[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127504-en":3,"doc-seo-127504-105":29,"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":20,"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},127504,13056712833777,"Logic","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Comparison of Machine Learning Algorithms for Human Activity Recognition - Machine Learning Classifiers Performance Study","Human activity recognition (HAR) enables automatic identification of daily-life activities to support effective management of age-related health conditions and movement disorders. The study evaluates eight classical and ensemble-learning machine learning classifiers under two HAR setups: subject-specific and population-based. Inertial measurement unit signals from 10 healthy participants cover static, dynamic, and transitional activities. Mean classification accuracy assesses performance, showing superior results for ES, RF, and SVM in subject-specific mode and more uniform outcomes in population-based settings.","# Comparison of Machine Learning Algorithms forHuman Activity Recognition\n\nHassan AshrafDa,Olivier BrülsD,Cédric SchwartzD\"and Mohamed BoutaayamouDLaboratory of Movement Analysis(LAM-Motion Lab),University of Liege,Liege,Belgium  \nKeywords:Human Activity Recognition,Daily-Life Activity Classification,Machine Learning,Pattern Recognition,Wearable Sensors,Inertial Sensors,Accelerometer,Gyroscope,IMU Signals.  \nAbstract:Human activity recognition(HAR)is utilized to automatically identify the daily-life activities of people forthe effective management of age-related health conditions.Classical machine learning(ML)algorithms areused to design HAR systems,in a subject-specific or population-based configuration depending on theapplication.In this study,the performance of 8 classical and ensemble-learning-based ML classifiers has beenstudied for both HAR configurations.Inertial measurement unit(IMU)signals from 10 healthy participants,corresponding to various static,dynamic,and transitional daily-life activities,were acquired.Random forest(RF),ensemble adaptive boosting(EAB),ensemble subspace(ES),decision tree(DT),k-nearest neighbors(KNN),linear discriminant analysis (LDA),support vector machine (SVM),and artificial neural network(ANN)were used to classify these activities.The performance of the classifiers was measured in terms ofmean classification accuracy(MCA).The results showed that,for a subject-specific HAR system,ES(97.78%)has achieved the highest MCA followed by RF(96.61%)and SVM(96.11%)while outperformingthe DT,KNN,and LDA(P-value\u003C0.05).For a population-based HAR system,SVM(95.18%)achieved thehighest MCA,however,no significant difference has been observed among the MCA of all the investigatedclassifiers(P-value>0.05).Also,the class-wise comparison reveals that SVM outperformed the otherinvestigated classifiers in tems of MCAs for each of the distinct activities.Based on the HAR configurationincorporating diverse static,dynamic,and transitional daily-life activities,the findings may be used to developa customized HAR system for the effective management of movement disorders.  \nactivities.Smart healthcare systems not only allowolder people to live autonomously,but they may alsooffer more sustainable healthcare solutions byreducing the strain placed on the entire health systemby the aged and dependent persons.  \n## 1 INTRODUCTION\n\nAccording to the International Diabetes Foundation(IDF),the global diabetes prevalence in adults aged20 to 79 years old is expected to be 536.6 million in2021,rising to 783.2 million in 2045(Atlas,2015).Similarly,more than 10 million people worldwide areliving with Parkinson's disease(PD)and theincidence of PD increases with age(Tysnes &Storstein,2017).Such an aging population needscare.Smart healthcare systems seem to be a possibleanswer to the rising aging population dilemma.Theycan provide smart health services to meet the needs ofthis rising population by monitoring and analysingany critical health state of the elderly in their daily  \nHuman activity recognition(HAR)is a prominentresearch topic that can give a solution to such achallenge by playing an important role in healthcare,particularly in medical diagnosis and fitnessmonitoring.Accurate assessment of physical activityis therefore critical in establishing interventionmethods,as it provides rich contextual informationfrom which more important information may beinferred.HAR may also be used for people with amental ailment or disease,such as Parkinson's  \n162  \ndisease,to monitor their actions regularly and noticeany abnormalities(Church,2021).  \nMachine learning(ML)or pattern recognitionmethods are primarily used to process signals for thedevelopment of HAR applications.Irrespective of thechosen ML method,the data is processed in twostages,i.e.,training the ML model on the pre-recorded dataset and then testing the trained model onunseen data.The HAR signal processing with MLmethods involves data acquisition,signal pre-processing,feature extrac","cbCaifk5mXkGaHhE","https://ap.wps.com/l/cbCaifk5mXkGaHhE","pdf",403395,1,"English","en",105,"# Keywords\n## Study Design and Data\n## Algorithms and Evaluation Metric\n## Results: Subject-Specific vs Population-Based\n## Implications for Customized HAR Systems","[{\"question\":\"What data source and signals were used for human activity recognition?\",\"answer\":\"The study used inertial measurement unit (IMU) signals from 10 healthy participants, derived from static, dynamic, and transitional daily-life activities.\"},{\"question\":\"Which classifiers were compared in the study?\",\"answer\":\"Random forest, ensemble adaptive boosting, ensemble subspace, decision tree, k-nearest neighbors, linear discriminant analysis, support vector machine, and artificial neural network were evaluated.\"},{\"question\":\"How did model performance differ between subject-specific and population-based HAR?\",\"answer\":\"In subject-specific HAR, ensemble subspace achieved the highest mean classification accuracy, followed by random forest and SVM. In population-based HAR, SVM had the highest mean classification accuracy, but no significant differences were found among the classifiers.\"}]","Comparison of Machine Learning Algorithms for Human Activity Recognition - Machine Learning Classifiers Performance Study | PDF",1785939508,20,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":27},"comparison-of-machine-learning-algorithms-for-human-activity-recognition-machine-learning-classifiers-performance-study","",{"@graph":35,"@context":85},[36,53,68],{"@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/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/comparison-of-machine-learning-algorithms-for-human-activity-recognition-machine-learning-classifiers-performance-study/127504/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data source and signals were used for human activity recognition?","Question",{"text":75,"@type":76},"The study used inertial measurement unit (IMU) signals from 10 healthy participants, derived from static, dynamic, and transitional daily-life activities.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which classifiers were compared in the study?",{"text":80,"@type":76},"Random forest, ensemble adaptive boosting, ensemble subspace, decision tree, k-nearest neighbors, linear discriminant analysis, support vector machine, and artificial neural network were evaluated.",{"name":82,"@type":73,"acceptedAnswer":83},"How did model performance differ between subject-specific and population-based HAR?",{"text":84,"@type":76},"In subject-specific HAR, ensemble subspace achieved the highest mean classification accuracy, followed by random forest and SVM. In population-based HAR, SVM had the highest mean classification accuracy, but no significant differences were found among the classifiers.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":28,"slug":126},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":28,"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":106,"slug":137},19,"General","general"]