Key result
A deep contrastive learning-based system for ECG biometric identification achieved an average top-1 accuracy of 98.02% on a multi-session dataset of 199 subjects.
Why the study?
ECG signals are promising for biometric security due to robustness against presentation attacks, prompting the development of an ECG biometric identification system.
Does a deep contrastive learning-based system provide high accuracy for ECG biometric identification?
Does a deep contrastive learning-based system provide high accuracy for ECG biometric identification?
A deep contrastive learning-based system achieves high accuracy (98.02%) for ECG biometric identification across multiple sessions.
Answers are grounded in this paper and cite their sources.
Promising for ECG biometrics; leaves open large-scale clinical validation before deployment.
The electrocardiogram (ECG) signal is shown to be promising as a biometric. To this end, it has been demonstrated that the analysis of ECG signals can be considered as a good solution for increasing the biometric security levels. This can be mainly due to its inherent robustness against presentation attacks. In this work, we present a deep contrastive learning-based system for ECG biometric identification. The proposed system consists of three blocks: a feature extraction backbone based on short time Fourier transform (STFT), a contrastive learning network, and a classification network. We evaluated the proposed system on the Heartprint dataset, a new ECG biometrics multi-session dataset. The experimental analysis shows promising capabilities of the proposed method. In particular, it yields an average top1 accuracy of 98.02% on a new dataset built by gathering 1539 ECG records from 199 subjects collected in multiple sessions with an average interval between sessions of 47 days.
No takes yet. Share an insight, caveat, or question.
Ammour et al. (2023) studied ECG biometrics (n=199). Deep contrastive learning-based system was evaluated on Top-1 accuracy for ECG biometric identification. A deep contrastive learning-based system for ECG biometric identification achieved an average top-1 accuracy of 98.02% on a multi-session dataset of 199 subjects.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: