Article Dans Une Revue IEEE Transactions on Neural Systems and Rehabilitation Engineering Année : 2024

A Strong and Simple Deep Learning Baseline for BCI Motor Imagery Decoding

Résumé

We propose EEG-SimpleConv, a straightforward 1D convolutional neural network for Motor Imagery decoding in BCI. Our main motivation is to propose a simple and performing baseline that achieves high classification accuracy, using only standard ingredients from the literature, to serve as a standard for comparison. The proposed architecture is composed of standard layers, including 1D convolutions, batch normalisations, ReLU activation functions and pooling functions. EEG-SimpleConv architecture is accompanied by a straightforward and tailored training routine, which is subjected to an extensive ablation study to quantify the influence of its components. We evaluate its performance on four EEG Motor Imagery datasets, including simulated online setups, and compare it to recent Deep Learning and Machine Learning approaches. EEG-SimpleConv is at least as good or far more efficient than other approaches, showing strong knowledge-transfer capabilities across subjects, at the cost of a low inference time. We believe that using standard components and ingredients can significantly help the adoption of Deep Learning approaches for BCI. We make the code of the models and the experiments accessible.

Fichier principal
Vignette du fichier
A_Strong_and_Simple_Deep_Learning_Baseline_for_BCI_Motor_Imagery_Decoding.pdf (1.07 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-05002793 , version 1 (27-03-2025)

Licence

Identifiants

Citer

Yassine El Ouahidi, Vincent Gripon, Bastien Pasdeloup, Ghaith Bouallegue, Nicolas Farrugia, et al.. A Strong and Simple Deep Learning Baseline for BCI Motor Imagery Decoding. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2024, 32, pp.3338-3347. ⟨10.1109/TNSRE.2024.3451010⟩. ⟨hal-05002793⟩
83 Consultations
400 Téléchargements

Altmetric

Partager

  • More