Next Article in Journal
Deep Dilated Convolutional Neural Network for Crowd Density Image Classification with Dataset Augmentation for Hajj Pilgrimage
Previous Article in Journal
Blockchain Private File Storage-Sharing Method Based on IPFS
Previous Article in Special Issue
Segmentation of Plantar Foot Thermal Images Using Prior Information
 
 
Communication

Multitask Siamese Network for Remote Photoplethysmography and Respiration Estimation

by 1,†, 2,†, 1,†, 1,†, 3, 4,* and 1,*
1
Department of Computer Engineering, Kwangwoon University, Seoul 01897, Korea
2
Department of Information Convergence, Kwangwoon University, Seoul 01897, Korea
3
Department of Electrical Engineering, Pohang University of Science and Technology, Seoul 37673, Korea
4
Emma Healthcare, Seongnam-si 13503, Korea
*
Authors to whom correspondence should be addressed.
These authors contributed equally to this work.
Academic Editor: Annie Lanzolla
Sensors 2022, 22(14), 5101; https://doi.org/10.3390/s22145101
Received: 9 April 2022 / Revised: 11 June 2022 / Accepted: 17 June 2022 / Published: 7 July 2022
(This article belongs to the Special Issue Contactless Sensors for Healthcare)
Heart and respiration rates represent important vital signs for the assessment of a person’s health condition. To estimate these vital signs accurately, we propose a multitask Siamese network model (MTS) that combines the advantages of the Siamese network and the multitask learning architecture. The MTS model was trained by the images of the cheek including nose and mouth and forehead areas while sharing the same parameters between the Siamese networks, in order to extract the features about the heart and respiratory information. The proposed model was constructed with a small number of parameters and was able to yield a high vital-sign-prediction accuracy, comparable to that obtained from the single-task learning model; furthermore, the proposed model outperformed the conventional multitask learning model. As a result, we can simultaneously predict the heart and respiratory signals with the MTS model, while the number of parameters was reduced by 16 times with the mean average errors of heart and respiration rates being 2.84 and 4.21. Owing to its light weight, it would be advantageous to implement the vital-sign-monitoring model in an edge device such as a mobile phone or small-sized portable devices. View Full-Text
Keywords: heart rate; respiration rate; contactless technique; deep learning; Siamese network; multitasking heart rate; respiration rate; contactless technique; deep learning; Siamese network; multitasking
Show Figures

Figure 1

MDPI and ACS Style

Lee, H.; Lee, J.; Kwon, Y.; Kwon, J.; Park, S.; Sohn, R.; Park, C. Multitask Siamese Network for Remote Photoplethysmography and Respiration Estimation. Sensors 2022, 22, 5101. https://doi.org/10.3390/s22145101

AMA Style

Lee H, Lee J, Kwon Y, Kwon J, Park S, Sohn R, Park C. Multitask Siamese Network for Remote Photoplethysmography and Respiration Estimation. Sensors. 2022; 22(14):5101. https://doi.org/10.3390/s22145101

Chicago/Turabian Style

Lee, Heejin, Junghwan Lee, Yujin Kwon, Jiyoon Kwon, Sungmin Park, Ryanghee Sohn, and Cheolsoo Park. 2022. "Multitask Siamese Network for Remote Photoplethysmography and Respiration Estimation" Sensors 22, no. 14: 5101. https://doi.org/10.3390/s22145101

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop