A Review of ECG Biometrics: Generalization in Deep Learning with Attention Mechanisms

A Review of ECG Biometrics: Generalization in Deep Learning with Attention Mechanisms

Common biometric systems like fingerprint and face recognition are more convenient in daily applications, but biological and behavioral characteristics of the biometrics features can be fabricated and digitally stolen. Thus, biometrics features with liveness detection such as the electrocardiogram (...

Full description

Bibliographic Details
Published in:Lecture Notes in Electrical Engineering
Main Author: Saod A.H.M.; Ramli D.A.
Format: Conference paper
Language:English
Published: Springer Science and Business Media Deutschland GmbH 2024
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85190385476&doi=10.1007%2f978-981-99-9005-4_57&partnerID=40&md5=8707407e04af68edbb028ce329e321e3
id 2-s2.0-85190385476
spelling 2-s2.0-85190385476
Saod A.H.M.; Ramli D.A.
A Review of ECG Biometrics: Generalization in Deep Learning with Attention Mechanisms
2024
Lecture Notes in Electrical Engineering
1123 LNEE

10.1007/978-981-99-9005-4_57
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85190385476&doi=10.1007%2f978-981-99-9005-4_57&partnerID=40&md5=8707407e04af68edbb028ce329e321e3
Common biometric systems like fingerprint and face recognition are more convenient in daily applications, but biological and behavioral characteristics of the biometrics features can be fabricated and digitally stolen. Thus, biometrics features with liveness detection such as the electrocardiogram (ECG) have been introduced as its features are hidden and difficult to forge. This study presents a review of ECG biometrics based on deep learning and generalization issues in deep learning. Based on the review, deep learning methods such as recurrent neural networks (RNN) and long short-term memory networks (LSTM) with attention mechanisms can be employed to improve the performance and generalization ability of ECG biometrics systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
Springer Science and Business Media Deutschland GmbH
18761100
English
Conference paper
author Saod A.H.M.; Ramli D.A.
spellingShingle Saod A.H.M.; Ramli D.A.
A Review of ECG Biometrics: Generalization in Deep Learning with Attention Mechanisms
author_facet Saod A.H.M.; Ramli D.A.
author_sort Saod A.H.M.; Ramli D.A.
title A Review of ECG Biometrics: Generalization in Deep Learning with Attention Mechanisms
title_short A Review of ECG Biometrics: Generalization in Deep Learning with Attention Mechanisms
title_full A Review of ECG Biometrics: Generalization in Deep Learning with Attention Mechanisms
title_fullStr A Review of ECG Biometrics: Generalization in Deep Learning with Attention Mechanisms
title_full_unstemmed A Review of ECG Biometrics: Generalization in Deep Learning with Attention Mechanisms
title_sort A Review of ECG Biometrics: Generalization in Deep Learning with Attention Mechanisms
publishDate 2024
container_title Lecture Notes in Electrical Engineering
container_volume 1123 LNEE
container_issue
doi_str_mv 10.1007/978-981-99-9005-4_57
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85190385476&doi=10.1007%2f978-981-99-9005-4_57&partnerID=40&md5=8707407e04af68edbb028ce329e321e3
description Common biometric systems like fingerprint and face recognition are more convenient in daily applications, but biological and behavioral characteristics of the biometrics features can be fabricated and digitally stolen. Thus, biometrics features with liveness detection such as the electrocardiogram (ECG) have been introduced as its features are hidden and difficult to forge. This study presents a review of ECG biometrics based on deep learning and generalization issues in deep learning. Based on the review, deep learning methods such as recurrent neural networks (RNN) and long short-term memory networks (LSTM) with attention mechanisms can be employed to improve the performance and generalization ability of ECG biometrics systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
publisher Springer Science and Business Media Deutschland GmbH
issn 18761100
language English
format Conference paper
accesstype
record_format scopus
collection Scopus
_version_ 1809677775272935424

Similar Items