EDITH :ECG biometrics aided by Deep learning for reliable Individual auTHentication

TL;DR

EDITH is a deep learning framework utilizing Siamese architectures for ECG-based biometric authentication, achieving high accuracy with minimal data and demonstrating potential for practical deployment.

Contribution

This work introduces EDITH, a novel deep learning-based ECG biometric authentication system using Siamese networks, outperforming prior methods with fewer beats and lower error rates.

Findings

Achieves 96-99.75% accuracy with a single heartbeat.

Reaches 100% accuracy using 3 to 6 beats.

Reduces Equal Error Rate to 1.29% with Siamese architecture.

Abstract

In recent years, physiological signal based authentication has shown great promises,for its inherent robustness against forgery. Electrocardiogram (ECG) signal, being the most widely studied biosignal, has also received the highest level of attention in this regard. It has been proven with numerous studies that by analyzing ECG signals from different persons, it is possible to identify them, with acceptable accuracy. In this work, we present, EDITH, a deep learning-based framework for ECG biometrics authentication system. Moreover, we hypothesize and demonstrate that Siamese architectures can be used over typical distance metrics for improved performance. We have evaluated EDITH using 4 commonly used datasets and outperformed the prior works using less number of beats. EDITH performs competitively using just a single heartbeat (96-99.75% accuracy) and can be further enhanced by fusing multiple beats (100% accuracy from 3 to 6 beats). Furthermore, the proposed Siamese architecture manages to reduce the identity verification Equal Error Rate (EER) to 1.29%. A limited case study of EDITH with real-world experimental data also suggests its potential as a practical authentication system.