The adoption of biomedical signals such as photoplethysmogram (PPG) and electrocardiogram (ECG) for health parameter estimation on wearable devices is growing in tandem with the increase of attention in mobile healthcare. In our work, we use PPG signals extracted from PPG sensors which are used for biometric identification. A challenge for biometric identification using PPG signal is the variation in domain (placement of sensors, wavelengths, device variation, etc.). In this work, we propose the use of both unsupervised and semi-supervised adversarial learning techniques for cross-domain adaptation. As such algorithm will be deployed on wearable devices, we propose a compact model meeting tight memory footprint limitation. All experiments will be simulated using a public dataset (TROIKA) and our in-house dataset. By introducing a cross-domain adaptation approach across sensors, we observe an accuracy gain of 4.15% on our in-house dataset. The proposed semi-supervised learning technique gives an additional accuracy boost of 2.02%.
Paper
Full text
Cross-Domain Adaptation for Biometric Identification Using Photoplethysmogram
Semantic Scholar · Medicine · 2020
Abstract
The adoption of biomedical signals such as photoplethysmogram (PPG) and electrocardiogram (ECG) for health parameter estimation on wearable devices is growing in tandem with the increase of attention in mobile healthcare. In our work, we use PPG signals extracted from PPG sensors which are used for biometric identification. A challenge for biometric identification using PPG signal is the variation in domain (placement of sensors, wavelengths, device variation, etc.). In this work, we propose the use of both unsupervised and semi-supervised adversarial learning techniques for cross-domain adaptation. As such algorithm will be deployed on wearable devices, we propose a compact model meeting tight memory footprint limitation. All experiments will be simulated using a public dataset (TROIKA) and our in-house dataset. By introducing a cross-domain adaptation approach across sensors, we observe an accuracy gain of 4.15% on our in-house dataset. The proposed semi-supervised learning technique gives an additional accuracy boost of 2.02%.