EEG-BBNet: a Hybrid Framework for Brain Biometric using Graph Connectivity

TL;DR

EEG-BBNet is a hybrid deep learning framework combining CNN and GCNN to improve brain biometric identification using EEG connectivity measures, achieving high accuracy and adaptability across sessions and tasks.

Contribution

The paper introduces EEG-BBNet, a novel hybrid CNN-GCNN model that leverages EEG connectivity for enhanced biometric identification, outperforming existing methods.

Findings

Achieves up to 99.26% accuracy on ERP tasks.

Pearson's correlation and RHO index yield best results.

Effective with fewer electrodes, especially over the frontal lobe.

Abstract

Brain biometrics based on electroencephalography (EEG) have been used increasingly for personal identification. Traditional machine learning techniques as well as modern day deep learning methods have been applied with promising results. In this paper we present EEG-BBNet, a hybrid network which integrates convolutional neural networks (CNN) with graph convolutional neural networks (GCNN). The benefit of the CNN in automatic feature extraction and the capability of GCNN in learning connectivity between EEG electrodes through graph representation are jointly exploited. We examine various connectivity measures, namely the Euclidean distance, Pearson's correlation coefficient, phase-locked value, phase-lag index, and Rho index. The performance of the proposed method is assessed on a benchmark dataset consisting of various brain-computer interface (BCI) tasks and compared to other state-of-the-art approaches. We found that our models outperform all baselines in the event-related potential (ERP) task with an average correct recognition rates up to 99.26% using intra-session data. EEG-BBNet with Pearson's correlation and RHO index provide the best classification results. In addition, our model demonstrates greater adaptability using inter-session and inter-task data. We also investigate the practicality of our proposed model with smaller number of electrodes. Electrode placements over the frontal lobe region appears to be most appropriate with minimal lost in performance.