[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127046-en":3,"doc-seo-127046-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127046,962084928904,"Asher","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","PREDICTIVE MODELLING OF KNEE ANTERIOR SHEAR FORCES USING INERTIAL MEASUREMENT UNIT DATA AND MACHINE LEARNING","A non-invasive machine learning approach estimates proximal tibial anterior shear force (ASF), a surrogate for anterior cruciate ligament (ACL) loads, from inertial measurement unit (IMU) data. An XGBoost model was trained using drop-jump IMU recordings from 22 female participants and validated on an additional participant. Model optimization included feature reduction and signal filtering to improve prediction accuracy. Performance reached an RMSE of 41.59 ± 13.18 N, MAE of 35.18 ± 11.97 N, and R² of 0.84 ± 0.07.","PREDICTIVE MODELLING OF KNEE ANTERIOR SHEAR FORCES USING  \nINERTIAL MEASUREMENT UNIT DATA AND MACHINE LEARNING  \nSean A. Brown1, Taliah Carlson1, Lauren Dami1, and Joshua T. Weinhandl1 Kinesiology, Recreation, and Sport Studies, University of Tennessee, Knoxville, TN, USA1  \nThis study presents a non-invasive approach using machine learning to predict proximal  \ntibial anterior shear force (ASF), a surrogate for anterior cruciate ligament (ACL) loads from  \ninertial measurement unit (IMU) data, providing a practical alternative to direct force  \nmeasurement. Employing XGBoost, the research analysed IMU data from drop jump tasks  \nperformed by 22 female participants and validated on an additional participant. The model  \nunderwent optimization through feature reduction and signal filtering. The results  \ndemonstrate an XGBoost model using IMU data to estimate ASF showed improved  \nprediction accuracy after feature reduction and a low-pass filter. The model was able to  \npredict ASF with a root mean squared error of 41.59 ± 13. 18N, a mean absolute error of  \n35.18 ± 11.97N, and an R² value of 0.84 ± 0.07.  \nKEYWORDS: Wearable sensors , XGBoost Regression , Anterior Cruciate Ligament  \nINTRODUCTION: The anterior cruciate ligament (ACL) is crucial for maintaining knee stability during dynamic movements. Injuries to the ACL are common in athletic populations and can have long-term consequences. Quantifying the forces applied to the ACL, particularly the anterior shear force, is essential for understanding injury mechanisms and for developing preventive measures (Beaulieu et al. , 2023) . Direct measurement of the forces on the ACL during dynamic activities is not feasible in real-world settings due to the invasive nature required to measure forces transmitted through ligaments. As a result, there is a critical need for non-invasive predictive models that can estimate these forces accurately to aid in injury prevention and rehabilitation strategies (Chappell et al. , 2002) . Current methods utilize a three-dimensional (3D) motion capture laboratory to collect the movement of participants during specific tasks. However, motion capture labs are expensive to install and require highly trained individuals to operate. Inertial measurement units (IMUs) are inexpensive and easier to utilize to collect data because they do not require highly trained technicians or a dedicated laboratory. Beyond the financial and practical implications, IMUs can be utilized in real world environments, taking the athlete out of the laboratory, and placing them in their real-world environments which may lead to more sport and athlete specific data collection (Fong & Chan,  \n2010) .  \nThe aim of this research was to develop a non-invasive predictive model using machine learning techniques to estimate net anteroposterior joint reaction force, a surrogate for ACL loads (Chappell et al. , 2002) from 3D motion capture data. This was accomplished by utilizing data collected via two IMUs during a drop jump movement task. The primary goal was to use the IMU data to predict the proximal tibial anterior shear force (ASF), which was measured and calculated from the 3D motion capture and ground reaction force (GRF) data. This approach intended to leverage the predictive power of machine learning to establish a relationship between the easily obtainable IMU data and the more complex measurements derived from  \n3D motion capture.  \nMETHODS: 23 healthy, recreationally active females (age: 21.26 ± 1.71 years, height: 1.70 ± 0.05 m, mass: 64.03 ± 8.30 kg) voluntarily participated after providing informed consent.  \nParticipants completed 5 drop jump trials with 2 IMUs (500 Hz, IMeasureU , Blue Thunder) affixed to the right shank with elastic straps. One IMU was placed distally over the medial malleolus while the other was placed more proximally just distal of the tibial tuberosity. The IMUs each provide six columns of data, acceleration in three directions (mm/s²) and angular","cbCaifeTZ8VpImPe","https://ap.wps.com/l/cbCaifeTZ8VpImPe","pdf",345378,1,4,"English","en",105,"# Introduction\n# Methods\n# Machine Learning Approach and Model Evaluation","[{\"question\":\"Why predict proximal tibial anterior shear force (ASF) instead of directly measuring ACL loads?\",\"answer\":\"Direct ACL force measurement during dynamic activity is invasive and impractical in real-world settings. ASF serves as a surrogate that can be estimated non-invasively to support injury prevention and rehabilitation.\"},{\"question\":\"How was the IMU data collected during the study?\",\"answer\":\"Participants performed drop-jump trials while wearing two IMUs on the right shank. One sensor was placed distally over the medial malleolus and the other proximally just distal to the tibial tuberosity.\"},{\"question\":\"Which machine learning method was used and how was the model optimized?\",\"answer\":\"The study used XGBoost to predict ASF from IMU features. Accuracy was improved through feature reduction and low-pass filtering of signals.\"}]","PREDICTIVE MODELLING OF KNEE ANTERIOR SHEAR FORCES USING INERTIAL MEASUREMENT UNIT DATA AND MACHINE LEARNING | PDF",1785936531,10,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"predictive-modelling-of-knee-anterior-shear-forces-using-inertial-measurement-unit-data-and-machine-learning","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":21},"https://docshare.wps.com/document/predictive-modelling-of-knee-anterior-shear-forces-using-inertial-measurement-unit-data-and-machine-learning/127046/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-21","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why predict proximal tibial anterior shear force (ASF) instead of directly measuring ACL loads?","Question",{"text":75,"@type":76},"Direct ACL force measurement during dynamic activity is invasive and impractical in real-world settings. ASF serves as a surrogate that can be estimated non-invasively to support injury prevention and rehabilitation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How was the IMU data collected during the study?",{"text":80,"@type":76},"Participants performed drop-jump trials while wearing two IMUs on the right shank. One sensor was placed distally over the medial malleolus and the other proximally just distal to the tibial tuberosity.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning method was used and how was the model optimized?",{"text":84,"@type":76},"The study used XGBoost to predict ASF from IMU features. Accuracy was improved through feature reduction and low-pass filtering of signals.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":29,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]