Multi-Layered Dual-Input Integrative Attention Model for Path Loss Prediction

Multi-Layered Dual-Input Integrative Attention Model for Path Loss Prediction | 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 Multi-Layered Dual-Input Integrative Attention Model for Path Loss Prediction Mamta Tikaria, Dr Vineeta Saxena This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5346222/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Path loss perdition significantly influences the strategic placement of base stations within cellular networks. The perdition of path loss using traditional approaches results in extensive field testing which is notably time-consuming. To address such issues, the paper explored the role of machine learning (ML) based approaches for path loss prediction. But in recent research contributions, mostly unmoral systems are used for prediction of path loss. To advance these approaches, the paper presented a bimodal path loss prediction system that integrates environmental data as well as visual information that are extracted from satellite relocation images. The paper presented a multi-layered architecture named as Dual-Input Integrative Attention Model (DIIAM) for path loss prediction. The DIIAM is composed of three major layers, Dual-Input Feature Extraction Layer (DIFEL), Feature Weighted At-tention Layer (FWAL) and Learning Layer (LL). DIFEL extracts features from each input. Environmental or channel parameters are selected by applying data imputation, normalization and relevant feature selection using T-Test and Z-Test. Whereas the relo-cation visual features are extracted by applying pre-trained transfer learning model such as ResNet50. Integration of these steps for dual-input feature extraction. This makes the DIFEL lightweight and requires less computational resources. FWAL used the attention mechanism to generate weighted features. LL layer implement six different learning models such as support vector re-gressor (SVR), Random forest regressor (RFR), Backpropagation Neural Network (BPNN), Long-short term memory (LSTM), Bidirectional LSTM (BiLSTM), and Gated recurrent unit (GRU). The multi-layered and dual-input nature of the proposed DI-IAM effectively process and learn the complex relationships between environmental characteristics and visual features. The simu-lation result was performed on four publicly available datasets for unimodal and bimodal systems. The average RMSE of the proposed DIIAM model was approx. 1.5dB which outperforms better as compared to state-of-the-art methods. Path loss 5G wireless communication machine learning bimodal Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-5346222","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":374703229,"identity":"525e3e74-2926-4117-aacd-cfb8367a7071","order_by":0,"name":"Mamta Tikaria","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBElEQVRIiWNgGAWjYPACCQMGBsYGhoQfNkAOY+MBAspBSqFaHvakgQWI0cJgAGY9YDsMFsKrRbf9dPqDnz8sjPlnH278kMBz3m5t+2GgLTU20bi0mJ3J3djYkyBhJnEusVkiweJ28rYziUAtx9JyG3BpOZC7sYEnQcKG4Qxjg0QCz+1kswNALYwNh3FrOf92Y+MfoBb5M4zNPxLYziWbnX9IQMuN3I3NQFvMDM4wtkkksB2wM7tByJYbbzfOlkmTMDYEarFI7ElOMLsBtCUBn1/O5274+MamznDeGfbHN3/8sLM3O5/+8MGHGhucWjBAIlhlArHKQcCeFMWjYBSMglEwMgAA7hxp9YJtzP0AAAAASUVORK5CYII=","orcid":"","institution":"University Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Mamta","middleName":"","lastName":"Tikaria","suffix":""},{"id":374703230,"identity":"33b10f46-cea3-436b-ba3a-945a425924ea","order_by":1,"name":"Dr Vineeta Saxena","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"Dr","firstName":"Vineeta","middleName":"","lastName":"Saxena","suffix":""}],"badges":[],"createdAt":"2024-10-28 10:23:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5346222/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5346222/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":77074121,"identity":"795580ba-6ac4-45f1-abfd-4232974e7e38","added_by":"auto","created_at":"2025-02-24 23:16:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":616570,"visible":true,"origin":"","legend":"","description":"","filename":"formatpaperupdated1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5346222/v1_covered_a52c4a19-87c2-4816-b0cd-6b61e7bd51dd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multi-Layered Dual-Input Integrative Attention Model for Path Loss Prediction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Path loss, 5G, wireless communication, machine learning, bimodal","lastPublishedDoi":"10.21203/rs.3.rs-5346222/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5346222/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePath loss perdition significantly influences the strategic placement of base stations within cellular networks. The perdition of path loss using traditional approaches results in extensive field testing which is notably time-consuming. To address such issues, the paper explored the role of machine learning (ML) based approaches for path loss prediction. But in recent research contributions, mostly unmoral systems are used for prediction of path loss. To advance these approaches, the paper presented a bimodal path loss prediction system that integrates environmental data as well as visual information that are extracted from satellite relocation images. The paper presented a multi-layered architecture named as Dual-Input Integrative Attention Model (DIIAM) for path loss prediction. The DIIAM is composed of three major layers, Dual-Input Feature Extraction Layer (DIFEL), Feature Weighted At-tention Layer (FWAL) and Learning Layer (LL). DIFEL extracts features from each input. Environmental or channel parameters are selected by applying data imputation, normalization and relevant feature selection using T-Test and Z-Test. Whereas the relo-cation visual features are extracted by applying pre-trained transfer learning model such as ResNet50. Integration of these steps for dual-input feature extraction. This makes the DIFEL lightweight and requires less computational resources. FWAL used the attention mechanism to generate weighted features. LL layer implement six different learning models such as support vector re-gressor (SVR), Random forest regressor (RFR), Backpropagation Neural Network (BPNN), Long-short term memory (LSTM), Bidirectional LSTM (BiLSTM), and Gated recurrent unit (GRU). The multi-layered and dual-input nature of the proposed DI-IAM effectively process and learn the complex relationships between environmental characteristics and visual features. The simu-lation result was performed on four publicly available datasets for unimodal and bimodal systems. The average RMSE of the proposed DIIAM model was approx. 1.5dB which outperforms better as compared to state-of-the-art methods.\u003c/p\u003e","manuscriptTitle":"Multi-Layered Dual-Input Integrative Attention Model for Path Loss Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-19 17:57:05","doi":"10.21203/rs.3.rs-5346222/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"e47f3248-7c90-4e4d-99ed-ffc3a3b25054","owner":[],"postedDate":"November 19th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-02-24T23:08:26+00:00","versionOfRecord":[],"versionCreatedAt":"2024-11-19 17:57:05","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5346222","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5346222","identity":"rs-5346222","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}