RNN-LSTM neural network for predicting fMRI neurofeedback scores from EEG signals - Archive ouverte HAL Access content directly
Poster Communications Year : 2022

RNN-LSTM neural network for predicting fMRI neurofeedback scores from EEG signals

Caroline Pinte
  • Function : Author
  • PersonId : 1170974
Claire Cury
Pierre Maurel

Abstract

In the context of neurofeedback (NF), simultaneous acquisitions with electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) provide more effective NF training due to their complementarity [1]. However, the use of MRI is expensive and draining for the subject. Therefore, we would like to reduce its use. Following the work of Cury et al. [2], we propose a method based on a recurrent neural network (RNN) that consists in learning a model from simultaneous EEG-fMRI acquisitions to predict NF-fMRI scores with EEG signals alone.
Fichier principal
Vignette du fichier
Pinte_Abstract-Poster_rtFIN2022.pdf (146.3 Ko) Télécharger le fichier
Pinte_Poster_rtFIN2022.pdf (856.05 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03798824 , version 1 (05-10-2022)

Licence

Attribution

Identifiers

  • HAL Id : hal-03798824 , version 1

Cite

Caroline Pinte, Claire Cury, Pierre Maurel. RNN-LSTM neural network for predicting fMRI neurofeedback scores from EEG signals. rtFIN 2022 - Real-time Functional Imaging and Neurofeedback, Oct 2022, New Haven, United States. ⟨hal-03798824⟩
161 View
94 Download

Share

Gmail Facebook X LinkedIn More