EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MsGCN: a multi-stream graph convolutional network for multiband PLV graph fusion in EEG-based biometric identification

Wenli Tian, Jun Yang, Xiangyu Ju, Ming Li, Dewen Hu

Frontiers in Computational Neuroscience · 17.06.2026 · 20

DOI: 10.3389/fncom.2026.1845003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Computational Neuroscience, online erschienen am 17.06.2026. Verfasst von Wenli Tian und 4 weiteren Autor:innen. Beteiligte Einrichtung: Northwest Institute of Nuclear Technology, Xi'an, Shaanxi, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

EEG-based biometric identification has attracted extensive attention due to its high security and uniqueness. Functional connectivity features derived from EEG exhibit strong individual specificity, yet existing methods do not fully leverage the complementary identity information contained in multiband functional connectivity features.

Methods

This study proposes a multi-stream graph convolutional network (MsGCN) for EEG-based biometric identification by fusing graph representations derived from multiband phase-locking value (PLV) matrices. The model processes PLV matrices from multiple frequency bands through parallel GCN branches and performs end-to-end identification using fully connected layers. Experiments on the public PhysioNet Motor Movement/Imagery dataset evaluated the method under non-preprocessed conditions, cross-task settings, channel reduction, and different graph binarization thresholds.

Results

MsGCN achieved 99.50% accuracy on preprocessed data and 98.12% on non-preprocessed data, showing numerically higher accuracy than the selected CNN and GCN baselines under the unified protocol. The model also showed improved robustness in cross-task identification, reduced-channel settings, and across a wide range of thresholds.

Discussion

These results suggest that multiband PLV graph fusion can improve robustness to preprocessing conditions, task variation, channel reduction, and threshold selection under the evaluated dataset and experimental settings.

Schlagwörter

Stichwörter der Autor:innen

EEG biometric identificationMsGCNfeature fusionfunctional connectivitymultiband PLV

Autor:innen und Institutionen

  • Northwest Institute of Nuclear Technology, Xi'an, Shaanxi, China.
  • College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China.

Zitieren

APA

Tian, W., Yang, J., Ju, X., Li, M., & Hu, D. (2026). MsGCN: a multi-stream graph convolutional network for multiband PLV graph fusion in EEG-based biometric identification. Frontiers in Computational Neuroscience, 20. https://doi.org/10.3389/fncom.2026.1845003

Vancouver

Tian W, Yang J, Ju X, Li M, Hu D. MsGCN: a multi-stream graph convolutional network for multiband PLV graph fusion in EEG-based biometric identification. Frontiers in Computational Neuroscience. 2026;20. doi:10.3389/fncom.2026.1845003

BibTeX
@article{Tian2026,
  author = {Tian, Wenli and Yang, Jun and Ju, Xiangyu and Li, Ming and Hu, Dewen},
  title = {MsGCN: a multi-stream graph convolutional network for multiband PLV graph fusion in EEG-based biometric identification},
  journal = {Frontiers in Computational Neuroscience},
  year = {2026},
  volume = {20},
  doi = {10.3389/fncom.2026.1845003}
}
Kostenlos starten →