Version 1
: Received: 29 July 2024 / Approved: 30 July 2024 / Online: 30 July 2024 (04:38:20 CEST)
Version 2
: Received: 13 September 2024 / Approved: 14 September 2024 / Online: 15 September 2024 (07:32:28 CEST)
How to cite:
Wimpff, M.; Zerfowski, J.; Yang, B. Tailoring Deep Learning for Real-Time Brain-Computer Interfaces: From Offline Models to Calibration-Free Online Decoding. Preprints2024, 2024072370. https://doi.org/10.20944/preprints202407.2370.v2
Wimpff, M.; Zerfowski, J.; Yang, B. Tailoring Deep Learning for Real-Time Brain-Computer Interfaces: From Offline Models to Calibration-Free Online Decoding. Preprints 2024, 2024072370. https://doi.org/10.20944/preprints202407.2370.v2
Wimpff, M.; Zerfowski, J.; Yang, B. Tailoring Deep Learning for Real-Time Brain-Computer Interfaces: From Offline Models to Calibration-Free Online Decoding. Preprints2024, 2024072370. https://doi.org/10.20944/preprints202407.2370.v2
APA Style
Wimpff, M., Zerfowski, J., & Yang, B. (2024). Tailoring Deep Learning for Real-Time Brain-Computer Interfaces: From Offline Models to Calibration-Free Online Decoding. Preprints. https://doi.org/10.20944/preprints202407.2370.v2
Chicago/Turabian Style
Wimpff, M., Jan Zerfowski and Bin Yang. 2024 "Tailoring Deep Learning for Real-Time Brain-Computer Interfaces: From Offline Models to Calibration-Free Online Decoding" Preprints. https://doi.org/10.20944/preprints202407.2370.v2
Abstract
The success of deep learning (DL) in offline brain-computer interfaces (BCIs) has not yet translated into efficient online applications. This is due to three primary challenges. First, most DL solutions are designed for offline decoding, making the transition to online decoding complex and unclear. Second, the use of sliding windows in online decoding increases the computational complexity of DL training. Third, DL models typically require large amounts of training data, which are often scarce in BCI applications. To address these issues and enable real-time decoding, even across different subjects without calibration data, we first introduce a novel approach called real-time adaptive pooling (RAP). RAP modifies the pooling layers of existing offline DL models towards the online decoding requirements. Additionally, it significantly reduces the computational demand during training by jointly decoding consecutive windows. To reduce the amount of training data required, our approach leverages different levels of domain adaptation. We show how different settings enable different adaptation solutions. The results demonstrate that our approach is both powerful and can be calibration-free, providing a robust and practical solution for real-time BCI applications. These findings pave the way for the development of co-adaptive and highly efficient DL-based online BCI systems.
Keywords
Motor imagery; Electroencephalography; Deep Learning; Online decoding; Domain adaptation; Calibration-free; Mutual learning
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
