Wearable wrist to finger photoplethysmogram translation through restoration using super operational neural networks based 1D-CycleGAN for enhancing cardiovascular monitoring

<h3>Background and Motivations</h3><p dir="ltr">Physiological signals, such as the Photoplethysmogram (PPG) collected through wearable devices, consistently encounter significant motion artifacts. Current signal processing techniques, and even state-of-the-art machine lea...

Full description

Saved in:
Bibliographic Details
Main Author: Sakib Mahmud (15302404) (author)
Other Authors: Muhammad E.H. Chowdhury (17151154) (author), Serkan Kiranyaz (3762058) (author), Malisha Islam Tapotee (17823464) (author), Purnata Saha (17823467) (author), Anas M. Tahir (16870077) (author), Amith Khandakar (14151981) (author), Abdulrahman Alqahtani (6056309) (author)
Published: 2024
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513529431719936
author Sakib Mahmud (15302404)
author2 Muhammad E.H. Chowdhury (17151154)
Serkan Kiranyaz (3762058)
Malisha Islam Tapotee (17823464)
Purnata Saha (17823467)
Anas M. Tahir (16870077)
Amith Khandakar (14151981)
Abdulrahman Alqahtani (6056309)
author2_role author
author
author
author
author
author
author
author_facet Sakib Mahmud (15302404)
Muhammad E.H. Chowdhury (17151154)
Serkan Kiranyaz (3762058)
Malisha Islam Tapotee (17823464)
Purnata Saha (17823467)
Anas M. Tahir (16870077)
Amith Khandakar (14151981)
Abdulrahman Alqahtani (6056309)
author_role author
dc.creator.none.fl_str_mv Sakib Mahmud (15302404)
Muhammad E.H. Chowdhury (17151154)
Serkan Kiranyaz (3762058)
Malisha Islam Tapotee (17823464)
Purnata Saha (17823467)
Anas M. Tahir (16870077)
Amith Khandakar (14151981)
Abdulrahman Alqahtani (6056309)
dc.date.none.fl_str_mv 2024-07-15T03:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.eswa.2024.123167
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Wearable_wrist_to_finger_photoplethysmogram_translation_through_restoration_using_super_operational_neural_networks_based_1D-CycleGAN_for_enhancing_cardiovascular_monitoring/25038299
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Biomedical engineering
Communications engineering
Information and computing sciences
Data management and data science
Machine learning
TTR-GAN
1D-CycleGANs
Super-ONN
Wearables
Blind PPG Restoration
Wrist to Finger PPG Translation
Heart Rate Variability
dc.title.none.fl_str_mv Wearable wrist to finger photoplethysmogram translation through restoration using super operational neural networks based 1D-CycleGAN for enhancing cardiovascular monitoring
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <h3>Background and Motivations</h3><p dir="ltr">Physiological signals, such as the Photoplethysmogram (PPG) collected through wearable devices, consistently encounter significant motion artifacts. Current signal processing techniques, and even state-of-the-art machine learning algorithms, frequently struggle to effectively restore the inherent bodily signals amidst the array of randomly generated distortions. This often leads to the modification or even the degradation of the underlying physiological information.</p><h3>Methods</h3><p dir="ltr">To enhance heart rate estimation from wrist PPG (wPPG) signals, this study introduces the Translation Through Restoration GAN (TTR-GAN). TTR-GAN comprises cascaded dual-stage 1D Cycle Generative Adversarial Networks (1D-CycleGANs) constructed using Super-ONNs. In the first phase, corrupted wPPG waveforms are blindly restored using a 1D-CycleGAN-based restoration framework. Subsequently, in the second phase, the restored wPPG waveforms are translated into clean finger PPG (fPPG) signals through a 1D-CycleGAN-based signal-to-signal translation or synthesis framework. Both the restorer and translator GANs undergo independent evaluation using robust temporal, spectral, and clinical metrics.</p><h3>Results</h3><p dir="ltr">The application of the multipass restoration scheme to the wPPG signals resulted in significantly lower entropy compared to the raw wPPGs, indicating reduced irregularity. Using the proposed PRTX metric to evaluate the translational ability of the multichannel translator CycleGAN, we achieved a substantial improvement of 35.88% in wrist-to-finger PPG translation. The correlation between the pulse rate and pulse rate variations estimated from the generated fPPG signals and the heart rate and heart rate variability readings from the ground truth ECG improved by approximately 10.4% and 14.7%, respectively, when compared to the raw wPPG signals.</p><h3>Conclusion</h3><p dir="ltr">The proposed TTR-GAN can be implemented in wearable devices to obtain reliable real-time cardiovascular data during daily activities.</p><h2>Other Information</h2><p dir="ltr">Published in: Expert Systems with Applications<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.eswa.2024.123167" target="_blank">https://dx.doi.org/10.1016/j.eswa.2024.123167</a></p>
eu_rights_str_mv openAccess
id Manara2_a49a2abdcb4dbaa60804ef28af16195b
identifier_str_mv 10.1016/j.eswa.2024.123167
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25038299
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Wearable wrist to finger photoplethysmogram translation through restoration using super operational neural networks based 1D-CycleGAN for enhancing cardiovascular monitoringSakib Mahmud (15302404)Muhammad E.H. Chowdhury (17151154)Serkan Kiranyaz (3762058)Malisha Islam Tapotee (17823464)Purnata Saha (17823467)Anas M. Tahir (16870077)Amith Khandakar (14151981)Abdulrahman Alqahtani (6056309)EngineeringBiomedical engineeringCommunications engineeringInformation and computing sciencesData management and data scienceMachine learningTTR-GAN1D-CycleGANsSuper-ONNWearablesBlind PPG RestorationWrist to Finger PPG TranslationHeart Rate Variability<h3>Background and Motivations</h3><p dir="ltr">Physiological signals, such as the Photoplethysmogram (PPG) collected through wearable devices, consistently encounter significant motion artifacts. Current signal processing techniques, and even state-of-the-art machine learning algorithms, frequently struggle to effectively restore the inherent bodily signals amidst the array of randomly generated distortions. This often leads to the modification or even the degradation of the underlying physiological information.</p><h3>Methods</h3><p dir="ltr">To enhance heart rate estimation from wrist PPG (wPPG) signals, this study introduces the Translation Through Restoration GAN (TTR-GAN). TTR-GAN comprises cascaded dual-stage 1D Cycle Generative Adversarial Networks (1D-CycleGANs) constructed using Super-ONNs. In the first phase, corrupted wPPG waveforms are blindly restored using a 1D-CycleGAN-based restoration framework. Subsequently, in the second phase, the restored wPPG waveforms are translated into clean finger PPG (fPPG) signals through a 1D-CycleGAN-based signal-to-signal translation or synthesis framework. Both the restorer and translator GANs undergo independent evaluation using robust temporal, spectral, and clinical metrics.</p><h3>Results</h3><p dir="ltr">The application of the multipass restoration scheme to the wPPG signals resulted in significantly lower entropy compared to the raw wPPGs, indicating reduced irregularity. Using the proposed PRTX metric to evaluate the translational ability of the multichannel translator CycleGAN, we achieved a substantial improvement of 35.88% in wrist-to-finger PPG translation. The correlation between the pulse rate and pulse rate variations estimated from the generated fPPG signals and the heart rate and heart rate variability readings from the ground truth ECG improved by approximately 10.4% and 14.7%, respectively, when compared to the raw wPPG signals.</p><h3>Conclusion</h3><p dir="ltr">The proposed TTR-GAN can be implemented in wearable devices to obtain reliable real-time cardiovascular data during daily activities.</p><h2>Other Information</h2><p dir="ltr">Published in: Expert Systems with Applications<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.eswa.2024.123167" target="_blank">https://dx.doi.org/10.1016/j.eswa.2024.123167</a></p>2024-07-15T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.eswa.2024.123167https://figshare.com/articles/journal_contribution/Wearable_wrist_to_finger_photoplethysmogram_translation_through_restoration_using_super_operational_neural_networks_based_1D-CycleGAN_for_enhancing_cardiovascular_monitoring/25038299CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/250382992024-07-15T03:00:00Z
spellingShingle Wearable wrist to finger photoplethysmogram translation through restoration using super operational neural networks based 1D-CycleGAN for enhancing cardiovascular monitoring
Sakib Mahmud (15302404)
Engineering
Biomedical engineering
Communications engineering
Information and computing sciences
Data management and data science
Machine learning
TTR-GAN
1D-CycleGANs
Super-ONN
Wearables
Blind PPG Restoration
Wrist to Finger PPG Translation
Heart Rate Variability
status_str publishedVersion
title Wearable wrist to finger photoplethysmogram translation through restoration using super operational neural networks based 1D-CycleGAN for enhancing cardiovascular monitoring
title_full Wearable wrist to finger photoplethysmogram translation through restoration using super operational neural networks based 1D-CycleGAN for enhancing cardiovascular monitoring
title_fullStr Wearable wrist to finger photoplethysmogram translation through restoration using super operational neural networks based 1D-CycleGAN for enhancing cardiovascular monitoring
title_full_unstemmed Wearable wrist to finger photoplethysmogram translation through restoration using super operational neural networks based 1D-CycleGAN for enhancing cardiovascular monitoring
title_short Wearable wrist to finger photoplethysmogram translation through restoration using super operational neural networks based 1D-CycleGAN for enhancing cardiovascular monitoring
title_sort Wearable wrist to finger photoplethysmogram translation through restoration using super operational neural networks based 1D-CycleGAN for enhancing cardiovascular monitoring
topic Engineering
Biomedical engineering
Communications engineering
Information and computing sciences
Data management and data science
Machine learning
TTR-GAN
1D-CycleGANs
Super-ONN
Wearables
Blind PPG Restoration
Wrist to Finger PPG Translation
Heart Rate Variability