Transformer-based hybrid systems to combat BCI illiteracy.

Pfeffer, MA; Wong, JKW; Ling, SH

Transformer-based hybrid systems to combat BCI illiteracy.

Pfeffer, MA Wong, JKW Ling, SH

Permalink

Publisher:: Elsevier
Publication Type:: Journal Article
Citation:: Comput Biol Med, 2026, 200, pp. 111378
Issue Date:: 2026-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (6.84 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Pfeffer, MA
dc.contributor.author	Wong, JKW
dc.contributor.author	Ling, SH
dc.date.accessioned	2026-01-14T05:13:08Z
dc.date.available	2025-12-05
dc.date.available	2026-01-14T05:13:08Z
dc.date.issued	2026-01-01
dc.identifier.citation	Comput Biol Med, 2026, 200, pp. 111378
dc.identifier.issn	0010-4825
dc.identifier.issn	1879-0534
dc.identifier.uri	http://hdl.handle.net/10453/191826
dc.description.abstract	This study addresses the challenge of enhancing Brain-Computer Interfaces (BCIs), focusing on low Signal-to-Noise Ratios and "BCI illiteracy" often affecting up to 20% of users. Transformer-based models show promise but remain underexplored. Three experiments were conducted. Experiment A assessed the performance of architectures combining Convolutional and Transformer Blocks for binary Motor Imagery (MI) classification. Experiment B introduced a hybrid system, refining both block types and adding a Noise Focus Block to infuse Stochastic Noise, enhancing multi-class classification robustness. Experiment C evaluated the emerging architectures on 106 subjects, focusing on robustness across weak and strong learners. In Experiment A, the best networks achieved a validation accuracy of 0.914 and a loss of 0.146 (p=0.000967, F=12.675). In Experiment B, the proposed architecture improved multi-class MI classification to 84.5% on Dataset II, significantly improving performance for BCI-illiterate users. Experiment C showed a Kappa >83%, reduced standard deviation, and a highest validation accuracy of 88.69% across all individuals. The hybrid integration of Transformers, CNNs, and Noise-Resonance-based layers significantly enhances classification performance, particularly for weak BCI learners. Further research is recommended to optimize hybrid system architectures and hyperparameter settings to overcome current limitations in BCI performance.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	Elsevier
dc.relation.ispartof	Comput Biol Med
dc.relation.isbasedon	10.1016/j.compbiomed.2025.111378
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	08 Information and Computing Sciences, 09 Engineering, 11 Medical and Health Sciences
dc.subject.classification	Biomedical Engineering
dc.subject.classification	3102 Bioinformatics and computational biology
dc.subject.classification	4203 Health services and systems
dc.subject.classification	4601 Applied computing
dc.subject.mesh	Brain-Computer Interfaces
dc.subject.mesh	Humans
dc.subject.mesh	Male
dc.subject.mesh	Female
dc.subject.mesh	Adult
dc.subject.mesh	Signal Processing, Computer-Assisted
dc.subject.mesh	Humans
dc.subject.mesh	Signal Processing, Computer-Assisted
dc.subject.mesh	Adult
dc.subject.mesh	Female
dc.subject.mesh	Male
dc.subject.mesh	Brain-Computer Interfaces
dc.title	Transformer-based hybrid systems to combat BCI illiteracy.
dc.type	Journal Article
utslib.citation.volume	200
utslib.location.activity	United States
utslib.for	08 Information and Computing Sciences
utslib.for	09 Engineering
utslib.for	11 Medical and Health Sciences
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 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)
pubs.organisational-group	University of Technology Sydney/Faculty of Design and Society
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	2026-01-14T05:13:04Z
pubs.publication-status	Published
pubs.volume	200

Abstract:

This study addresses the challenge of enhancing Brain-Computer Interfaces (BCIs), focusing on low Signal-to-Noise Ratios and "BCI illiteracy" often affecting up to 20% of users. Transformer-based models show promise but remain underexplored. Three experiments were conducted. Experiment A assessed the performance of architectures combining Convolutional and Transformer Blocks for binary Motor Imagery (MI) classification. Experiment B introduced a hybrid system, refining both block types and adding a Noise Focus Block to infuse Stochastic Noise, enhancing multi-class classification robustness. Experiment C evaluated the emerging architectures on 106 subjects, focusing on robustness across weak and strong learners. In Experiment A, the best networks achieved a validation accuracy of 0.914 and a loss of 0.146 (p=0.000967, F=12.675). In Experiment B, the proposed architecture improved multi-class MI classification to 84.5% on Dataset II, significantly improving performance for BCI-illiterate users. Experiment C showed a Kappa >83%, reduced standard deviation, and a highest validation accuracy of 88.69% across all individuals. The hybrid integration of Transformers, CNNs, and Noise-Resonance-based layers significantly enhances classification performance, particularly for weak BCI learners. Further research is recommended to optimize hybrid system architectures and hyperparameter settings to overcome current limitations in BCI performance.

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

http://hdl.handle.net/10453/191826