ECG Signals for Biometric Applications - Are we there yet?

Abstract

Abstract:The potential of the electrocardiographic (ECG) signal as a biometric trait has been ascertained in the literature over the past decade. The inherent characteristics of the ECG make it an interesting biometric modality, given its universality, intrinsic aliveness detection, continuous availability, and inbuilt hidden nature. These properties enable the development of novel applications, where non-intrusive and continuous authentication are critical factors. Examples include, among others, electronic trading platforms, the gaming industry, and the auto industry, in particular for car sharing programs and fleet management solutions. However, there are still some challenges to overcome in order to make the ECG a widely accepted biometric. In particular, the questions of uniqueness (inter-subject variability) and permanence over time (intra-subject variability) are still largely unanswered. In this paper we focus on the uniqueness question, presenting a preliminary study of our biometric recognition system, testing it on a database encompassing 618 subjects. We also performed tests with subsets of this population. The results reinforce that the ECG is a viable trait for biometrics, having obtained an Equal Error Rate of 9.01% and an Error of Identification of 15.64% for the entire test population.

Multi-factor Authentication for Improved Efficiency in ECG: Based Login

“…In order to better understand the delay associated with identifying vs authenticating a person we ran a (necessarily) limited number of tests to confirm the conclusions of previous studies published in (Carreiras et al, 2014). This study shows an increase in identification delay and decrease in accuracy when the number of subjects in database increases.…”

“…Both tests were performed with a group of five persons (an arbitrary small number, to simplify the tests). The smaller database was generated by measuring and registering the volunteers ECG; the bigger database was provided by the authors' of (Carreiras et al, 2014) complemented by the five testing individuals of the smaller data-base.…”

“…This paper addresses a problem reported in the literature concerning electrocardiogram (ECG) authentication. The problem is that it presents a significant time delay associated with identification performance when using larger databases (Carreiras et al, 2014). We suggest using a smartphone, as security token, to improve the performance of the process.…”

Efficiently Updating ECG-Based Biometric Authentication Based on Incremental Learning

“…In contrast, electrocardiogram (ECG) signals, which exhibit unique physiological characteristics across subjects related to the placement and size of the heart, are difficult to spoof because the underlying biometric features are concealed during authentication and can only be obtained from physical measurements on the subject [ 12 , 13 , 14 ]. Since Biel et al [ 15 ] first studied using ECG signal processing for the biometric recognition, ECG-based biometric authentication has received great attention as a next-generation promising technique and been implemented with various approaches to improve the authentication performance for the past few decades [ 16 , 17 , 18 ]. However, ECG signals of a person may vary according to his/her physical state or health condition, possibly leading to authentication failure in some cases [ 19 , 20 , 21 ].…”

Statistical Assessment of Biometrical Signs by Electrocardiography

“…В начале 2000-х годов было установлено, что в электрокардиограммах (ЭКГ) содержатся инвариантные признаки, не зависящие от физического и психоэмоционального состояния человека, позволяющие осуществлять биометрическую идентификацию личности [1,2]. Считается, что ЭКГ практически невозможно подделать [1].…”