[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120070-en":3,"doc-seo-120070-105":30,"detail-sidebar-cat-0-en-105":90},{"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":4,"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},120070,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",7,"Healthcare","Patient-Handling Tasks and Posture Classification with Machine Learning - Poster","Machine learning methods are used to predict which patient-handling task is performed and the quality of participants’ adopted postures using wearable IMU sensor data and force-plate measurements. The study addresses limitations of optical marker systems by leveraging IMUs for data collection in more realistic settings. Models are evaluated on multivariate time-series classification and trained on different IMU input combinations, with results showing the trunk+pelvis configuration and MiniRocket delivering the strongest accuracy and precision.","Hope College  \nHope College Digital Commons  \n\n| 22nd Annual Celebration of Undergraduate Research and Creative Activity (2023) | The A. Paul and Carol C. Schaap Celebration of Undergraduate Research and Creative Activity |\n| --- | --- |\n| 4-14-2023\u003Cbr>Patient-Handling Tasks and Posture Classification with Machine Learning\u003Cbr>Haniah Kring Hope College\u003Cbr>Annie Ngoc Tran Hope College\u003Cbr>Elsa Brillinger Hope College\u003Cbr>Aine Snoap Hope College\u003Cbr>Noah Bradford\u003Cbr>Hope College\u003Cbr>Follow this and additional works at: [https://digitalcommons.hope.edu/curca_22](https://digitalcommons.hope.edu/curca_22)\u003Cbr> Part of the Computer Sciences Commons |  |\n\nRecommended Citation  \nRepository citation: Kring, Haniah; Tran, Annie Ngoc; Brillinger, Elsa; Snoap, Aine; and Bradford, Noah,\"Patient-Handling Tasks and Posture Classification with Machine Learning\" (2023) . 22nd Annual Celebration of Undergraduate Research and Creative Activity (2023). Paper 41.  \n[https://digitalcommons.hope.edu/curca_22/41](https://digitalcommons.hope.edu/curca_22/41)  \nApril 14, 2023. Copyright © 2023 Hope College, Holland, Michigan.  \nThis Poster is brought to you for free and open access by the The A. Paul and Carol C. Schaap Celebration of Undergraduate Research and Creative Activity at Hope College Digital Commons. It has been accepted for inclusion in 22nd Annual Celebration of Undergraduate Research and Creative Activity (2023) by an authorized administrator of Hope College Digital Commons. For more information, please [contact digitalcommons@hope.edu](contact digitalcommons@hope.edu), [barneycj@hope.edu](barneycj@hope.edu).  \nPatient-Handling Tasks and Posture Classification with Machine Learning  \nNgoc Tran, Haniah Kring, Elsa Brillinger, Aine Snoap, Noah Bradford (with Dr. Brooke Odle and Dr. Omofolakunmi Olagbemi-Advisors)  \nHope College, Holland, Michigan  \nFor more information, contact: Dr. O. Olagbemi  \n141 East 12th Street, Holland, MI[olagbemi@hope.edu](olagbemi@hope.edu)  \n\n| Introduction\u003Cbr>A 2016 survey conducted by Venditelli et al [1] indicated that 39% of registered nursing respondents had reported musculoskeletal injuries after two years of regularly performing patient-handling tasks. Optical marker systems (considered the gold standard) can be accurately used in laboratory settings to explore mechanisms of injury during patient-handling tasks, but deploying inertial measuring units (IMUs) in biomechanics allows data collection in both laboratory and clinical environments. IMU-based capture systems are also preferable to optical marker systems because they avoid marker occlusion during more complicated patient-handling tasks. The purposes of our study are (1) to identify machine learning models that can accurately predict the task performed and the quality of posture adopted by participants performing patient-handling tasks (using data from wearable sensors-IMUs-and force plates), and (2) to determine an optimal combination ofthose IMUs.\u003Cbr>Time Series Classification\u003Cbr>Time series classification (TSC) is a type of supervised machine learning classification problem where the data is sequentially ordered by time. It can be further categorized into univariate (TSC) and multivariate (MTSC) problems. Our data is multivariate time series data as it comprises multivariate forces, accelerations, and angular velocity\u003Cbr>measurements.\u003Cbr>Recently, researchers have made significant progress in machine learning techniques for multivariate time series classification. In [2], Fawaz et al developed a Convolutional Neural Network ensemble called InceptionTime that is highly accurate\u003Cbr>and scalable for large datasets. Similarly, Dempster et al [4] used a convolutional\u003Cbr>\u003Cbr>kernel based approach (ROCKET) to perform very fast and accurate classifications on\u003Cbr>time series data. We compared the performances ofthe following multivariate time series classifiers on our dataset: MiniRocket [5], MultiRocket [6], HIVE-COTE 2.0 [7], InceptionTime [2], and ResNet [3] .\u003C","cbCaignQXW4cB3BR","https://ap.wps.com/l/cbCaignQXW4cB3BR","pdf",739006,1,2,"English","en",105,"# Introduction\n## Time Series Classification\n# Methodology\n## IMU and force-plate setup\n## Model training and validation\n# Results","[{\"question\":\"Why are inertial measuring units (IMUs) used instead of optical marker systems?\",\"answer\":\"IMUs enable data collection in both laboratory and clinical environments and avoid marker occlusion during more complex patient-handling tasks.\"},{\"question\":\"What patient-handling tasks and posture categories were used in the study?\",\"answer\":\"Participants performed three tasks: standing a patient up from a wheelchair, rolling a patient onto their side, and sitting a patient up at a table. Posture quality was categorized as good vs poor, or good, neutral, vs poor.\"},{\"question\":\"Which model and sensor combination produced the best performance?\",\"answer\":\"The trunk and pelvis sensor combination achieved the highest scores across models. MiniRocket performed best, reaching about 98.1% accuracy and 97.8% precision while training in just over 2 minutes.\"}]","Patient-Handling Tasks and Posture Classification with Machine Learning - Poster | PDF",1785727984,5,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":28},"patient-handling-tasks-and-posture-classification-with-machine-learning-poster","",{"@graph":36,"@context":84},[37,53,67],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":21},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/healthcare/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/patient-handling-tasks-and-posture-classification-with-machine-learning-poster/120070/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why are inertial measuring units (IMUs) used instead of optical marker systems?","Question",{"text":74,"@type":75},"IMUs enable data collection in both laboratory and clinical environments and avoid marker occlusion during more complex patient-handling tasks.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What patient-handling tasks and posture categories were used in the study?",{"text":79,"@type":75},"Participants performed three tasks: standing a patient up from a wheelchair, rolling a patient onto their side, and sitting a patient up at a table. Posture quality was categorized as good vs poor, or good, neutral, vs poor.",{"name":81,"@type":72,"acceptedAnswer":82},"Which model and sensor combination produced the best performance?",{"text":83,"@type":75},"The trunk and pelvis sensor combination achieved the highest scores across models. MiniRocket performed best, reaching about 98.1% accuracy and 97.8% precision while training in just over 2 minutes.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,108,113,116,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":105,"show_sort_weight":106,"slug":107},"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":46,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":114,"slug":115},40,"healthcare",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},8,"Research & Report",30,"research-report",{"id":122,"doc_module":4,"doc_module_name":46,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":29,"slug":136},19,"General","general"]