[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122815-en":3,"doc-seo-122815-105":29,"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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},122815,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",7,"Healthcare","Machine Learning Based Approaches for Cough Detection from Acceleration Signal","Machine learning based methods are presented to detect cough using three-dimensional acceleration signals collected non-invasively with the Hexoskin device. Two approaches are evaluated: a conventional supervised classifier using XGBoost and a deep learning model using a one-dimensional CNN architecture. The models distinguish acceleration patterns from coughing versus other activities such as throat clearing, talking, laughing, and movements in different directions with high accuracy. The study supports accelerometer-derived cough monitoring as a user-independent tool.","Machine learning based approaches for cough detection from  \nacceleration signal  \nInes Belhaj Messaoud2 , Elyes Ben Cheikh 1 , Assaad Chiboub 1 , Karim Loulou3 , Youssef Ouakrim3 , Sofia  \nBen Jebara 1 , Neila Mezghani3  \n1Université de Carthage, École Supérieure des communications de Tunis, Tunis, Tunisia  \n2Université Tunis El Manar, Ecole Nationale d’Ingénieurs de Tunis,Tunis, Tunisia  \n3Laboratoire de recherche en Imagerie et orthopedie (LIO), CRCHUM, TELUQ university, Montreal, Canada  \n1Laboratoire de recherche COSIM, Sup’Com, Tunis, Tunisia  \ne-mail: [inesbelhajj@gmail.com](inesbelhajj@gmail.com), [elyes.bencheikh@supcom.tn](elyes.bencheikh@supcom.tn), [assaad.chiboub@supcom.tn](assaad.chiboub@supcom.tn), [karim.loulou@outlook.com](karim.loulou@outlook.com),  \noua.youssef@gmail.com, sofia.benjebara@supcom.tn, neila.mezghani@teluq.ca  \nAbstract –  \nThe main goal ofthis research is to develop a a machine learning based method in order to detect cough from acceleration signals. In this study, two different methods are proposed: a conventional one that uses Xgboost asa classifier and a deep learning which uses CNN-1Das an architecture. We found that these models were able to distinguish between acceleration signals caused by coughing and acceleration signals caused by other activities such as clearing throat, talking, laughing and movements in different directions with high accuracy. This study affirms that cough monitoring based on accelerometer measurements generated by the Hexoskin device is possible, making it a new user-independent tool of cough detection.  \nKeywords – Cough detection, connected textile sensors, acceleration signals, supervised classification, machine learning, deep learning.  \nI. Introduction  \nCough can be described as a sudden and often repetitive expulsion of air with a strong expiratory effort. It isan important indicator of several health problems such as upper and lower respiratory tract infections (common cold, influenza, bronchitis bronchiolitis), asthma, chronic obstructive pulmonary, pulmonary edema, pneumonia, tuberculosis,... and recently COVID-19 [1] .  \nCough detection can be useful in a variety of purposes. Some potential applications include monitoring respiratory health (alert to infection presence of a chronic respiratory condition for instance), early detection of respiratory infections (useful in situations where it is not possible or desirable to perform more invasive diagnostic tests), and remote monitoring (using smart watches or fitness trackers, allowing individuals to monitor their own respiratory health on a continuous basis), surveillance in public settings (identifying individuals who may be infected with a respiratory illness and alert them to the need for further testing or isolation), improving public health (detection and tracking the spread of respiratory infections) ...  \nThere are several ways to detect coughs when using wearable devices and the Internet of Things [2] . Coughs can  \nbe detected using either audio signals or physiological signals (such as heart activity, blood pressure, airflow, or respiratory inhalation and expiration, movement signals,...) . In this work, we are interested with acceleration signals that detect the sudden and forceful movement associated with a cough. Infact, monitoring cough based on signals from an accelerometer placed on a human body is less intrusive and it was proven tobe an efficient way of detection [3] . It was also proven that the accelerometer could be used with other physiological sensors such as ECG and respiration sensors [4] .  \nAutomatic cough detection can be carried using machine learning. It involves training a machine learning model on a dataset which will be able to predict whether a measured information contains cough or not. Either conventional machine learning or deep learning can be used. Conventional machine leaning algorithms (such as decision trees, random forests, and support vector machines) can learn p","cbCaikOC9BJ5MIsa","https://ap.wps.com/l/cbCaikOC9BJ5MIsa","pdf",572388,1,"English","en",105,"# Introduction\n## Background and importance of cough detection\n## Detection methods with wearable devices and IoT\n## Focus on accelerometer signals\n## Machine learning approaches for automatic cough detection\n# Related work\n## Deep learning using bedside accelerometer measurements\n## Feature selection and SVM-based differentiation of cough vs other actions\n# Proposed approach (XGBoost and CNN)","[{\"question\":\"What is the main goal of the research?\",\"answer\":\"Develop a machine learning based method to detect cough from acceleration signals collected from the body.\"},{\"question\":\"Which two detection models are proposed?\",\"answer\":\"A conventional XGBoost classifier and a deep learning model based on a 1D CNN architecture.\"},{\"question\":\"How does the method collect data and what device is used?\",\"answer\":\"Acceleration is measured non-invasively with the Hexoskin device, capturing three-dimensional signals along X, Y, and Z axes.\"}]","Machine Learning Based Approaches for Cough Detection from Acceleration Signal | PDF",1785813058,18,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"machine-learning-based-approaches-for-cough-detection-from-acceleration-signal","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/healthcare/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/machine-learning-based-approaches-for-cough-detection-from-acceleration-signal/122815/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-04",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},"What is the main goal of the research?","Question",{"text":74,"@type":75},"Develop a machine learning based method to detect cough from acceleration signals collected from the body.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Which two detection models are proposed?",{"text":79,"@type":75},"A conventional XGBoost classifier and a deep learning model based on a 1D CNN architecture.",{"name":81,"@type":72,"acceptedAnswer":82},"How does the method collect data and what device is used?",{"text":83,"@type":75},"Acceleration is measured non-invasively with the Hexoskin device, capturing three-dimensional signals along X, Y, and Z axes.","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":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,117,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":115,"slug":116},40,"healthcare",{"id":118,"doc_module":4,"doc_module_name":45,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]