Sleep postures monitoring based on capacitively coupled electrodes and deep recurrent neural networks
Abstract Background Capacitively coupled electrode (CC electrode), as a non-contact and unobtrusive technology for measuring physiological signals, has been widely applied in sleep monitoring scenarios. The most common implementation is capacitive electrocardiogram (cECG) that could provide useful c...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2022-10-01
|
Series: | BioMedical Engineering OnLine |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12938-022-01031-5 |
_version_ | 1811238932865613824 |
---|---|
author | Shun Peng Yang Li Rui Cui Ke Xu Yonglin Wu Ming Huang Chenyun Dai Toshiyo Tamur Subhas Mukhopadhyay Chen Chen Wei Chen |
author_facet | Shun Peng Yang Li Rui Cui Ke Xu Yonglin Wu Ming Huang Chenyun Dai Toshiyo Tamur Subhas Mukhopadhyay Chen Chen Wei Chen |
author_sort | Shun Peng |
collection | DOAJ |
description | Abstract Background Capacitively coupled electrode (CC electrode), as a non-contact and unobtrusive technology for measuring physiological signals, has been widely applied in sleep monitoring scenarios. The most common implementation is capacitive electrocardiogram (cECG) that could provide useful clinical information for assessing cardiac function and detecting cardiovascular diseases. In the current study, we sought to explore another potential application of cECG in sleep monitoring, i.e., sleep postures recognition. Methods Two sets of experiments, the short-term experiment, and the overnight experiment, were conducted. The cECG signals were measured by a smart mattress based on flexible CC electrodes and sleep postures were recorded simultaneously. Then, a classifier model based on a deep recurrent neural network (RNN) was proposed to distinguish sleep postures (supine, left lateral and right lateral). To verify the reliability of the proposed model, leave-one-subject-out cross-validation was introduced. Results In the short-term experiment, the overall accuracy of 96.2% was achieved based on 30-s segment, while the overall accuracy was 88.8% using one heart beat segment. For the unconstrained overnight experiment, the accuracy of 91.0% was achieved based on 30-s segment, while the accuracy was 81.4% using one heart beat segment. Conclusions The results suggest that cECG could render valuable information about sleep postures detection and potentially be helpful for sleep disorder diagnosis. |
first_indexed | 2024-04-12T12:50:59Z |
format | Article |
id | doaj.art-dbbbe89ec7d447529b953fdf3f01c9bc |
institution | Directory Open Access Journal |
issn | 1475-925X |
language | English |
last_indexed | 2024-04-12T12:50:59Z |
publishDate | 2022-10-01 |
publisher | BMC |
record_format | Article |
series | BioMedical Engineering OnLine |
spelling | doaj.art-dbbbe89ec7d447529b953fdf3f01c9bc2022-12-22T03:32:29ZengBMCBioMedical Engineering OnLine1475-925X2022-10-0121111510.1186/s12938-022-01031-5Sleep postures monitoring based on capacitively coupled electrodes and deep recurrent neural networksShun Peng0Yang Li1Rui Cui2Ke Xu3Yonglin Wu4Ming Huang5Chenyun Dai6Toshiyo Tamur7Subhas Mukhopadhyay8Chen Chen9Wei Chen10Center for Intelligent Medical Electronics, School of Information Science and Technology, Fudan UniversityCenter for Intelligent Medical Electronics, School of Information Science and Technology, Fudan UniversityCenter for Intelligent Medical Electronics, School of Information Science and Technology, Fudan UniversityDepartment of Infectious Disease, Imperial College LondonCenter for Intelligent Medical Electronics, School of Information Science and Technology, Fudan UniversityComputational Systems Biology, Division of Information Science, Nara Institute of Science and TechnologyCenter for Intelligent Medical Electronics, School of Information Science and Technology, Fudan UniversityInstitute for Healthcare Robotics, Waseda UniversitySchool of Engineering, Macquarie UniversityHuman Phenome Institute, Fudan UniversityCenter for Intelligent Medical Electronics, School of Information Science and Technology, Fudan UniversityAbstract Background Capacitively coupled electrode (CC electrode), as a non-contact and unobtrusive technology for measuring physiological signals, has been widely applied in sleep monitoring scenarios. The most common implementation is capacitive electrocardiogram (cECG) that could provide useful clinical information for assessing cardiac function and detecting cardiovascular diseases. In the current study, we sought to explore another potential application of cECG in sleep monitoring, i.e., sleep postures recognition. Methods Two sets of experiments, the short-term experiment, and the overnight experiment, were conducted. The cECG signals were measured by a smart mattress based on flexible CC electrodes and sleep postures were recorded simultaneously. Then, a classifier model based on a deep recurrent neural network (RNN) was proposed to distinguish sleep postures (supine, left lateral and right lateral). To verify the reliability of the proposed model, leave-one-subject-out cross-validation was introduced. Results In the short-term experiment, the overall accuracy of 96.2% was achieved based on 30-s segment, while the overall accuracy was 88.8% using one heart beat segment. For the unconstrained overnight experiment, the accuracy of 91.0% was achieved based on 30-s segment, while the accuracy was 81.4% using one heart beat segment. Conclusions The results suggest that cECG could render valuable information about sleep postures detection and potentially be helpful for sleep disorder diagnosis.https://doi.org/10.1186/s12938-022-01031-5Capacitively coupled electrodeSleep postureCapacitive electrocardiogramRecurrent neural network |
spellingShingle | Shun Peng Yang Li Rui Cui Ke Xu Yonglin Wu Ming Huang Chenyun Dai Toshiyo Tamur Subhas Mukhopadhyay Chen Chen Wei Chen Sleep postures monitoring based on capacitively coupled electrodes and deep recurrent neural networks BioMedical Engineering OnLine Capacitively coupled electrode Sleep posture Capacitive electrocardiogram Recurrent neural network |
title | Sleep postures monitoring based on capacitively coupled electrodes and deep recurrent neural networks |
title_full | Sleep postures monitoring based on capacitively coupled electrodes and deep recurrent neural networks |
title_fullStr | Sleep postures monitoring based on capacitively coupled electrodes and deep recurrent neural networks |
title_full_unstemmed | Sleep postures monitoring based on capacitively coupled electrodes and deep recurrent neural networks |
title_short | Sleep postures monitoring based on capacitively coupled electrodes and deep recurrent neural networks |
title_sort | sleep postures monitoring based on capacitively coupled electrodes and deep recurrent neural networks |
topic | Capacitively coupled electrode Sleep posture Capacitive electrocardiogram Recurrent neural network |
url | https://doi.org/10.1186/s12938-022-01031-5 |
work_keys_str_mv | AT shunpeng sleepposturesmonitoringbasedoncapacitivelycoupledelectrodesanddeeprecurrentneuralnetworks AT yangli sleepposturesmonitoringbasedoncapacitivelycoupledelectrodesanddeeprecurrentneuralnetworks AT ruicui sleepposturesmonitoringbasedoncapacitivelycoupledelectrodesanddeeprecurrentneuralnetworks AT kexu sleepposturesmonitoringbasedoncapacitivelycoupledelectrodesanddeeprecurrentneuralnetworks AT yonglinwu sleepposturesmonitoringbasedoncapacitivelycoupledelectrodesanddeeprecurrentneuralnetworks AT minghuang sleepposturesmonitoringbasedoncapacitivelycoupledelectrodesanddeeprecurrentneuralnetworks AT chenyundai sleepposturesmonitoringbasedoncapacitivelycoupledelectrodesanddeeprecurrentneuralnetworks AT toshiyotamur sleepposturesmonitoringbasedoncapacitivelycoupledelectrodesanddeeprecurrentneuralnetworks AT subhasmukhopadhyay sleepposturesmonitoringbasedoncapacitivelycoupledelectrodesanddeeprecurrentneuralnetworks AT chenchen sleepposturesmonitoringbasedoncapacitivelycoupledelectrodesanddeeprecurrentneuralnetworks AT weichen sleepposturesmonitoringbasedoncapacitivelycoupledelectrodesanddeeprecurrentneuralnetworks |