Influence of Data Scaling and Normalization on Overall Neural Network Performances in Photoacoustics

Influence of Data Scaling and Normalization on Overall Neural Network Performances in Photoacoustics | 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 Research Article Influence of Data Scaling and Normalization on Overall Neural Network Performances in Photoacoustics Miroslava Ivko Jordovic Pavlovic, Katarina Djordjevic, Zarko Cojbasic, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-942309/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract In this paper, the influence of the input and output data scaling and normalization on the neural network overall performances is investigated aimed at inverse problem-solving in photoacoustics of semiconductors. The logarithmic scaling of the photoacoustic signal amplitudes as input data and numerical scaling of the sample thermal parameters as output data are presented as useful tools trying to reach maximal network precision. Max and min-max normalizations to the input data are presented to change their numerical values in the dataset to common scales, without distorting differences. It was demonstrated in theory that the largest network prediction error of all targeted parameters is obtained by a network with non-scaled output data. Also, it was found out that the best network prediction was achieved with min-max normalization of the input data and network predicted output data scale within the range of [110]. Network training and prediction performances analyzed with experimental input data show that the benefits and improvements of input and output scaling and normalization are not guaranteed but are strongly dependent on a specific problem to be solved. Electrical Engineering Electronic Materials and Devices Optical Materials and Devices Atomic and Molecular Physics photoacoustic semiconductors artificial neural networks thermal diffusion thermal expansion photothermal inverse problem Full Text Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Major revisions 21 Jan, 2022 Reviews received at journal 27 Dec, 2021 Reviewers invited by journal 16 Oct, 2021 First submitted to journal 26 Sep, 2021 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-942309","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":57010776,"identity":"1065bf4e-c382-45f5-b08a-85bd6f4de1af","order_by":0,"name":"Miroslava Ivko Jordovic Pavlovic","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0003-4038-6537","institution":"Western Serbia Academy of Applied Studies","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Miroslava","middleName":"Ivko Jordovic","lastName":"Pavlovic","suffix":""},{"id":57010777,"identity":"b6d6b7a5-a779-401a-a2d3-3bec191b395b","order_by":1,"name":"Katarina Djordjevic","email":"","orcid":"","institution":"Institut za nuklearne nauke Vinča: Univerzitet u Beogradu Institut za nuklearne nauke Vinca","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Katarina","middleName":"","lastName":"Djordjevic","suffix":""},{"id":57010778,"identity":"3df46f08-1d57-4b01-ab86-7e8527a4636b","order_by":2,"name":"Zarko Cojbasic","email":"","orcid":"","institution":"Univerzitet v Nisu Masinski fakultet","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Zarko","middleName":"","lastName":"Cojbasic","suffix":""},{"id":57010779,"identity":"4c973d8a-793f-485a-929e-5e1d7d584279","order_by":3,"name":"Slobodanka Galovic","email":"","orcid":"","institution":"Institut za nuklearne nauke Vinča: Univerzitet u Beogradu Institut za nuklearne nauke Vinca","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Slobodanka","middleName":"","lastName":"Galovic","suffix":""},{"id":57010780,"identity":"4e6acfdd-cf43-4820-9fd1-934742a53ad2","order_by":4,"name":"Marica Popovic","email":"","orcid":"","institution":"Institut za nuklearne nauke Vinča: Univerzitet u Beogradu Institut za nuklearne nauke Vinca","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Marica","middleName":"","lastName":"Popovic","suffix":""},{"id":57010781,"identity":"4435cbd3-6f5d-4248-8871-32c1e85583b3","order_by":5,"name":"Mioljub Nesic","email":"","orcid":"","institution":"Institut za nuklearne nauke Vinča: Univerzitet u Beogradu Institut za nuklearne nauke Vinca","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Mioljub","middleName":"","lastName":"Nesic","suffix":""},{"id":57010782,"identity":"3ed5b617-799b-4e75-b309-7f5f2b60e8e1","order_by":6,"name":"Dragan Markushev","email":"","orcid":"","institution":"Institute of Physics Belgrade: Univerzitet u Beogradu Institut za Fiziku","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Dragan","middleName":"","lastName":"Markushev","suffix":""}],"badges":[],"createdAt":"2021-09-27 11:09:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-942309/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-942309/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":14622502,"identity":"6d3050b2-6828-482f-95ba-5b2810e0569f","added_by":"auto","created_at":"2021-10-18 14:46:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4004103,"visible":true,"origin":"","legend":"","description":"","filename":"Influenceofdatascalingandnormalization.pdf","url":"https://assets-eu.researchsquare.com/files/rs-942309/v1_covered.pdf"}],"financialInterests":"","formattedTitle":"\u003cp\u003eInfluence of Data Scaling and Normalization on Overall Neural Network Performances in Photoacoustics\u003c/p\u003e","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-942309/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."}],"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":true,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"optical-and-quantum-electronics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"oqel","sideBox":"Learn more about [Optical and Quantum Electronics](https://www.springer.com/journal/11082)","snPcode":"11082","submissionUrl":"https://submission.nature.com/new-submission/11082/3","title":"Optical and Quantum Electronics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"photoacoustic, semiconductors, artificial neural networks, thermal diffusion, thermal expansion, photothermal, inverse problem","lastPublishedDoi":"10.21203/rs.3.rs-942309/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-942309/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In this paper, the influence of the input and output data scaling and normalization on the neural network overall performances is investigated aimed at inverse problem-solving in photoacoustics of semiconductors. The logarithmic scaling of the photoacoustic signal amplitudes as input data and numerical scaling of the sample thermal parameters as output data are presented as useful tools trying to reach maximal network precision. Max and min-max normalizations to the input data are presented to change their numerical values in the dataset to common scales, without distorting differences. It was demonstrated in theory that the largest network prediction error of all targeted parameters is obtained by a network with non-scaled output data. Also, it was found out that the best network prediction was achieved with min-max normalization of the input data and network predicted output data scale within the range of [110]. Network training and prediction performances analyzed with experimental input data show that the benefits and improvements of input and output scaling and normalization are not guaranteed but are strongly dependent on a specific problem to be solved.","manuscriptTitle":"Influence of Data Scaling and Normalization on Overall Neural Network Performances in Photoacoustics","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2021-10-18 14:46:16","doi":"10.21203/rs.3.rs-942309/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revisions","date":"2022-01-21T06:31:48+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2021-12-27T08:19:13+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2021-10-16T13:09:50+00:00","index":"","fulltext":""},{"type":"submitted","content":"Optical and Quantum Electronics","date":"2021-09-26T07:14:40+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"optical-and-quantum-electronics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"oqel","sideBox":"Learn more about [Optical and Quantum Electronics](https://www.springer.com/journal/11082)","snPcode":"11082","submissionUrl":"https://submission.nature.com/new-submission/11082/3","title":"Optical and Quantum Electronics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"7582d782-40b4-486a-a1d0-a88baf976f33","owner":[],"postedDate":"October 18th, 2021","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":7917516,"name":"Electrical Engineering"},{"id":7917517,"name":"Electronic Materials and Devices"},{"id":7917518,"name":"Optical Materials and Devices"},{"id":7917519,"name":"Atomic and Molecular Physics"}],"tags":[],"updatedAt":"2022-04-22T17:41:44+00:00","versionOfRecord":[],"versionCreatedAt":"2021-10-18 14:46:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-942309","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-942309","identity":"rs-942309","version":["v1"]},"buildId":"WrCJVZZCHTDjtuVLN7oU0","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}