AI-Driven Modelling and Control of Upper BodyBall and Socket Joints for Enhanced Swimming Performance in Sports Biomechanics

AI-Driven Modelling and Control of Upper BodyBall and Socket Joints for Enhanced Swimming Performance in Sports Biomechanics | 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 Article AI-Driven Modelling and Control of Upper BodyBall and Socket Joints for Enhanced Swimming Performance in Sports Biomechanics Zeeshan Saeed, Maryam Iqbal, Junaid Imtiaz This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7464013/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 In front crawl swimming, repetitive upper limb motion imposes substantial mechanical demands on the shoulder joint, potentially reducing performance and increasing injury risk. This study presents a noise aware, simulation based framework that integrates a reduced order biomechanical model, AI based shoulder angle estimation, and classical trajectory tracking control to analyze upper limb coordination under physiologically realistic conditions. This study is positioned as a simulation-based planar 3 DOF upper limb model, formulated using D’Alembert’s principle, is employed to evaluate shoulder abduction dynamics and joint torque profiles. Shoulder abduction angles are estimated from elbow kinematics using Linear Regression (LR), Decision Tree (DT), and Random Forest (RF) mod- els. Although the dataset is synthetically generated, it is constrained within experimentally reported swimming kinematics and validated against literature based range of motion and torque limits. Robustness is assessed by injecting 10% additive Gaussian noise. DT achieves high accuracy in noise free conditions (RMSE ≈ 0.16, R² ≈ 0.99) but degrades under noise, whereas RF demonstrates supe- rior robustness, with a 3 tree ensemble achieving RMSE ≈ 0.34 and R² ≈ 0.98 at low computational cost. AI predicted shoulder trajectories are directly used as reference inputs for PID and LQR controllers, forming a closed loop pipeline. Results show that prediction uncertainty propagates into control performance, with LQR providing smoother and more accurate tracking than PID, while maintaining joint torques within physiological limits. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Physical sciences/Mathematics and computing Biomechanical Model Sports Biomechanics Ball and Socket joint Random Forest Decision Tree Linear Quadratic Regulator Full Text Additional Declarations No competing interests reported. Supplementary Files datasettesting.csv DatasetTraining.csv 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-7464013","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":638275023,"identity":"a1a9b71f-c3d6-4189-a1f2-46806ac0752d","order_by":0,"name":"Zeeshan Saeed","email":"","orcid":"","institution":"Bahria University","correspondingAuthor":false,"prefix":"","firstName":"Zeeshan","middleName":"","lastName":"Saeed","suffix":""},{"id":638275025,"identity":"bb3faf5b-743a-429f-a423-2db87cc45554","order_by":1,"name":"Maryam Iqbal","email":"data:image/png;base64,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","orcid":"","institution":"Bahria University","correspondingAuthor":true,"prefix":"","firstName":"Maryam","middleName":"","lastName":"Iqbal","suffix":""},{"id":638275026,"identity":"d35033b7-47d9-4ab2-8d72-cbb38ecbbdbb","order_by":2,"name":"Junaid Imtiaz","email":"","orcid":"","institution":"Bahria University","correspondingAuthor":false,"prefix":"","firstName":"Junaid","middleName":"","lastName":"Imtiaz","suffix":""}],"badges":[],"createdAt":"2025-08-26 14:38:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7464013/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7464013/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109066218,"identity":"0d3542b1-33d2-4146-a7b4-4cab908aca8d","added_by":"auto","created_at":"2026-05-12 09:16:51","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1702492,"visible":true,"origin":"","legend":"","description":"","filename":"AIDrivenModellingandControlofUpperBodySRR3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7464013/v1_covered_7e26b1ce-ca83-4315-bf00-8ab428ea78db.pdf"},{"id":109065997,"identity":"5c624089-2a59-4411-8dba-64e17623c812","added_by":"auto","created_at":"2026-05-12 09:15:41","extension":"csv","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":2793,"visible":true,"origin":"","legend":"","description":"","filename":"datasettesting.csv","url":"https://assets-eu.researchsquare.com/files/rs-7464013/v1/86b1434fc60c5e26c9b61ff5.csv"},{"id":109066144,"identity":"d82e6788-007c-4f48-907b-689d98f393ca","added_by":"auto","created_at":"2026-05-12 09:16:11","extension":"csv","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":19593,"visible":true,"origin":"","legend":"","description":"","filename":"DatasetTraining.csv","url":"https://assets-eu.researchsquare.com/files/rs-7464013/v1/0ff993ff2c341b68e020a10d.csv"}],"financialInterests":"No competing interests reported.","formattedTitle":"AI-Driven Modelling and Control of Upper BodyBall and Socket Joints for Enhanced Swimming Performance in Sports Biomechanics","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Biomechanical Model, Sports Biomechanics, Ball and Socket joint, Random Forest, Decision Tree, Linear Quadratic Regulator","lastPublishedDoi":"10.21203/rs.3.rs-7464013/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7464013/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In front crawl swimming, repetitive upper limb motion imposes substantial mechanical demands on the shoulder joint, potentially reducing performance and increasing injury risk. This study presents a noise aware, simulation based framework that integrates a reduced order biomechanical model, AI\nbased shoulder angle estimation, and classical trajectory tracking control to analyze upper limb coordination under physiologically realistic conditions. This study is positioned as a simulation-based planar 3 DOF upper limb model, formulated using D’Alembert’s principle, is employed to evaluate shoulder abduction dynamics and joint torque profiles. Shoulder abduction angles are estimated from\nelbow kinematics using Linear Regression (LR), Decision Tree (DT), and Random Forest (RF) mod-\nels. Although the dataset is synthetically generated, it is constrained within experimentally reported swimming kinematics and validated against literature based range of motion and torque limits.\nRobustness is assessed by injecting 10% additive Gaussian noise. DT achieves high accuracy in noise\nfree conditions (RMSE ≈ 0.16, R² ≈ 0.99) but degrades under noise, whereas RF demonstrates supe-\nrior robustness, with a 3 tree ensemble achieving RMSE ≈ 0.34 and R² ≈ 0.98 at low computational\ncost.\nAI predicted shoulder trajectories are directly used as reference inputs for PID and LQR controllers, forming a closed loop pipeline. Results show that prediction uncertainty propagates into control\nperformance, with LQR providing smoother and more accurate tracking than PID, while maintaining\njoint torques within physiological limits.\n","manuscriptTitle":"AI-Driven Modelling and Control of Upper BodyBall and Socket Joints for Enhanced Swimming Performance in Sports Biomechanics","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-12 09:15:30","doi":"10.21203/rs.3.rs-7464013/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":"0e742634-d6ac-4efc-8538-38f73d33e3a3","owner":[],"postedDate":"May 12th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":67932795,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":67932796,"name":"Physical sciences/Engineering"},{"id":67932797,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-12T09:15:30+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-12 09:15:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7464013","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7464013","identity":"rs-7464013","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}