[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-125893-105":59,"doc-detail-125893-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","stress-detection-using-multimodal-physiological-signals-with-machine-learning-from-wearable-devices-results-gmr-118","Stress Detection using Multimodal Physiological Signals with Machine Learning from Wearable Devices - Results - GMR-118","","Stress is a common concern that can trigger serious health problems including cardiovascular diseases, hypertension, depression, and higher infection susceptibility. Physiological signals such as blood volume pulse, temperature, and electrodermal activity change under stress, providing measurable indicators for early detection. Using the publicly available WESAD dataset collected from 15 subjects, this work applies logistic regression, decision tree, random forest, and stacking ensemble learning to classify four mental states and evaluates personalized versus generalized models, achieving accuracies up to 99% and 91%.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/stress-detection-using-multimodal-physiological-signals-with-machine-learning-from-wearable-devices-results-gmr-118/125893/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/stress-detection-using-multimodal-physiological-signals-with-machine-learning-from-wearable-devices-results-gmr-118/125893.png","ImageObject",300,407,{"name":92,"@type":93},"Maeve","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-22","2026-08-05",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",13,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What physiological signals are used to detect stress in this study?","Question",{"text":113,"@type":114},"The approach uses multimodal physiological measurements such as blood volume pulse, temperature, and electrodermal activity, along with additional signals included in the WESAD dataset. These signals reflect changes caused by the stress response.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How are personalized and generalized models different in this paper?",{"text":118,"@type":114},"Personalized models train using individual subject data, while generalized models combine data across all 15 subjects to learn one model for all participants.",{"name":120,"@type":111,"acceptedAnswer":121},"Which machine learning methods are evaluated and what performance is reported?",{"text":122,"@type":114},"The study evaluates logistic regression, decision tree, random forest, and stacking ensemble learning. Reported accuracy reaches up to 99% for personalized data and about 91% for the generalized setup, with ensemble learning performing best among models.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},125893,1785901878,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":8,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":130,"read_time":81},2336474466712,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Title: Stress Detection using Multimodal Physiological Signals with Machine  \nLearning from Wearable Devices  \nResults  \nAbstract  \nGMR-118  \nStress is one of the most prevalent concerns among individuals. Stress can cause severe health issues such as cardiovascular diseases, hypertension, depression, etc. When a person gets stressed, physiological values like blood volume pulse, temperature, and electrodermal activity signals get affected. Machine learning techniques can be utilized to detect stress by using these physiological signals. In this paper, we used a WESAD dataset which has physiological data collected from 15 different subjects to identify the state of mind. In this study, we implemented Logistic Regression, Decision Tree, Random Forest, and Stacking Ensemble Learning. We developed both personalized models, utilizing individual subject data, and generalized models, amalgamating all subject data. We achieved accuracies reaching up to 99% and 91% for individual subject data and combined data, respectively.  \nIn the healthcare domain, one of the most common complaints of patients is‘’stress”. Stress can have significant impacts on the human body. For instance, prolonged mental stress can cause serious health issues such as hypertension, cardiovascular diseases, increased susceptibility to infections, and depression. Early detection of stress can help to prevent these health issues. When a person is under stress, the sympathetic nervous system (SNS) of the person triggers a physiological response that leads to a change in the heart rate, and muscle tension. Hence, understanding physiological values can be an effective way to detect the stress condition.  \nTo understand the effect of physiological signals on different states of mind, we implemented a stress detection method by using the publicly available\"Wearable Stress and Affect Detection\"(WESAD) dataset. WESAD dataset has physiological data and motion data collected from 15 people. This data is collected from two different devices, the wrist-worn device and the chest-worn  \nResults  \n1 ) Personalized Model:  \nBelow are the results of all machine learning models such as Logistic Regression, Decision Tree, Random Forest and SEL on individual subject and comparison of proposed model with the baseline model.  \nTable I : Model Performance of All Models  \nComparison of our Proposed work with the baseline model:  \n2) Generalized Model:  \nResults of ML models on combined data:  \ni) Logistic Regression  \nii) Decision Tree  \niii) Random Forest  \niv) Ensemble Learning Table II: Accuracy score of  \nDifferent Models  \nIn this research paper, we successfully implemented four class classification tasks on the data collected from the wrist-worn sensor. We predicted the four states of mind namely baseline, stress, amusement, and meditation. To achieve this task, we used classification machine learning algorithms namely LR, DT, RF, and SEL technique. In this paper, we successfully implemented a generalized as well as personalized machine learning model to predict the state of mind. In all three models, LR showed the least accuracy while RF gave the best accuracy ranging from 87% to 99% . While comparing all three ML models and the SEL technique, SEL showed the highest accuracy among all models. In both  \nConclusions  \nIntroduction  \nSUBJECT  \nS2  \nLR  \n85.99  \nDT  \n94.45  \nRF  \n97.04  \nSEL  \n97.99  \n\n| S3 | 82.47 | 95.32 | 97.50 | 99.03 |\n| --- | --- | --- | --- | --- |\n| S4 | 66.16 | 90.85 | 91.73 | 92.36 |\n| S5 | 88.50 | 98.17 | 98.28 | 99.59 |\n| S6 | 93.60 | 87.09 | 94.95 | 99.86 |\n| S7 | 77.12 | 94.70 | 95.87 | 97.62 |\n| S8 | 98.79 | 98.24 | 99.02 | 99.21 |\n| S9 | 98.32 | 97.77 | 98.10 | 98.64 |\n| S10 | 94.00 | 93.53 | 96.02 | 97.23 |\n| S11 | 89.10 | 91.48 | 94.86 | 98.16 |\n| S13 | 80.51 | 86.81 | 89.32 | 93.64 |\n| S14 | 85.75 | 99.29 | 99.38 | 99.55 |\n| S15 | 99.49 | 95.22 | 97.73 | 99.56 |\n| S16 | 83.32 | 97.51 | 99.22 | 99.45 |\n| S17 | 79.23 | 86.96 | 87.83 | 86.75 |\n\n| MODEL","cbCaic23BaW5hjby","https://ap.wps.com/l/cbCaic23BaW5hjby","pdf",1062787,"English","# Introduction\n## Physiological basis of stress detection\n## WESAD dataset and study setup\n# Materials and Methods\n## Personalized vs generalized modeling\n## Machine learning algorithms (LR, DT, RF, SEL)\n# Results\n## Personalized model performance\n## Generalized model performance on combined data\n# Conclusions\n# Acknowledgments\n# Contact information","[{\"question\":\"What physiological signals are used to detect stress in this study?\",\"answer\":\"The approach uses multimodal physiological measurements such as blood volume pulse, temperature, and electrodermal activity, along with additional signals included in the WESAD dataset. These signals reflect changes caused by the stress response.\"},{\"question\":\"How are personalized and generalized models different in this paper?\",\"answer\":\"Personalized models train using individual subject data, while generalized models combine data across all 15 subjects to learn one model for all participants.\"},{\"question\":\"Which machine learning methods are evaluated and what performance is reported?\",\"answer\":\"The study evaluates logistic regression, decision tree, random forest, and stacking ensemble learning. Reported accuracy reaches up to 99% for personalized data and about 91% for the generalized setup, with ensemble learning performing best among models.\"}]","Stress Detection using Multimodal Physiological Signals with Machine Learning from Wearable Devices - Results - GMR-118 | PDF"]