Multi-task Learning for Estimation of Remote PPG and Respiration rate with Complex valued Convolutional Neural Network

Multi-task Learning for Estimation of Remote PPG and Respiration rate with Complex valued Convolutional Neural Network | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Multi-task Learning for Estimation of Remote PPG and Respiration rate with Complex valued Convolutional Neural Network Junghwan Lee, Yusang Nam, Jihwan Won, Suhwan Baek, Donggyu Sim, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5121010/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 10 Nov, 2025 Read the published version in Scientific Reports → Version 1 posted 6 You are reading this latest preprint version Abstract Remote and continuous biometric signal monitoring has become increasingly crucial for the prompt diagnosis of physiological disorders. However, traditional contact sensors might pose the risk of virus spread and cause discomfort, thereby impeding the continuous monitoring process. Furthermore, the enhancement of diagnostic performance using deep neural networks necessitates the use of large models, which could be a burden when developing embedded edge devices. Thus, we propose a multitask learning model to estimate the remote photoplethysmogram (PPG) and respiratory rate simultaneously based on facial videos using complex-valued neural networks. The RGB channel images are obtained from a region of interest of the facial video streams and a complex-numbered dataset is constructed. The multitask learning model designed for the complex domain can yield a small network architecture by reducing the number of parameters, which is advantageous for small embedded devices. Using a public dataset of face video streams from multiple participants, the proposed multitask learning model could simultaneously learn the remote PPG and respiratory rate with higher performance and a smaller structure compared with conventional real-valued neural networks. These results validate the potential of the proposed model for the accurate and efficient remote monitoring of physiological disorders. Biological sciences/Computational biology and bioinformatics Health sciences/Health care Physical sciences/Engineering Full Text Additional Declarations No competing interests reported. Supplementary Files MultitaskLearningforEstimationofRemotePPGandRespirationratewithComplexvaluedConvolutionalNeuralNetwork2.zip Cite Share Download PDF Status: Published Journal Publication published 10 Nov, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Accepted 03 Oct, 2025 Editor assigned by journal 10 Jun, 2025 Editor invited by journal 04 Jun, 2025 Reviewers invited by journal 21 Mar, 2025 Submission checks completed at journal 20 Mar, 2025 First submitted to journal 10 Mar, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-5121010","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":432231695,"identity":"d73c0316-2d1e-4437-be80-dcdcdf3c6b8c","order_by":0,"name":"Junghwan Lee","email":"","orcid":"","institution":"Kwangwoon University","correspondingAuthor":false,"prefix":"","firstName":"Junghwan","middleName":"","lastName":"Lee","suffix":""},{"id":432231696,"identity":"8e79d64f-0812-4767-878b-9a19220523b9","order_by":1,"name":"Yusang Nam","email":"","orcid":"","institution":"Kwangwoon University","correspondingAuthor":false,"prefix":"","firstName":"Yusang","middleName":"","lastName":"Nam","suffix":""},{"id":432231697,"identity":"6f9e394c-b1f0-4bc3-8111-7a4f6640e81a","order_by":2,"name":"Jihwan Won","email":"","orcid":"","institution":"Kwangwoon University","correspondingAuthor":false,"prefix":"","firstName":"Jihwan","middleName":"","lastName":"Won","suffix":""},{"id":432231698,"identity":"cf4fef4e-0ee6-4abb-872e-51a71f9d350c","order_by":3,"name":"Suhwan Baek","email":"","orcid":"","institution":"Kwangwoon University","correspondingAuthor":false,"prefix":"","firstName":"Suhwan","middleName":"","lastName":"Baek","suffix":""},{"id":432231699,"identity":"0ad1ab71-b55b-4bf9-9c91-a45ed8550c96","order_by":4,"name":"Donggyu Sim","email":"","orcid":"","institution":"Kwangwoon University","correspondingAuthor":false,"prefix":"","firstName":"Donggyu","middleName":"","lastName":"Sim","suffix":""},{"id":432231700,"identity":"fd6f4ffa-9e49-4043-b3fd-6a5c64f5af3f","order_by":5,"name":"Ryanghee Sohn","email":"","orcid":"","institution":"Emma healthcare corporation","correspondingAuthor":false,"prefix":"","firstName":"Ryanghee","middleName":"","lastName":"Sohn","suffix":""},{"id":432231701,"identity":"3de6ed9f-7056-400c-9952-75318acc4b28","order_by":6,"name":"Cheolsoo Park","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIie3RvQrCMBDA8SsHdSlmrRTqK7QEqkLxWQyFuPQBHAtCXNrdR3GsBHSJuBa6CIKzo05axUkh2s0h/+k4+EE+AEym/wzBygC6j/FcvjY/EbuZrGVrgs4vZNDZHYPrKvZtItfHWEkgixLpTENG+ZSyQnFquzyhaSXBVRNkSkOCkqO0hGTCdSIvPdcAFeA605H96UFuTBAVecOG9L+SimNiiZIJSCMPqrrZADIdGS1PGBYied4lzNXNCRWbhzoyIBzdqxj7pHmxw2XDfX8rZU97sPeFA89vakNMJpPJ9NEdQLJKMPhgPv4AAAAASUVORK5CYII=","orcid":"","institution":"Kwangwoon University","correspondingAuthor":true,"prefix":"","firstName":"Cheolsoo","middleName":"","lastName":"Park","suffix":""}],"badges":[],"createdAt":"2024-09-20 06:06:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5121010/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5121010/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-23103-x","type":"published","date":"2025-11-10T15:57:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":96104952,"identity":"2caa9c47-0987-4e1d-b55d-cd690422f6ec","added_by":"auto","created_at":"2025-11-17 16:03:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1090334,"visible":true,"origin":"","legend":"","description":"","filename":"MultitaskLearningforEstimationofRemotePPGandRespirationratewithComplexvaluedConvolutionalNeuralNetwork1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5121010/v1_covered_ae94bff5-2c15-4d42-9a1f-f276c6737ec5.pdf"},{"id":79078969,"identity":"5e8d544f-546f-47bf-96d6-fc6f781ff44b","added_by":"auto","created_at":"2025-03-24 07:55:08","extension":"zip","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":6637305,"visible":true,"origin":"","legend":"","description":"","filename":"MultitaskLearningforEstimationofRemotePPGandRespirationratewithComplexvaluedConvolutionalNeuralNetwork2.zip","url":"https://assets-eu.researchsquare.com/files/rs-5121010/v1/9ea352760654ac0ea91800db.zip"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multi-task Learning for Estimation of Remote PPG and Respiration rate with Complex valued Convolutional Neural Network","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-5121010/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5121010/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Remote and continuous biometric signal monitoring has become increasingly crucial for the prompt diagnosis of physiological disorders. However, traditional contact sensors might pose the risk of virus spread and cause discomfort, thereby impeding the continuous monitoring process. Furthermore, the enhancement of diagnostic performance using deep neural networks necessitates the use of large models, which could be a burden when developing embedded edge devices. Thus, we propose a multitask learning model to estimate the remote photoplethysmogram (PPG) and respiratory rate simultaneously based on facial videos using complex-valued neural networks. The RGB channel images are obtained from a region of interest of the facial video streams and a complex-numbered dataset is constructed. The multitask learning model designed for the complex domain can yield a small network architecture by reducing the number of parameters, which is advantageous for small embedded devices. Using a public dataset of face video streams from multiple participants, the proposed multitask learning model could simultaneously learn the remote PPG and respiratory rate with higher performance and a smaller structure compared with conventional real-valued neural networks. These results validate the potential of the proposed model for the accurate and efficient remote monitoring of physiological disorders.","manuscriptTitle":"Multi-task Learning for Estimation of Remote PPG and Respiration rate with Complex valued Convolutional Neural Network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-24 07:55:03","doi":"10.21203/rs.3.rs-5121010/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Accepted","date":"2025-10-03T12:57:14+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-10T05:40:20+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-06-04T07:20:29+00:00","index":"","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-03-21T06:20:58+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-21T02:27:53+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-03-11T03:40:31+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"7fcc07bd-1fd7-40d5-99b4-88ec391115b4","owner":[],"postedDate":"March 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":46041018,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":46041019,"name":"Health sciences/Health care"},{"id":46041020,"name":"Physical sciences/Engineering"}],"tags":[],"updatedAt":"2025-11-17T15:59:20+00:00","versionOfRecord":{"articleIdentity":"rs-5121010","link":"https://doi.org/10.1038/s41598-025-23103-x","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-11-10 15:57:00","publishedOnDateReadable":"November 10th, 2025"},"versionCreatedAt":"2025-03-24 07:55:03","video":"","vorDoi":"10.1038/s41598-025-23103-x","vorDoiUrl":"https://doi.org/10.1038/s41598-025-23103-x","workflowStages":[]},"version":"v1","identity":"rs-5121010","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5121010","identity":"rs-5121010","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}