binary phase classifier, and 67.2% for a four-class path and phase classifier. Our path classifier outperforms existing algorithms in recall and F1, highlighting the reliability of our approach. This work demonstrates the feasibility of the use of hearables in continuous breath monitoring tasks with machine learning.
| Type de document: | Article publié dans une revue, révisé par les pairs |
|---|---|
| Professeur: | Professeur Voix, Jérémie Bouserhal, Rachel |
| Affiliation: | Génie mécanique, Génie électrique |
| Date de dépôt: | 12 nov. 2024 16:44 |
| Dernière modification: | 22 nov. 2024 15:21 |
| URI: | https://espace2.etsmtl.ca/id/eprint/29804 |
Actions (Authentification requise)
 |
Dernière vérification avant le dépôt |