[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122935-en":3,"doc-seo-122935-105":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":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},122935,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","Machine Learning and Feature Ranking for Impact Fall Detection Event Using Multisensor Data","Falls among older adults can cause severe injuries and long-term complications, so timely impact detection within a fall event is essential for effective assistance. This study addresses the problem by applying comprehensive preprocessing to the UP-FALL multisensor dataset to remove noise and improve data quality. A feature selection stage then identifies the most relevant sensor-derived attributes to boost machine learning performance and efficiency. Multiple models are evaluated for impact-moment detection using standard metrics, achieving high accuracy and demonstrating the value of multisensor data for safer fall detection systems.","Machine Learning and Feature Ranking for Impact Fall Detection Event Using Multisensor Data  \nTresor Y. Koffi CESI LINEACT Laboratory,  \nUR 7527  \nDijon, 21800, France [ytkoffi@cesi.fr](ytkoffi@cesi.fr)  \nYoussef Mourchid CESI LINEACT Laboratory,  \nUR 7527  \nDijon, 21800, France [ymourchid@cesi.fr](ymourchid@cesi.fr)  \nMohammed Hindawi CESI LINEACT Laboratory,  \nUR 7527  \nLyon, 69100, France [mhindawi@cesi.fr](mhindawi@cesi.fr)  \nYohan Dupuis CESI LINEACT Laboratory,  \nUR 7527  \nParis La Dfense, 92074, France [ydupuis@cesi.fr](ydupuis@cesi.fr)  \narXiv :2401 .05407v2 [ ee ss . SP] 25 Feb 2025  \nAbstract—Falls among individuals, especially the elderly population, can lead to serious injuries and complications. Detecting impact moments within a fall event is crucial for providing timely assistance and minimizing the negative consequences. In this work, we aim to address this challenge by applying thorough preprocessing techniques to the multisensor dataset, the goal is to eliminate noise and improve data quality. Furthermore, we employ a feature selection process to identify the most relevant features derived from the multisensor UP-FALL dataset, which in turn will enhance the performance and efficiency of machine learning models. We then evaluate the efficiency of various machine learning models in detecting the impact moment using the resulting data information from multiple sensors. Through extensive experimentation, we assess the accuracy of our approach using various evaluation metrics. Our results achieve high accuracy rates in impact detection, showcasing the power of leveraging multisensor data for fall detection tasks. This highlights the potential of our approach to enhance fall detection systems and improve the overall safety and well-being of individuals at risk of falls.  \nIndex Terms—Impact detection, Machine Learning, Fall detection, Accelerometers, Multisensor data, UP-Fall data  \nI. INTRODUCTION  \nAccording to the World Health Organization report, falls affect 32 percent of older adults annually, making it a leading cause of mortality among this demographic [1] . The elderly population is particularly vulnerable to the detrimental effects of falls, which can result in fractures and cognitive impairments [2] . Recent research efforts have focused on fall detection to predict and prevent such incidents [3] . The primary objective of these studies is to minimize fall-related injuries and provide timely assistance to individuals at risk. An important advancement in this field is the implementation of pre-impact fall detection systems [4] . These systems identify falls at an early stage before the impact occurs.  \nAdvancements in computer vision, driven by graphs, statistical techniques, and deep learning, have greatly enhanced visual data processing, which is particularly beneficial for improving fall detection accuracy [5]–[8] . To detect falls across different stages, including pre-impact, and post-impact, accelerometerbased fall detection systems have gained prominence. However, while identifying fall at the early stage and post-stage can help to rescue people, it is crucial to identify the impact point, in order to avoid false alert and accurately provide  \nassistance to people who really fall. Furthermore, it has been observed that the current datasets available for fall detection lack proper preprocessing, leading to inaccurate detection of falls and impacts in real-life scenarios. Therefore, depending on raw data from these datasets for the development of fall detection systems can lead to an increased occurrence of false positives or false negatives, as illustrated in Fig. 1(b) . This figure demonstrates the occurrence of a false positive, where the system incorrectly identifies an impact where it has not actually occurred. This can cause false alarms and that reduces trust in the detection system. False negative cases are more dangerous in this context, where the person has actually fallen but the system doe","cbCaitNetKUWvWJ2","https://ap.wps.com/l/cbCaitNetKUWvWJ2","pdf",4651163,1,7,"English","en",105,"# Introduction\n## Motivation and background\n## Contributions and paper organization\n# Related Work\n## Fall detection and impact detection review\n# Methodology\n## Dataset description and preprocessing\n## Feature selection\n## Machine learning models\n# Results and Evaluation","[{\"question\":\"Why is impact detection within a fall event important?\",\"answer\":\"Impact detection enables timely assistance and reduces negative outcomes. It also helps avoid false alerts by pinpointing when contact with the ground actually occurs.\"},{\"question\":\"How does the study improve the multisensor dataset before training models?\",\"answer\":\"It uses thorough preprocessing to eliminate noise and enhance data quality, aiming to make subsequent learning more robust and accurate.\"},{\"question\":\"What is the role of feature selection in this work?\",\"answer\":\"Feature selection ranks and keeps the most relevant multisensor features, reducing dimensionality while emphasizing attributes that contribute most to accurate impact detection.\"}]","Machine Learning and Feature Ranking for Impact Fall Detection Event Using Multisensor Data | PDF",1785813767,18,{"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},"machine-learning-and-feature-ranking-for-impact-fall-detection-event-using-multisensor-data","",{"@graph":36,"@context":85},[37,54,68],{"@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":53},"https://docshare.wps.com/document/machine-learning-and-feature-ranking-for-impact-fall-detection-event-using-multisensor-data/122935/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is impact detection within a fall event important?","Question",{"text":75,"@type":76},"Impact detection enables timely assistance and reduces negative outcomes. It also helps avoid false alerts by pinpointing when contact with the ground actually occurs.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the study improve the multisensor dataset before training models?",{"text":80,"@type":76},"It uses thorough preprocessing to eliminate noise and enhance data quality, aiming to make subsequent learning more robust and accurate.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the role of feature selection in this work?",{"text":84,"@type":76},"Feature selection ranks and keeps the most relevant multisensor features, reducing dimensionality while emphasizing attributes that contribute most to accurate impact detection.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"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":53,"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":21,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]