Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

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

Wenli Tian¹, Jun Yang², Xiangyu Ju²

¹Northwest Institute of Nuclear Technology, Xi'an, Shaanxi, China.

Frontiers in Computational Neuroscience

|July 2, 2026

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Reinforcement learning in linear embedding space unlocks generalizable control across soft robot configurations.

Nature communications·2026

Same author

Dual controllability de-differentiation of functional brain networks in major depressive disorder: Insights from large-scale neuroimaging and transcriptomic integration.

Journal of affective disorders·2026

Same author

Functional connectivity-based classification and subtyping of major depression for precision mental health: An ensemble graph neural network approach.

PLOS digital health·2026

Same author

Multi-Site Transfer Classification of Major Depressive Disorder: An fMRI Study in 3335 Subjects.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

Transfer learning from 2D natural images to 4D fMRI brain images via geometric mapping.

Medical image analysis·2026

Same author

Classifying Major Depressive Disorder Using Multimodal MRI Data: A Personalized Federated Algorithm.

Brain sciences·2025

This study introduces a multi-stream graph convolutional network (MsGCN) for enhanced EEG-based biometric identification. The novel approach effectively fuses multiband functional connectivity, significantly improving accuracy and robustness.

Area of Science:

Neuroscience
Biometrics
Machine Learning

Background:

Electroencephalography (EEG)-based biometrics offer high security and uniqueness.
Existing methods often fail to utilize the full potential of multiband functional connectivity for identification.

Purpose of the Study:

To propose a novel multi-stream graph convolutional network (MsGCN) for EEG-based biometric identification.
To leverage complementary identity information from multiband functional connectivity features.

Main Methods:

Developed a multi-stream graph convolutional network (MsGCN) fusing graph representations from multiband phase-locking value (PLV) matrices.
Processed multi-band PLV matrices through parallel GCN branches for end-to-end identification.
Evaluated performance on the PhysioNet Motor Movement/Imagery dataset under various conditions (non-preprocessed, cross-task, channel reduction).

Keywords:

EEG biometric identification MsGCN feature fusion functional connectivity multiband PLV

Related Experiment Videos

Main Results:

Achieved 99.50% accuracy on preprocessed data and 98.12% on non-preprocessed data.
Demonstrated superior accuracy compared to baseline CNN and GCN methods.
Showcased improved robustness in cross-task identification, reduced-channel settings, and across different graph binarization thresholds.

Conclusions:

Multiband PLV graph fusion enhances EEG biometric identification robustness.
The proposed MsGCN effectively integrates information across multiple frequency bands.
The method shows significant potential for real-world biometric applications.