A Hybrid Flower Pollination and Seed Dispersal Algorithm for Optimizing Artificial Neural Networks in Medical Image Classification

A Hybrid Flower Pollination and Seed Dispersal Algorithm for Optimizing Artificial Neural Networks in Medical Image Classification | 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 A Hybrid Flower Pollination and Seed Dispersal Algorithm for Optimizing Artificial Neural Networks in Medical Image Classification Mona Alsbakhi, Mohammed Lubbad, Mohammed Alhanjouri This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9593415/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 Purpose: Artificial Neural Networks (ANNs) are considered the core of recent medical image analysis. They provide a powerful tool for disease classification with high accuracy. However, ANN performance depends heavily on parameter improvements. Traditional optimization methods face challenges including slow convergence and entrapment in local minima, which restrict the accuracy of the diagnostic process. Methods: To address these challenges, this paper investigates two plant-inspired metaheuristic algorithms: the Flower Pollination Algorithm (FPA) and the Seed Dispersal Algorithm (SDA). A novel Hybrid FPA-SDA framework is proposed by integrating FPA's global exploration capabilities with SDA's local refinement strengths to achieve effective ANN parameter optimization. The proposed framework was assessed using a benchmark chest X-ray dataset for pneumonia detection. Results: The performance of the proposed approach was compared against standalone FPA and SDA, in addition to established baselines including Stochastic Gradient Descent (SGD) and PCA-based random search. Experimental results show that the Hybrid FPA-SDA framework achieved the highest accuracy (68.73%) among all tested methods. It also showed advantages in recall (75.84%) and training speed (85.69s vs 93.40s for FPA). Conclusion: The results demonstrate that hybrid metaheuristic optimization can improve ANN parameter tuning for medical image classification. Both FPA-based methods outperformed the gradient-based SGD baseline, confirming the efficiency of metaheuristic optimization in improving diagnostic performance. Hybrid Optimization Metaheuristics Flower Pollination Algorithm Seed Dispersal Algorithm Artificial Neural Network Medical Image Classification 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-9593415","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":640017588,"identity":"23781c8d-421c-4960-8d39-6007670d17d6","order_by":0,"name":"Mona Alsbakhi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAApUlEQVRIiWNgGAWjYLCCDwUMCQYMDAbE62CcYUCqFmYekrTotvce/GxjcDjPnP3wBqYbFURoMTtzLlk6x+BwsWVPWgFzzhlitNzIMQBpSdxwIMeAObeNOC3Gvy1AWs6/AWr5R5wWM2kGkJYbIFsaiNFy5oyZZY9BerHljGcFh3OOEaPleI/xjR8V1nnm/MkbH+fUEKEFBRwgVcMoGAWjYBSMAhwAAL9vOKzYPRM5AAAAAElFTkSuQmCC","orcid":"","institution":"Islamic University of Gaza","correspondingAuthor":true,"prefix":"","firstName":"Mona","middleName":"","lastName":"Alsbakhi","suffix":""},{"id":640017592,"identity":"bce8ebf7-5c5f-4ef4-bf87-60ec8681f007","order_by":1,"name":"Mohammed Lubbad","email":"","orcid":"","institution":"Islamic University of Gaza","correspondingAuthor":false,"prefix":"","firstName":"Mohammed","middleName":"","lastName":"Lubbad","suffix":""},{"id":640017595,"identity":"bf1dc047-af4e-4703-8fe4-7f13c95cbdc5","order_by":2,"name":"Mohammed Alhanjouri","email":"","orcid":"","institution":"Islamic University of Gaza","correspondingAuthor":false,"prefix":"","firstName":"Mohammed","middleName":"","lastName":"Alhanjouri","suffix":""}],"badges":[],"createdAt":"2026-05-02 11:38:28","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9593415/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9593415/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109405774,"identity":"95802476-e908-4576-bd38-a8a09f0fece2","added_by":"auto","created_at":"2026-05-17 13:20:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":901681,"visible":true,"origin":"","legend":"","description":"","filename":"HybridFPASDAMay.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9593415/v1_covered_644296d5-79b4-4297-b1ec-8a013a498ffb.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Hybrid Flower Pollination and Seed Dispersal Algorithm for Optimizing Artificial Neural Networks in Medical Image Classification","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":true,"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":"Hybrid Optimization, Metaheuristics, Flower Pollination Algorithm, Seed Dispersal Algorithm, Artificial Neural Network, Medical Image Classification","lastPublishedDoi":"10.21203/rs.3.rs-9593415/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9593415/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003ePurpose:\u003c/h2\u003e\u003cp\u003eArtificial Neural Networks (ANNs) are considered the core of recent medical image analysis. They provide a powerful tool for disease classification with high accuracy. However, ANN performance depends heavily on parameter improvements. Traditional optimization methods face challenges including slow convergence and entrapment in local minima, which restrict the accuracy of the diagnostic process.\u003c/p\u003e\u003ch2\u003eMethods:\u003c/h2\u003e\u003cp\u003eTo address these challenges, this paper investigates two plant-inspired metaheuristic algorithms: the Flower Pollination Algorithm (FPA) and the Seed Dispersal Algorithm (SDA). A novel Hybrid FPA-SDA framework is proposed by integrating FPA's global exploration capabilities with SDA's local refinement strengths to achieve effective ANN parameter optimization. The proposed framework was assessed using a benchmark chest X-ray dataset for pneumonia detection.\u003c/p\u003e\u003ch2\u003eResults:\u003c/h2\u003e\u003cp\u003eThe performance of the proposed approach was compared against standalone FPA and SDA, in addition to established baselines including Stochastic Gradient Descent (SGD) and PCA-based random search. Experimental results show that the Hybrid FPA-SDA framework achieved the highest accuracy (68.73%) among all tested methods. It also showed advantages in recall (75.84%) and training speed (85.69s vs 93.40s for FPA).\u003c/p\u003e\u003ch2\u003eConclusion:\u003c/h2\u003e\u003cp\u003eThe results demonstrate that hybrid metaheuristic optimization can improve ANN parameter tuning for medical image classification. Both FPA-based methods outperformed the gradient-based SGD baseline, confirming the efficiency of metaheuristic optimization in improving diagnostic performance.\u003c/p\u003e","manuscriptTitle":"A Hybrid Flower Pollination and Seed Dispersal Algorithm for Optimizing Artificial Neural Networks in Medical Image Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-15 07:26:02","doi":"10.21203/rs.3.rs-9593415/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":"9c1475fb-a00f-4d53-87e8-6033d636f445","owner":[],"postedDate":"May 15th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Rejected","date":"2026-05-15T11:39:41+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-14T02:52:37+00:00","index":17,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-13T17:23:39+00:00","index":16,"fulltext":""},{"type":"reviewerAgreed","content":"331937776077631961636290642208914111435","date":"2026-05-13T17:19:56+00:00","index":15,"fulltext":""},{"type":"reviewerAgreed","content":"11276551401918898134074777707459880603","date":"2026-05-06T13:50:59+00:00","index":14,"fulltext":""},{"type":"reviewersInvited","content":"6","date":"2026-05-06T13:24:48+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-05T03:45:00+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-05-05T03:44:33+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of King Saud University Computer and Information Sciences","date":"2026-05-02T11:24:34+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-15T11:54:57+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-15 07:26:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9593415","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9593415","identity":"rs-9593415","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}