[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-290769-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-290769-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","explainability-in-multivariate-time-series-classification-machine-learning-models-poster","EXPLAINABILITY IN MULTIVARIATE TIME SERIES CLASSIFICATION MACHINE LEARNING MODELS - Poster","","Poster presents a study classifying nurse patient-handling postures as good, poor, or neutral using multivariate time series data. Research motivates the work by linking musculoskeletal injury risk for nurses to physiological changes observed in astronauts after spaceflight. Explainability is achieved with an XCM model implemented via Gradient-weighted Class Activation Mapping (Grad-CAM), producing task-specific heatmaps that reveal which features most strongly drive classification decisions. Future work expands testing to larger nursing cohorts and professional nurses.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/explainability-in-multivariate-time-series-classification-machine-learning-models-poster/290769/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/explainability-in-multivariate-time-series-classification-machine-learning-models-poster/290769.png","ImageObject",300,407,{"name":42,"@type":43},"Liam","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-18","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the poster address?","Question",{"text":63,"@type":64},"The poster investigates how to classify posture adopted by nurses during patient handling tasks and use explainability to reduce early-onset musculoskeletal injury risk.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How is explainability implemented in the study?",{"text":68,"@type":64},"Explainability is generated using an explainable ML model called XCM, implemented with Gradient-weighted Class Activation Mapping (Grad-CAM) to produce color-coded heatmaps.",{"name":70,"@type":61,"acceptedAnswer":71},"What do the Grad-CAM heatmaps represent?",{"text":72,"@type":64},"Each task receives a heatmap showing the relative importance of input features for the model’s classification decision, with more intense red indicating a more positive contribution.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},290769,1789642533,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":26,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":80,"read_time":97,"preview_page_count":4},8796095461564,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Hope College  \n23rd Annual A.Paul and Carol C.SchaapCelebration of Undergraduate Research andThe A.Paul and Carol C.Schaap Celebration ofCreative Activity(2024)                                 Undergraduate Research and Creative Activity  \n4-12-2024  \nExplainability in Multivariate Time Series Classification MachineLearning Models  \nEmanuel Sanchez  \nHope College  \nGiovanni Battaglia  \nHope College  \nFollow this and additional works at:https://digitalcommons.hope.edu/curca_23  \nPart of the Computer Sciences Commons  \nRecommended Citation  \nRepository citation:Sanchez,Emanuel and Battaglia,Giovanni,\"Explainability in Multivariate Time SeriesClassification Machine Learning Models\"(2024).23rd AnnualA.Paul and Carol C.Schaap Celebration ofUndergraduate Research and Creative Activity(2024).Paper74.https://digitalcommons.hope.edu/curca_23/74April 12,2024.Copyright ◎2024 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 ofUndergraduate Research and Creative Activity at Hope College Digital Commons.It has been accepted for inclusionin 23rd Annual A.Paul and Carol C.Schaap Celebration of Undergraduate Research and Creative Activity (2024)byan authorized administrator of Hope College Digital Commons.For more information,please contactdigitalcommons@hope.edu,barneycj@hope.edu.  \n# EXPLAINABILITY IN MULTIVARIATE TIME SERIESCLASSIFICATION MACHINE LEARNING MODELS\n\nHope  \nFor more information,contact:Dr.O.Olagbemi  \n141 East 12th Street,Holland,MIolagbemi@hope.edu  \nEmanuel Sanchez,Giovani Battaglia  \nC ○LLE G E  \n(with Dr.Brooke Odle and Dr.Omofolakunmi Olagbemi-Advisors)  \nHope College,Holland,Michigan  \n·Two Roll:Roll a patient to their left side,placing a sheet under them,then rolling themto their right side  \nthe body to focus on.Future work will consist of applying our findings to a largercohort of nursing students as well as expanding testing to include professional nursesin the workforce and lay caregivers,in hopes of developing more sophisticated MLalgorithms to estimate loads applied to the low back while tasks are performed.  \n# Introduction\n\n·Wheelchair:Picking a patient up out of a wheelchair  \nStudies show that while on NASA missions in outer space,the bodies ofastronauts undergo significant changes resulting in weight,bone and muscleloss,which result in them being more susceptible to low back pain post-flight[3],[4].A parallel can be drawn between nurses and astronauts.A related studybeing conducted by the Pls seeks to classify posture adopted by nurses whileperforming patient handling tasks as good,poor,or,with some specific tasks,neutral.It seeks to investigate the mechanics of task performance to betterunderstand the cause of early onset of musculoskeletal injuries in nursingprofessionals.The purpose of our research therefore is to use explainability toidentify the features of the data that are most critical in the classificationprocess,and apply the knowledge gained in the formulation of guidelines thatwill help minimize the risk of musculoskeletal injuries sustained by nurses andastronauts.  \nThe data was then downloaded the repetitions were then separated into their own files,and organized by tasks task folders,separated by task file formatted needed.  \n\n| Task:   | Leg Lift   | Roll   | Sit Up   | Slide   | Two Roll   | Wheelchair   |\n| --- | --- | --- | --- | --- | --- | --- |\n| Features:   | Hips  \u003Cbr>-Pelvis  \u003Cbr>-Lumbar   | -Arms  \u003Cbr>Hips  \u003Cbr>-Subtalar  \u003Cbr>-Lumbar  \u003Cbr>-Knees   | -Left Subtalar  \u003Cbr>Angle  \u003Cbr>-Left MTP Angle  \u003Cbr>-Left Hip  \u003Cbr>-Lumbar  \u003Cbr>-Pelvis  \u003Cbr>-Weight   | -Hips  \u003Cbr>-Pelvis  \u003Cbr>-Lumbar  \u003Cbr>-Weight   | -Hips  \u003Cbr>-Lumbar  \u003Cbr>-MTP  \u003Cbr>Angle  \u003Cbr>-Subtalar  \u003Cbr>Angle   | -Hips  \u003Cbr>-Knees  \u003Cbr>-Weight  \u003Cbr>-Lumbar  \u003Cbr>-Pelvis   |\n\nThe 6 different pairs of  \ntraining and testing  \ndatasets were utilized  \nwith XCM's implementatt  \nion of Grad-CAM,in  \nTabel 1:The table above list off the important f","cbCaifD2hGslORgv","https://ap.wps.com/l/cbCaifD2hGslORgv","pdf",404314,"English","# Introduction\n## Features used when classifying different posture\n# Explainability\n## Results\n# Methods\n## Data formatting and XCM inputs\n# References","[{\"question\":\"What problem does the poster address?\",\"answer\":\"The poster investigates how to classify posture adopted by nurses during patient handling tasks and use explainability to reduce early-onset musculoskeletal injury risk.\"},{\"question\":\"How is explainability implemented in the study?\",\"answer\":\"Explainability is generated using an explainable ML model called XCM, implemented with Gradient-weighted Class Activation Mapping (Grad-CAM) to produce color-coded heatmaps.\"},{\"question\":\"What do the Grad-CAM heatmaps represent?\",\"answer\":\"Each task receives a heatmap showing the relative importance of input features for the model’s classification decision, with more intense red indicating a more positive contribution.\"}]","EXPLAINABILITY IN MULTIVARIATE TIME SERIES CLASSIFICATION MACHINE LEARNING MODELS - Poster | PDF"]