TY  - JOUR
IS  - 1
N1  - Copyright©2025 by the authors. Published by ELS Publishing. This work is licensed under a Creative Commons
Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any
medium provided the original work is properly cited.
TI  - Advancing EEG classification for neurodegenerative conditions using BCI: a graph attention approach with phase synchrony
AV  - public
Y1  - 2025/01/20/
VL  - 2
JF  - Neuroelectronics
A1  - Patel, Rishan
A1  - Zhu, Ziyue
A1  - Bryson, Barney
A1  - Carlson, Tom
A1  - Jiang, Dai
A1  - Demosthenous, Andreas
KW  - motor imagery
KW  -  amyotrophic lateral sclerosis
KW  -  graph attention networks
KW  -  electroencephalography
KW  - 
brain computer interface (BCI)
N2  - Accurately classifying electroencephalogram (EEG) signals, especially for individuals
with neurodegenerative conditions such as amyotrophic lateral sclerosis (ALS), poses a significant
challenge due to high inter-subject and inter-session changes in signal. This study introduces a novel
three-layer graph attention network (GAT) model for motor imagery (MI) classification, utilizing phase
locking value (PLV) as the graph input. The GAT model outperforms state-of-the-art deep learning
methods, demonstrating notable improvements with a two-class accuracy of 74.06% on an ALS dataset
(approximately 320 trials collected over 1-2 months), and 71.89% on the BCI Comp IV 2a Dataset. This
improvement demonstrates the effectiveness of graph-based representations to enhance classification
performance for neurodegenerative conditions. There are statistically significant reductions in variance
compared to state-of-the-art, due to subject-specific attention given by the model during testing. These
results support the hypothesis that phase-locking value-based graph representations can enhance neural
representations in BCIs, offering promising avenues for more personalized approaches in MI classification.
This study highlights the potential for further optimizing GAT architectures and feature sets, pointing to
future research directions that could improve performance and efficiency in MI classification tasks whilst
establishing a lightweight methodology.
ID  - discovery10205463
PB  - ELS Publishing Co. Limited
UR  - https://doi.org/10.55092/neuroelectronics20250001
SN  - 3006-1032
ER  -