Le, Than-Dung, Macabiau, Clara, Albert, Kévin, Jouvet, Philippe et Noumeir, Rita.
2024.
« A novel transformer-based self-supervised learning method to enhance photoplethysmogram signal artifact detection ».
IEEE Access, vol. 12.
pp. 159860-159874.
Prévisualisation |
PDF
Noumeir-R-2024-29916.pdf - Version publiée Licence d'utilisation : Creative Commons CC BY-NC-ND. Télécharger (1MB) | Prévisualisation |
Résumé
Recent research has revealed that traditional machine learning methods, such as semisupervised label propagation and K-nearest neighbors, outperform Transformer-based models in artifact detection from photoplethysmogram (PPG) signals, mainly when data is limited. This study addresses the underutilization of abundant unlabeled data by employing self-supervised learning (SSL) to extract latent features from these data, followed by fine-tuning on labeled data. Our experiments demonstrate that SSL significantly enhances the Transformer model’s ability to learn representations, improving its robustness in artifact classification tasks. Among various SSL techniques—including masking, contrastive learning, and DINO (self-distillation with no labels)—contrastive learning exhibited the most stable and superior performance in small PPG datasets. Further, we delve into optimizing contrastive loss functions, which are crucial for contrastive SSL. Inspired by InfoNCE, we introduce a novel contrastive loss function that facilitates smoother training and better convergence, thereby enhancing performance in artifact classification. In summary, this study establishes the efficacy of SSL in leveraging unlabeled data, particularly in enhancing the capabilities of the Transformer model in PPG artifact detection. This approach holds promise for broader applications in PICU environments, where annotated data is often limited.
| Type de document: | Article publié dans une revue, révisé par les pairs |
|---|---|
| Professeur: | Professeur Noumeir, Rita |
| Affiliation: | Génie électrique |
| Date de dépôt: | 22 nov. 2024 21:25 |
| Dernière modification: | 02 déc. 2024 20:50 |
| URI: | https://espace2.etsmtl.ca/id/eprint/29916 |
Actions (Authentification requise)
 |
Dernière vérification avant le dépôt |