EEG_GLT-Net: Optimising EEG graphs for real-time motor imagery signals classification

Aung, HW; Li, JJ; Shi, B; An, Y; Su, SW

EEG_GLT-Net: Optimising EEG graphs for real-time motor imagery signals classification

Aung, HW Li, JJ Shi, B An, Y Su, SW

Permalink

Publisher:: ELSEVIER SCI LTD
Publication Type:: Journal Article
Citation:: Biomedical Signal Processing and Control, 2025, 104
Issue Date:: 2025-06-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (4.93 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Aung, HW
dc.contributor.author	Li, JJ
dc.contributor.author	Shi, B
dc.contributor.author	An, Y
dc.contributor.author	Su, SW
dc.date.accessioned	2025-08-06T03:52:45Z
dc.date.available	2025-08-06T03:52:45Z
dc.date.issued	2025-06-01
dc.identifier.citation	Biomedical Signal Processing and Control, 2025, 104
dc.identifier.issn	1746-8094
dc.identifier.issn	1746-8108
dc.identifier.uri	http://hdl.handle.net/10453/189124
dc.description.abstract	Brain-Computer Interfaces (BCIs) connect the brain to external control devices, necessitating the accurate translation of brain signals such as from electroencephalography (EEG) into executable commands. EEG MI classification has numerous applications, including neurorehabilitation for stroke patients, control of assistive robotic devices, and advancements in neurofeedback systems. Graph Neural Networks (GCN) have been increasingly applied for classifying EEG Motor Imagery (MI) signals, primarily because they incorporates the spatial relationships among EEG channels, resulting in improved accuracy over traditional convolutional methods. However, existing methods for constructing adjacency matrices, such as Geodesic distances, Pearson Correlation Coefficient (PCC), and others, often rely on predefined inter-channel relationships. These methods not only demand high computational resources during inference but often achieve limited performance accuracy, particularly for single time-point EEG MI classification where rapid interpretation is crucial. To address this, our paper introduces the EEG Graph Lottery Ticket (EEG_GLT) algorithm, an innovative technique for constructing adjacency matrices for EEG channels. This method does not require pre-existing knowledge of inter-channel relationships, and it can be tailored to suit both individual subjects and GCN model architectures. We conducted an empirical study with 20 subjects and six different GCN architectures to compare the performance of our EEG_GLT adjacency matrix against both Geodesic and PCC adjacency matrices on time-resolved EEG MI dataset, PhysioNet dataset. Our EEG_GLT method consistently exceeded performance accuracy benchmarks. Additionally, we compared our model with state-of-the-art models, achieving superior results. EEG_GLT algorithm marks a breakthrough in development of optimal adjacency matrices, effectively boosting both computational accuracy and efficiency, making it well-suited for single time point classification of EEG MI signals that demand intensive computational resources.
dc.language	English
dc.publisher	ELSEVIER SCI LTD
dc.relation.ispartof	Biomedical Signal Processing and Control
dc.relation.isbasedon	10.1016/j.bspc.2024.107458
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	0903 Biomedical Engineering, 0906 Electrical and Electronic Engineering, 1004 Medical Biotechnology
dc.subject.classification	Biomedical Engineering
dc.subject.classification	3006 Food sciences
dc.subject.classification	4003 Biomedical engineering
dc.title	EEG_GLT-Net: Optimising EEG graphs for real-time motor imagery signals classification
dc.type	Journal Article
utslib.citation.volume	104
utslib.for	0903 Biomedical Engineering
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	1004 Medical Biotechnology
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Biomedical Engineering
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	University of Technology Sydney/UTS Groups
pubs.organisational-group	University of Technology Sydney/UTS Groups/Centre for Health Technologies (CHT)
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/
dc.date.updated	2025-08-06T03:52:41Z
pubs.publication-status	Published
pubs.volume	104

Abstract:

Brain-Computer Interfaces (BCIs) connect the brain to external control devices, necessitating the accurate translation of brain signals such as from electroencephalography (EEG) into executable commands. EEG MI classification has numerous applications, including neurorehabilitation for stroke patients, control of assistive robotic devices, and advancements in neurofeedback systems. Graph Neural Networks (GCN) have been increasingly applied for classifying EEG Motor Imagery (MI) signals, primarily because they incorporates the spatial relationships among EEG channels, resulting in improved accuracy over traditional convolutional methods. However, existing methods for constructing adjacency matrices, such as Geodesic distances, Pearson Correlation Coefficient (PCC), and others, often rely on predefined inter-channel relationships. These methods not only demand high computational resources during inference but often achieve limited performance accuracy, particularly for single time-point EEG MI classification where rapid interpretation is crucial. To address this, our paper introduces the EEG Graph Lottery Ticket (EEG_GLT) algorithm, an innovative technique for constructing adjacency matrices for EEG channels. This method does not require pre-existing knowledge of inter-channel relationships, and it can be tailored to suit both individual subjects and GCN model architectures. We conducted an empirical study with 20 subjects and six different GCN architectures to compare the performance of our EEG_GLT adjacency matrix against both Geodesic and PCC adjacency matrices on time-resolved EEG MI dataset, PhysioNet dataset. Our EEG_GLT method consistently exceeded performance accuracy benchmarks. Additionally, we compared our model with state-of-the-art models, achieving superior results. EEG_GLT algorithm marks a breakthrough in development of optimal adjacency matrices, effectively boosting both computational accuracy and efficiency, making it well-suited for single time point classification of EEG MI signals that demand intensive computational resources.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/189124