A novel deep learning framework (BiometricNET) using wrist-worn PPG signals achieved an average five-fold cross-validation accuracy of 96% for biometric identification during physical activity.
A novel deep learning framework using wrist-worn PPG signals demonstrated high accuracy for biometric identification during physical activity.
Rapid advances in semiconductor fabrication technology have enabled the proliferation of miniaturized body-worn sensors capable of long term pervasive biomedical signal monitoring. In this paper, we present a novel deep learning-based framework (BiometricNET) on biometric identification using data collected from wrist-worn Photoplethysmography (PPG) signals in ambulatory environments. We have formulated a completely personalized data-driven approach, using a four-layer deep neural network - employing two convolution neural network (CNN) layers in conjunction with two long short-term memory (LSTM) layers, followed by a dense output layer for modelling the temporal sequence inherent within the pulsatile signal representative of cardiac activity. The proposed network configuration was evaluated on the TROIKA dataset collected from 12 subjects involved in physical activity, achieved an average five-fold cross-validation accuracy of 96%.
Everson et al. (Mon,) conducted a other in Biometric identification (n=12). BiometricNET (deep learning-based framework) was evaluated on Average five-fold cross-validation accuracy for biometric identification. A novel deep learning framework (BiometricNET) using wrist-worn PPG signals achieved an average five-fold cross-validation accuracy of 96% for biometric identification during physical activity.