Improved motor imagery decoding with spatiotemporal filtering based on beta burst kernels - Équipe CoPhy : Computation, Cognition et Neurophysiologie du CRNL
Communication Dans Un Congrès Année : 2024

Improved motor imagery decoding with spatiotemporal filtering based on beta burst kernels

Résumé

The description of the event-related desynchronization and synchronization phenomena in the mu and beta frequency bands has to a significant extent shaped our understanding of motor-related brain processes. Accordingly, Brain-Computer Interface applications leveraging attempted or imagined movements usually depend on spatially-and bandlimited power changes as the brain markers of interest. Yet, converging neuroscience evidence question the idea that signal power best describes the movementrelated modulation of brain activity. On a single-trial level, beta band activity is characterized by short, transient and heterogeneous events termed bursts rather than sustained oscillations. In a recent study we demonstrated that a beta burst analysis of hand motor imagery binary classification tasks is often superior to beta power in terms of classification score. Here we expand upon this idea proposing a comparable to stateof-the-art algorithm. We confirm our previous results by using convolution kernels extracted from beta bursts. Moreover, we show that these kernels can effectively be used in inter-session transfer learning strategies.

Domaines

Neurosciences
Fichier principal
Vignette du fichier
Beta_burst_kernels_transfer_learning_GBCIC2024.pdf (1005.03 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-04701260 , version 1 (18-09-2024)

Licence

Identifiants

  • HAL Id : hal-04701260 , version 1

Citer

Sotirios Papadopoulos, Ludovic Darmet, Maciej J Szul, Marco Congedo, James Bonaiuto, et al.. Improved motor imagery decoding with spatiotemporal filtering based on beta burst kernels. 9th Graz Brain-Computer Interface Conference 2024, Sep 2024, Graz, Austria. ⟨hal-04701260⟩
0 Consultations
0 Téléchargements

Partager

More