CorNET: Deep Learning Framework for PPG-Based Heart Rate Estimation and Biometric Identification in Ambulant Environment

• Published in: IEEE transactions on biomedical circuits and systems 2019-04, Vol.13 (2), p.282-291
• Main Authors: Biswas, Dwaipayan, Everson, Luke, Liu, Muqing, Panwar, Madhuri, Verhoef, Bram-Ernst, Patki, Shrishail, Kim, Chris H., Acharyya, Amit, Van Hoof, Chris, Konijnenburg, Mario, Van Helleputte, Nick
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural networks; Average heart rate; biometric; Biometric Identification; Biometrics; Convolution; convolutional neural network; Data processing; Deep Learning; EKG; Electrocardiography; Estimation; Heart rate; Heart Rate - physiology; Humans; Long short-term memory; Monitoring; Neural networks; Neurons; Photoplethysmography; PPG; Remote monitoring; Remote sensors; Sensors; Signal monitoring; Signal Processing, Computer-Assisted; Walking - physiology; Wireless sensor networks; Wrist
• ISSN: 1932-4545; 1940-9990
• DOI: 10.1109/TBCAS.2019.2892297

Advancements in wireless sensor network technologies have enabled the proliferation of miniaturized body-worn sensors, capable of long-term pervasive biomedical signal monitoring. Remote cardiovascular monitoring has been one of the beneficiaries of this development, resulting in non-invasive, photoplethysmography (PPG) sensors being used in ambulatory settings. Wrist-worn PPG, although a popular alternative to electrocardiogram, suffers from motion artifacts inherent in daily life. Hence, in this paper, we present a novel deep learning framework (CorNET) to efficiently estimate heart rate (HR) information and perform biometric identification (BId) using only a wrist-worn, single-channel PPG signal collected in ambulant environment. We have formulated a completely personalized data-driven approach, using a four-layer deep neural network. Two convolution neural network layers are used in conjunction with two long short-term memory layers, followed by a dense output layer for modeling the temporal sequence inherent within the pulsatile signal representative of cardiac activity. The final dense layer is customized with respect to the application, functioning as: regression layer-having a single neuron to predict HR; classification layer-two neurons that identify a subject among a group. The proposed network was evaluated on the TROIKA dataset having 22 PPG records collected during various physical activities. We achieve a mean absolute error of 1.47 ± 3.37 beats per minute for HR estimation and an average accuracy of 96% for BId on 20 subjects. CorNET was further evaluated successfully in an ambulant use-case scenario with custom sensors for two subjects.