[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124249-en":3,"doc-seo-124249-105":30,"detail-sidebar-cat-0-en-105":95},{"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},124249,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Freezing of gait detection - The effect of sensor type, position, activities, datasets, and machine learning model","Freezing of gait (FoG) is a complex, frequent, and disabling motor symptom in Parkinson’s disease (PD), and wearable technology is positioned as a way to deliver objective, quantitative, and continuous monitoring. The study develops a robust FoG detection algorithm for a simple, unobtrusive wearable sensor system to enable reliable unsupervised home assessment. Twenty-two PD subjects with FoG performed multiple tasks using inertial sensors, and feature-driven and data-driven machine learning models were trained and validated. External datasets covering 545 FoG episodes tested robustness, achieving 88–95% correct detection, while turning remained a major challenge.","POLITECNICO DI TORINO  \nRepository ISTITUZIONALE  \nFreezing of gait detection: The effect of sensor type, position, activities, datasets, and machine learning model  \nOriginal  \nFreezing of gait detection: The effect of sensor type, position, activities, datasets, and machine learning model / Borzì, Luigi; Demrozi, Florenc; Bacchin, Ruggero Angelo; Turetta, Cristian; Sigcha, Luis; Rinaldi, Domiziana; Fazzina, Giuliana; Balestro, Giulio; Picelli, Alessandro; Pravadelli, Graziano; Olmo, Gabriella; Tamburin, Stefano; Lopiano, Leonardo; Artusi, Carlo Alberto. -In: JOURNAL OF PARKINSON'S DISEASE. -ISSN 1877-7171. -ELETTRONICO. -15:1(2025), pp. 163-181. [10 . 1177/1877718x241302766]  \nAvailability:  \nThis version is available at: 11583/2998330 since: 2025-05-15T09:56:23Z  \nPublisher:  \nSage  \nPublished  \nDOI:10.1177/1877718x241302766  \nTerms of use:  \nThis article is made available under terms and conditions as specified in the corresponding bibliographic description in the repository  \nPublisher copyright  \n(Article begins on next page)  \nResearch Article  \nFreezing of gait detection: The effect of sensor type, position, activities, datasets, and machine learning model  \nJournal of Parkinson’s Disease 2025, Vol. 15(1) 163–181 © The Author(s) 2025  \nArticle reuse guidelines:  \n[sagepub.com/journals-permissions](sagepub.com/journals-permissions)[ ](sagepub.com/journals-permissions)DOI: 10.1177/1877718X241302766 [journals.sagepub.com/home/pkn](journals.sagepub.com/home/pkn)  \nLuigi Borzì 1 , Florenc Demrozi2 , Ruggero Angelo Bacchin3,4  ,  \nCristian Turetta5 , Luis Sigcha6, Domiziana Rinaldi7,8, Giuliana Fazzina9,10,  \nGiulio Balestro3 , Alessandro Picelli3 , Graziano Pravadelli5 , Gabriella Olmo 1  , Stefano Tamburin3 , Leonardo Lopiano9,10 and Carlo Alberto Artusi9,10   \nAbstract  \nBackground: Freezing of gait (FoG) is a complex, frequent, and disabling motor symptom of Parkinson’s disease (PD). Wearable technology has the potential to improve FoG assessment by providing objective, quantitative, and continuous monitoring.  \nObjective: This study aims to develop a robust FoG detection algorithm that can be embedded in a simple and unobtrusive wearable sensor system and can lead to a reliable unsupervised home assessment.  \nMethods: Twenty-two subjects with PD and FoG were enrolled, equipped with four inertial modules on the ankles, back, and wrist, and asked to perform different tasks. Feature-driven and data-driven machine learning approaches were implemented, optimized, and evaluated. Further testing was conducted on two external datasets including a total of 545 FoG episodes.  \nResults: Sixteen subjects experienced FoG, providing a total number of 101 FoG events. Results demonstrated that a single sensor on the ankle, with an adequate algorithm of data analysis based on machine learning, can provide a non-invasive approach for accurate FoG detection. The model proved robust on the independent datasets, with 88–95% FoG episodes correctly detected. Interestingly, while FoG can be easily discriminated from walking, static positions, and postural transitions, turning represents a significant challenge. The high number of false alarms still represents the main limitation of the FoG recognition algorithms.  \nConclusions: The collected dataset includes data from different sensors at different body positions. This, together with detailed labeling of tasks, activities, FoG episodes and their severity, can be a significant contribution to research on automatic FoG detection and characterization.  \nKeywords  \nParkinson’s disease, freezing of gait, wearable sensor, machine learning, deep learning, detection  \nReceived: 31 May 2024; accepted: 2 November 2024  \n1 Department of Control and Computer Engineering, Politecnico di Torino, Turin, Italy  \n2Department of Electrical Engineering and Computer Science, University of Stavanger, Stavanger, Norway  \n3Department of Neurosciences, Biomedicine and Movement Sciences, University of Verona, Verona, It","cbCaid8N0dyYHLcV","https://ap.wps.com/l/cbCaid8N0dyYHLcV","pdf",3155129,1,20,"English","en",105,"# Introduction\n## Background and challenges in FoG assessment\n# Methods and study objective\n## Wearable sensing setup and tasks\n## Machine learning approaches and datasets\n# Results\n## Sensor selection and detection performance\n## Task-specific effects and limitations\n# Conclusions","[{\"question\":\"What problem does the study address in Parkinson’s disease?\",\"answer\":\"It addresses freezing of gait (FoG), a disabling and hard-to-assess motor symptom where episodic behavior, variable triggers, and reporting bias complicate reliable monitoring.\"},{\"question\":\"How is the FoG detection algorithm developed and evaluated?\",\"answer\":\"The study trains machine learning approaches using data from wearable inertial modules placed on the ankles, back, and wrist, and evaluates performance on external datasets totaling 545 FoG episodes.\"},{\"question\":\"Which sensor configuration provides the best practical detection outcome?\",\"answer\":\"A single ankle sensor combined with an adequate machine-learning data analysis algorithm enables accurate, non-invasive FoG detection, with 88–95% correctly detected episodes on independent datasets.\"},{\"question\":\"What is the main limitation of current FoG recognition performance?\",\"answer\":\"False alarms remain the key limitation, and turning is highlighted as a significant challenge despite discrimination from walking and other static or transitional conditions.\"}]","Freezing of gait detection - The effect of sensor type, position, activities, datasets, and machine learning model | PDF",1785821223,50,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"freezing-of-gait-detection-the-effect-of-sensor-type-position-activities-datasets-and-machine-learning-model","",{"@graph":36,"@context":89},[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/freezing-of-gait-detection-the-effect-of-sensor-type-position-activities-datasets-and-machine-learning-model/124249/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address in Parkinson’s disease?","Question",{"text":75,"@type":76},"It addresses freezing of gait (FoG), a disabling and hard-to-assess motor symptom where episodic behavior, variable triggers, and reporting bias complicate reliable monitoring.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the FoG detection algorithm developed and evaluated?",{"text":80,"@type":76},"The study trains machine learning approaches using data from wearable inertial modules placed on the ankles, back, and wrist, and evaluates performance on external datasets totaling 545 FoG episodes.",{"name":82,"@type":73,"acceptedAnswer":83},"Which sensor configuration provides the best practical detection outcome?",{"text":84,"@type":76},"A single ankle sensor combined with an adequate machine-learning data analysis algorithm enables accurate, non-invasive FoG detection, with 88–95% correctly detected episodes on independent datasets.",{"name":86,"@type":73,"acceptedAnswer":87},"What is the main limitation of current FoG recognition performance?",{"text":88,"@type":76},"False alarms remain the key limitation, and turning is highlighted as a significant challenge despite discrimination from walking and other static or transitional conditions.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,118,123,126,130,133,137],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":29,"slug":117},6,"Technology","technology",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":124,"slug":125},30,"research-report",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":21,"slug":129},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":21,"slug":132},"World Cup","world-cup",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":134,"slug":136},10,"Lifestyle","lifestyle",{"id":138,"doc_module":4,"doc_module_name":46,"category_name":139,"show_sort_weight":110,"slug":140},19,"General","general"]