Key result
A proposed pipeline for ECG biometric authentication using short recordings from wearable and medical devices enables competitive performance with limited training data.
Why the study?
Previous ECG biometric authentication studies have not considered mobile device implementations requiring fast-training models with limited signal recording time.
Demonstrates the feasibility of a fast-training ECG biometric authentication pipeline using short recordings from mobile and wearable devices.
May enable ECG biometrics in wearable cardiac devices; leaves open prospective validation for clinical use.
Biometric authentication is nowadays widely used in a multitude of scenarios. Several studies have been conducted on electrocardiogram (ECG) for subject identification or verification among the various modalities. However, none have considered a typical implementation with a mobile device and the necessity for a fast-training model with limited recording time for the signal. This study tackles this issue by exploring various classification models on short recordings and evaluating the performance varying the sample length and the training set size. We run our tests on two public datasets collected from wearable and medical devices and propose a pipeline for ECG authentication with limited data required for competitive usage across applications.
No takes yet. Share an insight, caveat, or question.
Yeşilkaya et al. (2021) studied ECG biometric authentication. Classification models for ECG authentication on short recordings was evaluated on Model performance varying sample length and training set size. A proposed pipeline for ECG biometric authentication using short recordings from wearable and medical devices enables competitive performance with limited training data.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: