Innovative Deep Graph Learning of Brain Dynamics for Smart Brain--Computer Interface
IEEE Transactions on Consumer Electronics · 2026-11 · 72 (4) · 10191-10202
DOI: 10.1109/tce.2026.3701869 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2026-11. Verfasst von Jiadao Zou und 1 weiteren Autor:innen. Die Arbeit nennt 69 Literaturangaben. Gefördert von: NSF CAREER Award, NSF.
Abstract (Originalsprache)
Brain dynamics encode critical patterns related to cognitive, metabolic, and hemodynamic processes, among others. With the advancement of signal perception techniques, brain dynamics decoding has been attracting increasing interest, towards promising human-computer-interfaces practices. In this study, we have proposed a novel graph neural network (GNN) framework, for innovatively mining hidden patterns in noisy brain dynamics. We take a special interest in the challenging cognitive load detection task with functional Near-Infrared Spectroscopy (fNIRS). In our innovative multi-stage GNN framework, the first stage leverages the graph learning for spatial pattern abstraction, and the second stage facilitates further pattern fusion and performs final cognitive load detection. To boost the performance, we have uniquely leveraged multi-view learning in the framework, through integrating the engineered features into the model. Various representation approaches, such as the temporal, spectral, time-frequency, and statistical domains, have been thoroughly investigated in the proposed multi-view learning framework. The evaluation experiments have been conducted on the 26-subject 4-cognitive-level detection task. The accuracy achieved is up to 79.49%, which is much superior to state-of-the-art. Our study has laid a solid foundation for the next-generation consumer brain-computer-interface electronics, through innovative deep graph learning of brain dynamics for smart brain-computer-interface.
Förderung
- NSF CAREER Award
- NSF
Zitieren
APA
Zou, J., & Zhang, Q. (2026). Innovative Deep Graph Learning of Brain Dynamics for Smart Brain--Computer Interface. IEEE Transactions on Consumer Electronics, 72(4), 10191-10202. https://doi.org/10.1109/tce.2026.3701869
Vancouver
Zou J, Zhang Q. Innovative Deep Graph Learning of Brain Dynamics for Smart Brain--Computer Interface. IEEE Transactions on Consumer Electronics. 2026;72(4):10191-10202. doi:10.1109/tce.2026.3701869
BibTeX
@article{Zou2026,
author = {Zou, Jiadao and Zhang, Qingxue},
title = {Innovative Deep Graph Learning of Brain Dynamics for Smart Brain--Computer Interface},
journal = {IEEE Transactions on Consumer Electronics},
year = {2026},
volume = {72},
number = {4},
pages = {10191--10202},
doi = {10.1109/tce.2026.3701869}
}
EUVIMED