An Investigation of Ear-EEG Signals for a Novel Biometric Authentication System

2025-07-17

AI Summary

To address the low usability of conventional scalp EEG-based biometric authentication caused by cumbersome electrode placement, this work systematically investigates, for the first time, the feasibility of in-ear EEG (ear-EEG) for identity verification. We propose a lightweight time-frequency fusion deep learning framework that jointly extracts time-domain statistical features and short-time Fourier transform (STFT) spectral features, feeding them into an optimized fully connected neural network for subject identification. Designed specifically for wearable applications, the architecture balances computational efficiency with discriminative power. Evaluated on a public ear-EEG dataset, our method achieves an average identification accuracy of 82%, significantly outperforming baseline approaches. This demonstrates the practical potential of ear-EEG as a highly usable and covert biometric modality, establishing a novel paradigm for next-generation seamless (contactless and unobtrusive) biometric authentication.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

This work explores the feasibility of biometric authentication using EEG signals acquired through in-ear devices, commonly referred to as ear-EEG. Traditional EEG-based biometric systems, while secure, often suffer from low usability due to cumbersome scalp-based electrode setups. In this study, we propose a novel and practical framework leveraging ear-EEG signals as a user-friendly alternative for everyday biometric authentication. The system extracts an original combination of temporal and spectral features from ear-EEG signals and feeds them into a fully connected deep neural network for subject identification. Experimental results on the only currently available ear-EEG dataset suitable for different purposes, including biometric authentication, demonstrate promising performance, with an average accuracy of 82% in a subject identification scenario. These findings confirm the potential of ear-EEG as a viable and deployable direction for next-generation real-world biometric systems.

Problem

• Feasibility of ear-EEG for biometric authentication
• Overcoming usability issues in traditional EEG systems
• Developing a practical deep learning-based ear-EEG framework

Innovation

• Uses ear-EEG signals for biometric authentication
• Extracts temporal and spectral features
• Employs deep neural network for identification