Abstract
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.
Original language | English (US) |
---|---|
Article number | 8607019 |
Pages (from-to) | 282-291 |
Number of pages | 10 |
Journal | IEEE transactions on biomedical circuits and systems |
Volume | 13 |
Issue number | 2 |
DOIs | |
State | Published - Apr 2019 |
Bibliographical note
Funding Information:Manuscript received September 28, 2018; revised December 7, 2018 and January 4, 2019; accepted January 8, 2019. Date of publication January 10, 2019; date of current version March 22, 2019. This work was supported by the NSF IGERT Grant DGE-1069104. This paper was recommended by Associate Editor P. C. Chung. (Corresponding author: Dwaipayan Biswas.) D. Biswas, B.-E. Verhoef, C. Van Hoof, and N. Van Helleputte are with the imec, 3001 Leuven, Belgium (e-mail:,Dwaipayan.Biswas@imec.be; Bram. Verhoef@imec.be; Chris.VanHoof@imec.be; Nick.VanHelleputte@imec.be).
Publisher Copyright:
© 2007-2012 IEEE.
Keywords
- Average heart rate
- PPG
- biometric
- convolutional neural network
- deep learning
- long short-Term memory