Evaluation of electrocardiogram biometric verification models based on short enrollment time on medical and wearable recorders
Evaluation of electrocardiogram biometric verification models based on short enrollment time on medical and wearable recorders
Biometric authentication is nowadays widely used in a multitude of scenarios. Several studies have been conducted on electrocardiogram (ECG) for subject identification or verification among the various modalities. However, none have considered a typical implementation with a mobile device and the necessity for a fast-training model with limited recording time for the signal. This study tackles this issue by exploring various classification models on short recordings and evaluating the performance varying the sample length and the training set size. We run our tests on two public datasets collected from wearable and medical devices and propose a pipeline for ECG authentication with limited data required for competitive usage across applications.
Biometric Authentication, ECG Biometrics, Performance Assessment, Wearable devices
Su Bıçakcı, Hazal
d834ab27-440f-4cff-ad6f-1bd84117653e
Santopietro, Marco
fcfe5a84-a740-4a15-898c-a170b48a8264
Boakes, Matthew
25dc2eee-df65-439f-b979-20c3fb416575
Guest, Richard
93533dbd-b101-491b-83cc-39ccfdc18165
Su Bıçakcı, Hazal
d834ab27-440f-4cff-ad6f-1bd84117653e
Santopietro, Marco
fcfe5a84-a740-4a15-898c-a170b48a8264
Boakes, Matthew
25dc2eee-df65-439f-b979-20c3fb416575
Guest, Richard
93533dbd-b101-491b-83cc-39ccfdc18165
Su Bıçakcı, Hazal, Santopietro, Marco, Boakes, Matthew and Guest, Richard
(2022)
Evaluation of electrocardiogram biometric verification models based on short enrollment time on medical and wearable recorders.
In 2021 International Carnahan Conference on Security Technology (ICCST).
IEEE.
6 pp
.
(doi:10.1109/ICCST49569.2021.9717372).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Biometric authentication is nowadays widely used in a multitude of scenarios. Several studies have been conducted on electrocardiogram (ECG) for subject identification or verification among the various modalities. However, none have considered a typical implementation with a mobile device and the necessity for a fast-training model with limited recording time for the signal. This study tackles this issue by exploring various classification models on short recordings and evaluating the performance varying the sample length and the training set size. We run our tests on two public datasets collected from wearable and medical devices and propose a pipeline for ECG authentication with limited data required for competitive usage across applications.
This record has no associated files available for download.
More information
e-pub ahead of print date: 25 February 2022
Venue - Dates:
2021 International Carnahan Conference on Security Technology, Virtual, 2021-10-11 - 2021-10-15
Keywords:
Biometric Authentication, ECG Biometrics, Performance Assessment, Wearable devices
Identifiers
Local EPrints ID: 489558
URI: http://eprints.soton.ac.uk/id/eprint/489558
PURE UUID: 1e7a9a08-8d1e-43a9-a66e-9d739f33ceca
Catalogue record
Date deposited: 26 Apr 2024 17:13
Last modified: 28 Apr 2024 02:05
Export record
Altmetrics
Contributors
Author:
Hazal Su Bıçakcı
Author:
Marco Santopietro
Author:
Matthew Boakes
Author:
Richard Guest
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics