Transfer learning of an ensemble of DNNs for SSVEP BCI spellers without user-specific training
Journal of Neural Engineering · 2023
DOI: 10.1088/1741-2552/acacca ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Neural Engineering, 2023. Verfasst von Osman Berke Guney und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, Boston University, Boston, MA, United States of America. Hauptthemen laut MEDLINE: Brain-Computer Interfaces. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: The Scientific and Technological Research Council of Turkey.
Abstract (Originalsprache)
Objective. Steady-state visually evoked potentials (SSVEPs), measured with electroencephalogram (EEG), yield decent information transfer rates (ITRs) in brain-computer interface (BCI) spellers. However, the current high performing SSVEP BCI spellers in the literature require an initial lengthy and tiring user-specific training for each new user for system adaptation, including data collection with EEG experiments, algorithm training and calibration (all are before the actual use of the system). This impedes the widespread use of BCIs. To ensure practicality, we propose a novel target identification method based on an ensemble of deep neural networks (DNNs), which does not require any sort of user-specific training. Approach. We exploit already-existing literature datasets from participants of previously conducted EEG experiments to train a global target identifier DNN first, which is then fine-tuned to each participant. We transfer this ensemble of fine-tuned DNNs to the new user instance, determine the k most representative DNNs according to the participants’ statistical similarities to the new user, and predict the target character through a weighted combination of the ensemble predictions. Main results. The proposed method significantly outperforms all the state-of-the-art alternatives for all stimulation durations in [0.2–1.0] s on two large-scale benchmark and BETA datasets, and achieves impressive 155.51 bits/min and 114.64 bits/min ITRs. Code is available for reproducibility: https://github.com/osmanberke/Ensemble-of-DNNs . Significance. Our Ensemble-DNN method has the potential to promote the practical widespread deployment of BCI spellers in daily lives as we provide the highest performance while enabling the immediate system use without any user-specific training.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical and Computer Engineering, Boston University, Boston, MA, United States of America.
- Faculty of Engineering and Natural Sciences, Sabanci University, Istanbul, Turkey.
ORCID-Profile: Osman Berke Guney, Huseyin Ozkan
Förderung
- The Scientific and Technological Research Council of Turkey
Zitieren
APA
Berke Guney, O., & Ozkan, H. (2023). Transfer learning of an ensemble of DNNs for SSVEP BCI spellers without user-specific training. Journal of Neural Engineering. https://doi.org/10.1088/1741-2552/acacca
Vancouver
Berke Guney O, Ozkan H. Transfer learning of an ensemble of DNNs for SSVEP BCI spellers without user-specific training. Journal of Neural Engineering. 2023. doi:10.1088/1741-2552/acacca
BibTeX
@article{BerkeGuney2023,
author = {Berke Guney, Osman and Ozkan, Huseyin},
title = {Transfer learning of an ensemble of DNNs for SSVEP BCI spellers without user-specific training},
journal = {Journal of Neural Engineering},
year = {2023},
doi = {10.1088/1741-2552/acacca}
}
EUVIMED