Heartbeats in the Wild: A Field Study Exploring ECG Biometrics in Everyday Life

Abstract

This paper reports on an in-depth study of electrocardiogram (ECG) biometrics in everyday life. We collected ECG data from 20 people over a week, using a non-medical chest tracker. We evaluated user identification accuracy in several scenarios and observed equal error rates of 9.15% to 21.91%, heavily depending on 1) the number of days used for training, and 2) the number of heartbeats used per identification decision. We conclude that ECG biometrics can work in the wild but are less robust than expected based on the literature, highlighting that previous lab studies obtained highly optimistic results with regard to real life deployments. We explain this with noise due to changing body postures and states as well as interrupted measures. We conclude with implications for future research and the design of ECG biometrics systems for real world deployments, including critical reflections on privacy.

Broken Heart: Privacy Leakage Analysis on ECG-Based Authentication Schemes

“…eir research shows that malicious users can capture and store users' ECG templates and reconstruct the ECG signals. [16] recruited 20 participants to measure ECG biometrics and identify user authentication based on the collected ECG data. In that paper, they mentioned individual privacy but did not prove that personal privacy could actually be leaked.…”

“…Lehmann and Buschek [16] proposed an ECG-based authentication scheme that can be used with a continuous electrocardiogram device. In their paper, they mentioned that certain private information, such as one's health status and lifestyle, can be inferred from the ECG features.…”

Activity‐based electrocardiogram biometric verification using wearable devices

“…They used normalised QRS complex features with a MLP classifier and they achieved 96.1% classification accuracy. Kim et al [20] and Lehmann et al [21] recognised that ECG recordings which were collected on different days vary because of different activity and emotional conditions. In ref.…”

“…[20] and Lehmann et al. [21] recognised that ECG recordings which were collected on different days vary because of different activity and emotional conditions. In ref.…”

“…In Ref. [21], they used a chest band for ECG recordings with 256 Hz from 20 subjects during a week. They used peak‐to‐peak intervals of QR, RS, and QS as features with RF, neural network (NN) and SVM classifiers.…”