Enhancing biometric identification using 12-lead ECG signals and graph convolutional networks
IntroductionThe electrocardiogram (ECG) is a highly secure biometric modality due to its intrinsic physiological characteristics, making it resilient to forgery and external attacks. This study presents a novel real-time biometric authentication system integrating Graph Convolutional Networks (GCN)...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-04-01
|
| Series: | Frontiers in Digital Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fdgth.2025.1547208/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850151249306976256 |
|---|---|
| author | Maram Al Alfi Pedro Peris-Lopez Carmen Camara |
| author_facet | Maram Al Alfi Pedro Peris-Lopez Carmen Camara |
| author_sort | Maram Al Alfi |
| collection | DOAJ |
| description | IntroductionThe electrocardiogram (ECG) is a highly secure biometric modality due to its intrinsic physiological characteristics, making it resilient to forgery and external attacks. This study presents a novel real-time biometric authentication system integrating Graph Convolutional Networks (GCN) with Mutual Information (MI) indices extracted from 12-lead ECG signals.MethodsThe MI index quantifies the statistical dependencies among ECG leads and is computed using entropy-based estimations. This index is used to construct a graph representation, where nodes correspond to ECG features and edges reflect their relationships based on MI values. The GCN model is trained on this graph, enabling it to learn complex patterns for user identification efficiently.ResultsExperimental results demonstrate that the proposed GCN-MI model achieves 100% accuracy with a 5-layer architecture at a k-fold of 75, outperforming conventional approaches that require less training data.DiscussionThis work introduces several innovations: the integration of MI indices enhances feature selection, improving model robustness and efficiency; the graph-based learning framework effectively captures both spatial and statistical relationships within ECG data, leading to higher classification accuracy; the proposed approach offers a scalable and real-time biometric authentication system suitable for applications in finance, healthcare, and personal device access. These findings highlight the practical value of the GCN-MI approach, setting a new benchmark in ECG-based biometric identification. |
| format | Article |
| id | doaj-art-c20019e3fcc745cd8aff466a67c54568 |
| institution | OA Journals |
| issn | 2673-253X |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Digital Health |
| spelling | doaj-art-c20019e3fcc745cd8aff466a67c545682025-08-20T02:26:19ZengFrontiers Media S.A.Frontiers in Digital Health2673-253X2025-04-01710.3389/fdgth.2025.15472081547208Enhancing biometric identification using 12-lead ECG signals and graph convolutional networksMaram Al AlfiPedro Peris-LopezCarmen CamaraIntroductionThe electrocardiogram (ECG) is a highly secure biometric modality due to its intrinsic physiological characteristics, making it resilient to forgery and external attacks. This study presents a novel real-time biometric authentication system integrating Graph Convolutional Networks (GCN) with Mutual Information (MI) indices extracted from 12-lead ECG signals.MethodsThe MI index quantifies the statistical dependencies among ECG leads and is computed using entropy-based estimations. This index is used to construct a graph representation, where nodes correspond to ECG features and edges reflect their relationships based on MI values. The GCN model is trained on this graph, enabling it to learn complex patterns for user identification efficiently.ResultsExperimental results demonstrate that the proposed GCN-MI model achieves 100% accuracy with a 5-layer architecture at a k-fold of 75, outperforming conventional approaches that require less training data.DiscussionThis work introduces several innovations: the integration of MI indices enhances feature selection, improving model robustness and efficiency; the graph-based learning framework effectively captures both spatial and statistical relationships within ECG data, leading to higher classification accuracy; the proposed approach offers a scalable and real-time biometric authentication system suitable for applications in finance, healthcare, and personal device access. These findings highlight the practical value of the GCN-MI approach, setting a new benchmark in ECG-based biometric identification.https://www.frontiersin.org/articles/10.3389/fdgth.2025.1547208/fullgraph convolutional networks (GCN)electrocardiogram (ECG)mutual information (MI)Identification12 ECG leads |
| spellingShingle | Maram Al Alfi Pedro Peris-Lopez Carmen Camara Enhancing biometric identification using 12-lead ECG signals and graph convolutional networks Frontiers in Digital Health graph convolutional networks (GCN) electrocardiogram (ECG) mutual information (MI) Identification 12 ECG leads |
| title | Enhancing biometric identification using 12-lead ECG signals and graph convolutional networks |
| title_full | Enhancing biometric identification using 12-lead ECG signals and graph convolutional networks |
| title_fullStr | Enhancing biometric identification using 12-lead ECG signals and graph convolutional networks |
| title_full_unstemmed | Enhancing biometric identification using 12-lead ECG signals and graph convolutional networks |
| title_short | Enhancing biometric identification using 12-lead ECG signals and graph convolutional networks |
| title_sort | enhancing biometric identification using 12 lead ecg signals and graph convolutional networks |
| topic | graph convolutional networks (GCN) electrocardiogram (ECG) mutual information (MI) Identification 12 ECG leads |
| url | https://www.frontiersin.org/articles/10.3389/fdgth.2025.1547208/full |
| work_keys_str_mv | AT maramalalfi enhancingbiometricidentificationusing12leadecgsignalsandgraphconvolutionalnetworks AT pedroperislopez enhancingbiometricidentificationusing12leadecgsignalsandgraphconvolutionalnetworks AT carmencamara enhancingbiometricidentificationusing12leadecgsignalsandgraphconvolutionalnetworks |