Deep Contrastive Learning-Based Model for ECG Biometrics


Ammour N., Jomaa R. M., Islam M. S., Bazi Y., Alhichri H., Alajlan N.

Applied Sciences (Switzerland), vol.13, no.5, 2023 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 13 Issue: 5
  • Publication Date: 2023
  • Doi Number: 10.3390/app13053070
  • Journal Name: Applied Sciences (Switzerland)
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Agricultural & Environmental Science Database, Applied Science & Technology Source, Communication Abstracts, INSPEC, Metadex, Directory of Open Access Journals, Civil Engineering Abstracts
  • Keywords: ECG biometric, biometric identification, contrastive learning, deep learning
  • TED University Affiliated: Yes

Abstract

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.