• Transformer-based hybrid syste...

Treffer: Transformer-based hybrid systems to combat BCI illiteracy.

Title:
Transformer-based hybrid systems to combat BCI illiteracy.
Authors:
Pfeffer MA; Faculty of Engineering and Information Technology, University of Technology Sydney, New South Wales, Australia. Electronic address: maximilianAchim.pfeffer@student.uts.edu.au., Wong JKW; Faculty of Design, Architecture and Building, University of Technology Sydney, New South Wales, Australia. Electronic address: Johnny.Wong@uts.edu.au., Ling SH; Faculty of Engineering and Information Technology, University of Technology Sydney, New South Wales, Australia. Electronic address: steve.ling@uts.edu.au.
Source:
Computers in biology and medicine [Comput Biol Med] 2026 Jan 01; Vol. 200, pp. 111378. Date of Electronic Publication: 2025 Dec 12.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Elsevier Country of Publication: United States NLM ID: 1250250 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1879-0534 (Electronic) Linking ISSN: 00104825 NLM ISO Abbreviation: Comput Biol Med Subsets: MEDLINE
Imprint Name(s):
Publication: New York : Elsevier
Original Publication: New York, Pergamon Press.
MeSH Terms:
Brain-Computer Interfaces* , Signal Processing, Computer-Assisted*, Humans ; Male ; Female ; Adult
Contributed Indexing:
Keywords: Artificial intelligence; BCI illiteracy; Biomedical engineering; Brain–computer-interface; Convolutional neural networks; Electroencephalography; Hybrid-models; Neural networks; Signal processing; Transformers
Entry Date(s):
Date Created: 20251213 Date Completed: 20251221 Latest Revision: 20251221
Update Code:
20251222
DOI:
10.1016/j.compbiomed.2025.111378
PMID:
41389568
Database:
MEDLINE

Weitere Informationen

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.
(Copyright © 2025. Published by Elsevier Ltd.)

Declaration of competing interest The authors declare that there are no conflicts of interest.