Dead Leaf Butterfly Optimizer: A novel optimization algorithm for engineering optimization and medical diagnosis based on graph neural network

Dead Leaf Butterfly Optimizer: A novel optimization algorithm for engineering optimization and medical diagnosis based on graph 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 Research Article Dead Leaf Butterfly Optimizer: A novel optimization algorithm for engineering optimization and medical diagnosis based on graph neural network Dedai Wei, Min Wan, Xinye Sha, Jiechao Chen, Jiawei Wang, Wanting Xiao, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6176013/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 Traditional optimization methods often face the problem of local optima, where the optimization process may get trapped in a local optimum, making it difficult to find the global optimal solution. Additionally, these methods tend to have low computational efficiency, especially when dealing with large-scale and complex problems, leading to high time and resource consumption. To address these challenges, we propose an innovative metaheuristic algorithm—Dead Leaf Butterfly Optimizer (DLBO). The algorithm is inspired by the behavior of dead leaf butterflies, mimicking their ability to protect themselves through color changes and camouflage, as well as altering the color of their dorsal surface by spreading their wings to ward off predators. The dead leaf butterfly hides itself from predators by mimicking the shape and color of dead leaves. When it gets threatened or in danger, it spreads its wings to reveal vibrant colors and patterns on its back, creating a visual contrast to deter and surprise enemies. The mix of camouflage and deterrence helps the dead leaf butterfly with great survival abilities. DLBO introduces a new optimization method that effectively avoids getting stuck in local optima and effectively improves global search capabilities. To assess the effectiveness of DLBO, we first compared it with 11 high-performance optimization algorithms on the CEC2017 and CEC2022 benchmark datasets. The results showed that DLBO performed better than other competitors in both convergence and robustness. Next, DLBO was applied to five real-world engineering challenges, including compression spring design, pressure vessel design, multi-disc clutch brake design, and robot gripper optimization. The experimental outcomes showed that DLBO performed excellently in dealing with convoluted engineering problems. Finally, we carried out experiments based on a breast cancer dataset, optimizing the hyperparameters of the Graph Convolutional Networks (GCNs) model with the help of DLBO and 11 other algorithms. GCNs are deep learning models specifically made for graph-structured data analysis, commonly used in biomedical and engineering tasks. Although GCNs can handle complex datasets well, their performance significantly relies on hyperparameter tuning and optimization. The experimental outcomes showcased that DLBO can significantly improve the predictive accuracy of GCNs when applied to breast cancer feature extraction and classification tasks. This study highlights both the strong optimization capabilities of DLBO but also shows the broad usefulness of GCNs in analyzing complex biomedical data. Graph Convolutional Networks Dead Leaf Butterfly Optimizer Numerical optimization Engineering design Breast Cancer Detection. Full Text Additional Declarations No competing interests reported. Supplementary Files SupplementaryMaterial.zip 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-6176013","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":428080187,"identity":"9c9d0758-dddc-47f0-b6a5-69b55bcaa569","order_by":0,"name":"Dedai Wei","email":"","orcid":"","institution":"Shenyang University","correspondingAuthor":false,"prefix":"","firstName":"Dedai","middleName":"","lastName":"Wei","suffix":""},{"id":428080188,"identity":"42c138c5-d79d-4857-9d6e-842e71f4dd23","order_by":1,"name":"Min Wan","email":"","orcid":"","institution":"Nanchang Jiaotong Institute","correspondingAuthor":false,"prefix":"","firstName":"Min","middleName":"","lastName":"Wan","suffix":""},{"id":428080189,"identity":"efc1e1fb-2beb-4351-bf88-24c22850a2fa","order_by":2,"name":"Xinye Sha","email":"","orcid":"","institution":"Columbia University","correspondingAuthor":false,"prefix":"","firstName":"Xinye","middleName":"","lastName":"Sha","suffix":""},{"id":428080190,"identity":"bae90db8-a862-4e6b-a790-fe2e426f73ed","order_by":3,"name":"Jiechao Chen","email":"","orcid":"","institution":"Guang zhou College of Technology and Business","correspondingAuthor":false,"prefix":"","firstName":"Jiechao","middleName":"","lastName":"Chen","suffix":""},{"id":428080191,"identity":"5e9915cd-8f31-4e13-bad9-d4debf8d048e","order_by":4,"name":"Jiawei Wang","email":"","orcid":"","institution":"Xiamen Medical College","correspondingAuthor":false,"prefix":"","firstName":"Jiawei","middleName":"","lastName":"Wang","suffix":""},{"id":428080192,"identity":"29528742-511a-4e2e-b95b-79cf9e877665","order_by":5,"name":"Wanting Xiao","email":"","orcid":"","institution":"Zhejiang University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Wanting","middleName":"","lastName":"Xiao","suffix":""},{"id":428080193,"identity":"da575568-6658-45c2-957d-b958191e8899","order_by":6,"name":"Shengwei Fu","email":"","orcid":"","institution":"Ministry of Education, Guizhou University","correspondingAuthor":false,"prefix":"","firstName":"Shengwei","middleName":"","lastName":"Fu","suffix":""},{"id":428080194,"identity":"9d323dec-9aa2-461b-a975-3f0a8d156267","order_by":7,"name":"Minyu Qiu","email":"","orcid":"","institution":"China Jiliang University","correspondingAuthor":false,"prefix":"","firstName":"Minyu","middleName":"","lastName":"Qiu","suffix":""},{"id":428080195,"identity":"a8a63ba5-711c-4d8d-bf43-2b9ec60453b2","order_by":8,"name":"Kaichen Ouyang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6ElEQVRIiWNgGAWjYFACNgaGDwwMPHxwgQNEaGGcAdTCBldNjBZmHohlRGrhl0hL/GybYyfDxsBj/PlDDYMc340Exs8FeLRIzkg7LJ27LRnoMB4ziQPHGIwlbyQwS8/Ao8XgRnobc+42ZrAWhoMNDIkbbiSwgZ2KV4vltnqQFuMPQC31RGhJO8bMuO0wSIuBBFBLggEhLZI9z5Ile7cd52FjZiuTOHNMwnDmmYfN0vi08LOnGX74ua3anp+9efOHihobeb7jyQc/49PCIJAAZTCDSQkgZmzApwFozQH88qNgFIyCUTAKGAATWkInNDYsZwAAAABJRU5ErkJggg==","orcid":"","institution":"University of Science and Technology of China","correspondingAuthor":true,"prefix":"","firstName":"Kaichen","middleName":"","lastName":"Ouyang","suffix":""}],"badges":[],"createdAt":"2025-03-07 07:38:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6176013/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6176013/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":79024837,"identity":"1c964e6c-cdcb-42e2-9fbf-2e1e65c64109","added_by":"auto","created_at":"2025-03-22 20:31:22","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2921115,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6176013/v1_covered_83880cc6-1080-4469-971a-0942873a87e0.pdf"},{"id":78633876,"identity":"e5cbf5a7-05e1-4cfc-bdfa-ad8990958b30","added_by":"auto","created_at":"2025-03-17 04:37:15","extension":"zip","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":21250,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterial.zip","url":"https://assets-eu.researchsquare.com/files/rs-6176013/v1/90e8e9532ab54ce410fb6db3.zip"}],"financialInterests":"No competing interests reported.","formattedTitle":"Dead Leaf Butterfly Optimizer: A novel optimization algorithm for engineering optimization and medical diagnosis based on graph neural network","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":"Graph Convolutional Networks, Dead Leaf Butterfly Optimizer, Numerical optimization, Engineering design, Breast Cancer Detection.","lastPublishedDoi":"10.21203/rs.3.rs-6176013/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6176013/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTraditional optimization methods often face the problem of local optima, where the optimization process may get trapped in a local optimum, making it difficult to find the global optimal solution. Additionally, these methods tend to have low computational efficiency, especially when dealing with large-scale and complex problems, leading to high time and resource consumption. To address these challenges, we propose an innovative metaheuristic algorithm\u0026mdash;Dead Leaf Butterfly Optimizer (DLBO). The algorithm is inspired by the behavior of dead leaf butterflies, mimicking their ability to protect themselves through color changes and camouflage, as well as altering the color of their dorsal surface by spreading their wings to ward off predators. The dead leaf butterfly hides itself from predators by mimicking the shape and color of dead leaves. When it gets threatened or in danger, it spreads its wings to reveal vibrant colors and patterns on its back, creating a visual contrast to deter and surprise enemies. The mix of camouflage and deterrence helps the dead leaf butterfly with great survival abilities. DLBO introduces a new optimization method that effectively avoids getting stuck in local optima and effectively improves global search capabilities. To assess the effectiveness of DLBO, we first compared it with 11 high-performance optimization algorithms on the CEC2017 and CEC2022 benchmark datasets. The results showed that DLBO performed better than other competitors in both convergence and robustness. Next, DLBO was applied to five real-world engineering challenges, including compression spring design, pressure vessel design, multi-disc clutch brake design, and robot gripper optimization. The experimental outcomes showed that DLBO performed excellently in dealing with convoluted engineering problems. Finally, we carried out experiments based on a breast cancer dataset, optimizing the hyperparameters of the Graph Convolutional Networks (GCNs) model with the help of DLBO and 11 other algorithms. GCNs are deep learning models specifically made for graph-structured data analysis, commonly used in biomedical and engineering tasks. Although GCNs can handle complex datasets well, their performance significantly relies on hyperparameter tuning and optimization. The experimental outcomes showcased that DLBO can significantly improve the predictive accuracy of GCNs when applied to breast cancer feature extraction and classification tasks. This study highlights both the strong optimization capabilities of DLBO but also shows the broad usefulness of GCNs in analyzing complex biomedical data.\u003c/p\u003e","manuscriptTitle":"Dead Leaf Butterfly Optimizer: A novel optimization algorithm for engineering optimization and medical diagnosis based on graph neural network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-17 04:21:10","doi":"10.21203/rs.3.rs-6176013/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":"9fff8c6c-6c3d-40ce-b90d-725b8cc88e3a","owner":[],"postedDate":"March 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-03-22T20:23:08+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-17 04:21:10","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6176013","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6176013","identity":"rs-6176013","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}