A Novel Non-Invasive Estimation of Respiration Rate From Motion Corrupted Photoplethysmograph Signal Using Machine Learning Model

<p>Respiratory ailments such as asthma, chronic obstructive pulmonary disease (COPD), pneumonia, and lung cancer are life-threatening. Respiration rate (RR) is a vital indicator of the wellness of a patient. Continuous monitoring of RR can provide early indication and thereby save lives. Howev...

Full description

Saved in:
Bibliographic Details
Main Author: Md. Nazmul Islam Shuzan (16888827) (author)
Other Authors: Moajjem Hossain Chowdhury (16888830) (author), Md. Shafayet Hossain (16888833) (author), Muhammad E. H. Chowdhury (14150526) (author), Mamun Bin Ibne Reaz (16875933) (author), Mohammad Monir Uddin (16888836) (author), Amith Khandakar (14151981) (author), Zaid Bin Mahbub (16869975) (author), Sawal Hamid Md. Ali (16888839) (author)
Published: 2021
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513560261951488
author Md. Nazmul Islam Shuzan (16888827)
author2 Moajjem Hossain Chowdhury (16888830)
Md. Shafayet Hossain (16888833)
Muhammad E. H. Chowdhury (14150526)
Mamun Bin Ibne Reaz (16875933)
Mohammad Monir Uddin (16888836)
Amith Khandakar (14151981)
Zaid Bin Mahbub (16869975)
Sawal Hamid Md. Ali (16888839)
author2_role author
author
author
author
author
author
author
author
author_facet Md. Nazmul Islam Shuzan (16888827)
Moajjem Hossain Chowdhury (16888830)
Md. Shafayet Hossain (16888833)
Muhammad E. H. Chowdhury (14150526)
Mamun Bin Ibne Reaz (16875933)
Mohammad Monir Uddin (16888836)
Amith Khandakar (14151981)
Zaid Bin Mahbub (16869975)
Sawal Hamid Md. Ali (16888839)
author_role author
dc.creator.none.fl_str_mv Md. Nazmul Islam Shuzan (16888827)
Moajjem Hossain Chowdhury (16888830)
Md. Shafayet Hossain (16888833)
Muhammad E. H. Chowdhury (14150526)
Mamun Bin Ibne Reaz (16875933)
Mohammad Monir Uddin (16888836)
Amith Khandakar (14151981)
Zaid Bin Mahbub (16869975)
Sawal Hamid Md. Ali (16888839)
dc.date.none.fl_str_mv 2021-07-07T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2021.3095380
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_Novel_Non-Invasive_Estimation_of_Respiration_Rate_From_Motion_Corrupted_Photoplethysmograph_Signal_Using_Machine_Learning_Model/24038994
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Biomedical engineering
Information and computing sciences
Data management and data science
Machine learning
Feature extraction
Estimation
Electrocardiography
Motion artifacts
Motion segmentation
Monitoring
Machine learning algorithms
Photoplethysmogram
Respiration rate
Machine learning
Feature selection
Motion artifact correction
Gaussian process regression
dc.title.none.fl_str_mv A Novel Non-Invasive Estimation of Respiration Rate From Motion Corrupted Photoplethysmograph Signal Using Machine Learning Model
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Respiratory ailments such as asthma, chronic obstructive pulmonary disease (COPD), pneumonia, and lung cancer are life-threatening. Respiration rate (RR) is a vital indicator of the wellness of a patient. Continuous monitoring of RR can provide early indication and thereby save lives. However, a real-time continuous RR monitoring facility is only available at the intensive care unit (ICU) due to the size and cost of the equipment. Recent researches have proposed Photoplethysmogram (PPG) and/ Electrocardiogram (ECG) signals for RR estimation however, the usage of ECG is limited due to the unavailability of it in wearable devices. Due to the advent of wearable smartwatches with built-in PPG sensors, it is now being considered for continuous monitoring of RR. This paper describes a novel approach for RR estimation using motion artifact correction and machine learning (ML) models with the PPG signal features. Feature selection algorithms were used to reduce computational complexity and the chance of overfitting. The best ML model and the best feature selection algorithm combination were fine-tuned to optimize its performance using hyperparameter optimization. Gaussian Process Regression (GPR) with Fit a Gaussian process regression model (Fitrgp) feature selection algorithm outperformed all other combinations and exhibits a root mean squared error (RMSE), mean absolute error (MAE), and two-standard deviation (2SD) of 2.63, 1.97, and 5.25 breaths per minute, respectively. Patients would be able to track RR at a lower cost and with less inconvenience if RR can be extracted efficiently and reliably from the PPG signal.</p><h2>Other Information</h2><p>Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2021.3095380" target="_blank">https://dx.doi.org/10.1109/access.2021.3095380</a></p>
eu_rights_str_mv openAccess
id Manara2_1a6e4cee0b73e2cfa9a3d49c3e280ea1
identifier_str_mv 10.1109/access.2021.3095380
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24038994
publishDate 2021
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A Novel Non-Invasive Estimation of Respiration Rate From Motion Corrupted Photoplethysmograph Signal Using Machine Learning ModelMd. Nazmul Islam Shuzan (16888827)Moajjem Hossain Chowdhury (16888830)Md. Shafayet Hossain (16888833)Muhammad E. H. Chowdhury (14150526)Mamun Bin Ibne Reaz (16875933)Mohammad Monir Uddin (16888836)Amith Khandakar (14151981)Zaid Bin Mahbub (16869975)Sawal Hamid Md. Ali (16888839)EngineeringBiomedical engineeringInformation and computing sciencesData management and data scienceMachine learningFeature extractionEstimationElectrocardiographyMotion artifactsMotion segmentationMonitoringMachine learning algorithmsPhotoplethysmogramRespiration rateMachine learningFeature selectionMotion artifact correctionGaussian process regression<p>Respiratory ailments such as asthma, chronic obstructive pulmonary disease (COPD), pneumonia, and lung cancer are life-threatening. Respiration rate (RR) is a vital indicator of the wellness of a patient. Continuous monitoring of RR can provide early indication and thereby save lives. However, a real-time continuous RR monitoring facility is only available at the intensive care unit (ICU) due to the size and cost of the equipment. Recent researches have proposed Photoplethysmogram (PPG) and/ Electrocardiogram (ECG) signals for RR estimation however, the usage of ECG is limited due to the unavailability of it in wearable devices. Due to the advent of wearable smartwatches with built-in PPG sensors, it is now being considered for continuous monitoring of RR. This paper describes a novel approach for RR estimation using motion artifact correction and machine learning (ML) models with the PPG signal features. Feature selection algorithms were used to reduce computational complexity and the chance of overfitting. The best ML model and the best feature selection algorithm combination were fine-tuned to optimize its performance using hyperparameter optimization. Gaussian Process Regression (GPR) with Fit a Gaussian process regression model (Fitrgp) feature selection algorithm outperformed all other combinations and exhibits a root mean squared error (RMSE), mean absolute error (MAE), and two-standard deviation (2SD) of 2.63, 1.97, and 5.25 breaths per minute, respectively. Patients would be able to track RR at a lower cost and with less inconvenience if RR can be extracted efficiently and reliably from the PPG signal.</p><h2>Other Information</h2><p>Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2021.3095380" target="_blank">https://dx.doi.org/10.1109/access.2021.3095380</a></p>2021-07-07T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2021.3095380https://figshare.com/articles/journal_contribution/A_Novel_Non-Invasive_Estimation_of_Respiration_Rate_From_Motion_Corrupted_Photoplethysmograph_Signal_Using_Machine_Learning_Model/24038994CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/240389942021-07-07T00:00:00Z
spellingShingle A Novel Non-Invasive Estimation of Respiration Rate From Motion Corrupted Photoplethysmograph Signal Using Machine Learning Model
Md. Nazmul Islam Shuzan (16888827)
Engineering
Biomedical engineering
Information and computing sciences
Data management and data science
Machine learning
Feature extraction
Estimation
Electrocardiography
Motion artifacts
Motion segmentation
Monitoring
Machine learning algorithms
Photoplethysmogram
Respiration rate
Machine learning
Feature selection
Motion artifact correction
Gaussian process regression
status_str publishedVersion
title A Novel Non-Invasive Estimation of Respiration Rate From Motion Corrupted Photoplethysmograph Signal Using Machine Learning Model
title_full A Novel Non-Invasive Estimation of Respiration Rate From Motion Corrupted Photoplethysmograph Signal Using Machine Learning Model
title_fullStr A Novel Non-Invasive Estimation of Respiration Rate From Motion Corrupted Photoplethysmograph Signal Using Machine Learning Model
title_full_unstemmed A Novel Non-Invasive Estimation of Respiration Rate From Motion Corrupted Photoplethysmograph Signal Using Machine Learning Model
title_short A Novel Non-Invasive Estimation of Respiration Rate From Motion Corrupted Photoplethysmograph Signal Using Machine Learning Model
title_sort A Novel Non-Invasive Estimation of Respiration Rate From Motion Corrupted Photoplethysmograph Signal Using Machine Learning Model
topic Engineering
Biomedical engineering
Information and computing sciences
Data management and data science
Machine learning
Feature extraction
Estimation
Electrocardiography
Motion artifacts
Motion segmentation
Monitoring
Machine learning algorithms
Photoplethysmogram
Respiration rate
Machine learning
Feature selection
Motion artifact correction
Gaussian process regression