Domain adaptation with optimal transport improves EEG sleep stage classifiers

Abstract : —Low sample size and the absence of labels on certain data limits the performances of predictive algorithms. To overcome this problem, it is sometimes possible to learn a model on a large labeled auxiliary dataset. Yet, this assumes that the two datasets exhibit similar statistical properties which is rarely the case in practice: there is a discrepancy between the large dataset, called the source, and the dataset of interest, called the target. Improving the prediction performance on the target domain by reducing the distribution discrepancy, between the source and the target domains, is known as Domain Adaptation (DA). Presently, Optimal transport DA (OTDA) methods yield state-of-the-art performances on several DA problems. In this paper, we consider the problem of sleep stage classification, and use OTDA to improve the performances of a convolutional neural network. We use features learnt from the electroencephalogram (EEG) and the electrooculogram (EOG) signals. Our results demonstrate that the method significantly improves the network predictions on the target data.
Type de document :
Communication dans un congrès
Pattern Recognition in Neuroimaging, Jun 2018, Singapour, Singapore
Liste complète des métadonnées

Littérature citée [21 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01814190
Contributeur : Stanislas Chambon <>
Soumis le : mercredi 13 juin 2018 - 04:30:27
Dernière modification le : mercredi 4 juillet 2018 - 23:14:06
Document(s) archivé(s) le : vendredi 14 septembre 2018 - 15:13:45

Fichier

main.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01814190, version 1

Citation

Stanislas Chambon, Mathieu N. Galtier, Alexandre Gramfort. Domain adaptation with optimal transport improves EEG sleep stage classifiers. Pattern Recognition in Neuroimaging, Jun 2018, Singapour, Singapore. 〈hal-01814190〉

Partager

Métriques

Consultations de la notice

202

Téléchargements de fichiers

254