ECG Biometrics with ArcFace-Inception: External Validation on MIMIC and HEEDB

1. 1Train a 1D Inception-v1 model with ArcFace on a large internal clinical corpus of ECGs
2. 2Evaluate the model on external datasets such as MIMIC-IV-ECG and HEEDB to assess its performance on large cohorts and domain shift
3. 3Analyze the results to determine the model's accuracy and robustness in identifying individuals from ECG signals
4. 4Refine the model and experiment with different architectures and techniques to further improve its performance

Data scientists and AI engineers working on biometric identification and healthcare applications can benefit from this research, as it provides a robust method for ECG-based identification

💡 The use of ArcFace-Inception on ECG signals can provide a robust and accurate method for biometric identification, even with external domain shift and multi-year temporal gaps

🚀 ECG biometrics with ArcFace-Inception achieves high accuracy on large cohorts! 📈