A systematic evaluation of Euclidean alignment with deep learning for EEG decoding

• Published in: Journal of neural engineering Vol. 21; no. 3; pp. 36038 - 36050
• Main Authors: Junqueira, Bruna, Aristimunha, Bruno, Chevallier, Sylvain, de Camargo, Raphael Y
• Format: Journal Article
• Language: English
• Published: England IOP Publishing 01.06.2024
• Subjects: Adult; Algorithms; Artificial Intelligence; Brain-Computer Interfaces; Cognitive science; Computer Science; Deep Learning; Electroencephalography - methods; Euclidean alignment; Female; Humans; Male; neural network; Neuroscience; Signal and Image Processing; Brain–Computer interfaces; Euclidean alignment; neural network; Brain-Computer Interfaces; Neural Network; Euclidean Alignment; Brain-Computer Interfaces Neural Network Euclidean Alignment
• ISSN: 1741-2560; 1741-2552; 1741-2552
• DOI: 10.1088/1741-2552/ad4f18

Objective: Electroencephalography signals are frequently used for various Brain–Computer interface (BCI) tasks. While deep learning (DL) techniques have shown promising results, they are hindered by the substantial data requirements. By leveraging data from multiple subjects, transfer learning enables more effective training of DL models. A technique that is gaining popularity is Euclidean alignment (EA) due to its ease of use, low computational complexity, and compatibility with DL models. However, few studies evaluate its impact on the training performance of shared and individual DL models. In this work, we systematically evaluate the effect of EA combined with DL for decoding BCI signals. Approach: We used EA as a pre-processing step to train shared DL models with data from multiple subjects and evaluated their transferability to new subjects. Main results: Our experimental results show that it improves decoding in the target subject by 4.33% and decreases convergence time by more than 70%. We also trained individual models for each subject to use as a majority-voting ensemble classifier. In this scenario, using EA improved the 3-model ensemble accuracy by 3.71%. However, when compared to the shared model with EA, the ensemble accuracy was 3.62% lower. Significance: EA succeeds in the task of improving transfer learning performance with DL models and, could be used as a standard pre-processing technique.