Design and Research of a Fusiform Fish Vaccination Machine Based on Enhanced YOLOv8s

Design and Research of a Fusiform Fish Vaccination Machine Based on Enhanced YOLOv8s | 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 Design and Research of a Fusiform Fish Vaccination Machine Based on Enhanced YOLOv8s Chen Li, Umar Abdulbaki Danhassan, Lin Luo, Songming Zhu, Jianping Li, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7469918/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract Traditional manual fish vaccination is labor-intensive, inefficient, and often characterized by poor working conditions. To address these challenges, this study introduces an intelligent fish vaccination system using grass carp as a model species. An improved YOLOv8s model was employed for real-time detection of fish fry. Specifically, the backbone integrates a C2f-DCNv2-MPCA module, which enhances the deformable convolutional structure by replacing parts of the original C2f. The spatial pyramid pooling (SPPF) was upgraded to an AIFI architecture, and an EMA attention mechanism was introduced for better performance. Similarly, an auxiliary bounding box inner-IoU loss function was implemented to optimize both the loss function and the accuracy. Experimental results demonstrate that the improved YOLOv8s-fish model achieves a mAP 50 of 95.5%, precision of 95.1%, and recall of 94.8%. These results represent improvements of 1.6, 1.5, and 1.1 percentage points over the baseline YOLOv8s, respectively, and the model operates at a detection speed of 175.4 frames per second (fps). When compared to YOLOv3-tiny, YOLOv5s, YOLOv7, and RT-DETR, the model shows increases in mAP 50 of 7.1, 8.2, 2.4, and 3.2 percentage points, respectively. These findings indicate the effectiveness of the improved model for the real-time detection of fry characteristics in complex micro-flow environments and provide valuable technical support for the subsequent design of fish vaccine injection devices. Grass carp YOLOv8s Attention mechanism Deep learning Object detection Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 15 Sep, 2025 Reviews received at journal 15 Sep, 2025 Reviews received at journal 10 Sep, 2025 Reviews received at journal 09 Sep, 2025 Reviews received at journal 30 Aug, 2025 Reviewers agreed at journal 30 Aug, 2025 Reviewers agreed at journal 29 Aug, 2025 Reviewers agreed at journal 28 Aug, 2025 Reviewers agreed at journal 28 Aug, 2025 Reviewers invited by journal 28 Aug, 2025 Editor assigned by journal 28 Aug, 2025 Submission checks completed at journal 28 Aug, 2025 First submitted to journal 27 Aug, 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-7469918","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":507930850,"identity":"fa5e6896-fa74-425c-8a75-a5583bf0b985","order_by":0,"name":"Chen Li","email":"","orcid":"","institution":"Zhejiang Academy of Agricultural Sciences","correspondingAuthor":false,"prefix":"","firstName":"Chen","middleName":"","lastName":"Li","suffix":""},{"id":507930851,"identity":"edfbbd01-a06d-4570-b76d-ea5e7057084a","order_by":1,"name":"Umar Abdulbaki Danhassan","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Umar","middleName":"Abdulbaki","lastName":"Danhassan","suffix":""},{"id":507930852,"identity":"b0e1f36c-7fc1-40cb-8963-2d8a6c08a463","order_by":2,"name":"Lin Luo","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Lin","middleName":"","lastName":"Luo","suffix":""},{"id":507930853,"identity":"6bc06e9f-8468-4b79-9f48-05cabaa24fbd","order_by":3,"name":"Songming Zhu","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Songming","middleName":"","lastName":"Zhu","suffix":""},{"id":507930854,"identity":"1b19969a-d9c0-4ecf-9ccd-83c978f41b35","order_by":4,"name":"Jianping Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAsklEQVRIiWNgGAWjYBACxgbmhgMfGNhAbANitTA2HJxBkhawPTwQFpFamGc3Nh62+cOX2MDevE2CoeYOEXbMOdhwOIeHLbGB51iZBMOxZ0RomZEI1CIB1CKRYybB2HCYSC0WBkAt8m9I0cKQALKFh1gtQL8c7DnAZtzGk1ZskXCMCC2Gs5sPf/jx55hsP/vhjTc+1BCjZQaYOgaJzATCGhgY5CXAVA0xakfBKBgFo2CkAgCiljrlnh8fRgAAAABJRU5ErkJggg==","orcid":"","institution":"Zhejiang University","correspondingAuthor":true,"prefix":"","firstName":"Jianping","middleName":"","lastName":"Li","suffix":""},{"id":507930855,"identity":"cb387dfa-d8d3-4280-99d5-7d3372ed5ed1","order_by":5,"name":"Zhangying Ye","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Zhangying","middleName":"","lastName":"Ye","suffix":""}],"badges":[],"createdAt":"2025-08-27 09:08:45","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7469918/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7469918/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90583058,"identity":"c718a2a4-0bb0-4b5a-ba24-29f660d19df0","added_by":"auto","created_at":"2025-09-04 10:39:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1371101,"visible":true,"origin":"","legend":"","description":"","filename":"DesignandResearchofaFusiformFishVaccinationMachineBasedonEnhancedYOLOv8s827.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7469918/v1_covered_8efa45af-d4c3-4fca-8f0e-a8a03017a77d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Design and Research of a Fusiform Fish Vaccination Machine Based on Enhanced YOLOv8s","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":"","identity":"aquaculture-international","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"10499","submissionUrl":"https://submission.nature.com/new-submission/10499/3","title":"Aquaculture International","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"","reportingPortfolio":"VoR Journals","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Grass carp, YOLOv8s, Attention mechanism, Deep learning, Object detection","lastPublishedDoi":"10.21203/rs.3.rs-7469918/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7469918/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTraditional manual fish vaccination is labor-intensive, inefficient, and often characterized by poor working conditions. To address these challenges, this study introduces an intelligent fish vaccination system using grass carp as a model species. An improved YOLOv8s model was employed for real-time detection of fish fry. Specifically, the backbone integrates a C2f-DCNv2-MPCA module, which enhances the deformable convolutional structure by replacing parts of the original C2f. The spatial pyramid pooling (SPPF) was upgraded to an AIFI architecture, and an EMA attention mechanism was introduced for better performance. Similarly, an auxiliary bounding box inner-IoU loss function was implemented to optimize both the loss function and the accuracy. Experimental results demonstrate that the improved YOLOv8s-fish model achieves a \u003cem\u003emAP\u003c/em\u003e\u003csub\u003e50\u003c/sub\u003e of 95.5%, precision of 95.1%, and recall of 94.8%. These results represent improvements of 1.6, 1.5, and 1.1 percentage points over the baseline YOLOv8s, respectively, and the model operates at a detection speed of 175.4 frames per second (fps). When compared to YOLOv3-tiny, YOLOv5s, YOLOv7, and RT-DETR, the model shows increases in \u003cem\u003emAP\u003c/em\u003e\u003csub\u003e50\u003c/sub\u003e of 7.1, 8.2, 2.4, and 3.2 percentage points, respectively. These findings indicate the effectiveness of the improved model for the real-time detection of fry characteristics in complex micro-flow environments and provide valuable technical support for the subsequent design of fish vaccine injection devices.\u003c/p\u003e","manuscriptTitle":"Design and Research of a Fusiform Fish Vaccination Machine Based on Enhanced YOLOv8s","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-04 10:15:08","doi":"10.21203/rs.3.rs-7469918/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-15T15:24:28+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-15T15:20:10+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-10T21:26:18+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-09T17:58:23+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-31T00:43:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"267979756268430325261480500430425820845","date":"2025-08-30T13:23:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"224795894750122082874782751862148733504","date":"2025-08-29T20:30:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"310506979417619101972799126054767099819","date":"2025-08-28T23:27:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"223604040074447898863891601928667192945","date":"2025-08-28T15:42:45+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-28T14:39:05+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-28T14:37:42+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-28T04:46:53+00:00","index":"","fulltext":""},{"type":"submitted","content":"Aquaculture International","date":"2025-08-27T08:58:22+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"","identity":"aquaculture-international","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"10499","submissionUrl":"https://submission.nature.com/new-submission/10499/3","title":"Aquaculture International","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"","reportingPortfolio":"VoR Journals","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"91287229-84d2-47ef-86a4-cfbb193281cf","owner":[],"postedDate":"September 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-12-24T14:23:42+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-04 10:15:08","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7469918","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7469918","identity":"rs-7469918","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}