CardioID: Mitigating the Effects of Irregular Cardiac Signals for Biometric Identification

TL;DR

This paper introduces a novel adaptive framework for biometric identification using cardiac signals that maintains high accuracy in uncontrolled, real-world scenarios by addressing signal variability and user diversity.

Contribution

The work presents a new adaptive filtering method, leverages multiple cardiac morphologies, and employs a multi-cluster Mahalanobis distance approach to improve identification accuracy in uncontrolled environments.

Findings

State-of-the-art accuracy drops from 90%+ to 75% in uncontrolled scenarios.

Proposed method maintains above 90% accuracy in uncontrolled scenarios.

Addresses variability and distortion effects in cardiac biometric signals.

Abstract

Cardiac patterns are being used to obtain hard-to-forge biometric signatures and have led to high accuracy in state-of-the-art (SoA) identification applications. However, this performance is obtained under controlled scenarios where cardiac signals maintain a relatively uniform pattern, facilitating the identification process. In this work, we analyze cardiac signals collected in more realistic (uncontrolled) scenarios and show that their high signal variability (i.e., irregularity) makes it harder to obtain stable and distinct user features. Furthermore, SoA usually fails to identify specific groups of users, rendering existing identification methods futile in uncontrolled scenarios. To solve these problems, we propose a framework with three novel properties. First, we design an adaptive method that achieves stable and distinct features by tailoring the filtering spectrum to each user. Second, we show that users can have multiple cardiac morphologies, offering us a much bigger pool of cardiac signals and users compared to SoA. Third, we overcome other distortion effects present in authentication applications with a multi-cluster approach and the Mahalanobis distance. Our evaluation shows that the average balanced accuracy (BAC) of SoA drops from above 90% in controlled scenarios to 75% in uncontrolled ones, while our method maintains an average BAC above 90% in uncontrolled scenarios.