Evaluation of PPG Biometrics for Authentication in different states

TL;DR

This paper evaluates the robustness of PPG biometrics for authentication across various states, demonstrating high accuracy with a novel non-fiducial method using CWT and DLDA, suitable for real-world wearable applications.

Contribution

It introduces a comprehensive evaluation of PPG biometrics under different conditions and proposes a robust non-fiducial authentication method outperforming previous techniques.

Findings

Achieved EER of 0.5%-6% across different states and datasets.

Demonstrated robustness of PPG biometrics against stress, exercise, and time lapse.

Outperformed existing dimensionality reduction and biometric authentication methods.

Abstract

Amongst all medical biometric traits, Photoplethysmograph (PPG) is the easiest to acquire. PPG records the blood volume change with just combination of Light Emitting Diode and Photodiode from any part of the body. With IoT and smart homes' penetration, PPG recording can easily be integrated with other vital wearable devices. PPG represents peculiarity of hemodynamics and cardiovascular system for each individual. This paper presents non-fiducial method for PPG based biometric authentication. Being a physiological signal, PPG signal alters with physical/mental stress and time. For robustness, these variations cannot be ignored. While, most of the previous works focused only on single session, this paper demonstrates extensive performance evaluation of PPG biometrics against single session data, different emotions, physical exercise and time-lapse using Continuous Wavelet Transform (CWT) and Direct Linear Discriminant Analysis (DLDA). When evaluated on different states and datasets, equal error rate (EER) of $0.5\%$-$6\%$ was achieved for $45$-$60$s average training time. Our CWT/DLDA based technique outperformed all other dimensionality reduction techniques and previous work.