[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128275-en":3,"doc-seo-128275-105":31,"detail-sidebar-cat-0-en-105":75},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128275,2336475104957,"Seraphina","https://ap-avatar.wpscdn.com/avatar/22000c4c6bd8a5076e1?x-image-process=image/resize,m_fixed,w_180,h_180&k=1787554080175789136",8,"Research & Report","CLASSIFICATION OF EMOTION-BASED BODYODOUR USING MACHINE LEARNINGAPPROACHES","Emotions influence daily communication, decision-making, and behavior through physiological responses such as sweating, making the mapping between emotional states and body odour a key research direction. This study uses Differential Mobility Spectrometry (DMS) electronic-nose measurements to analyze volatile organic compounds (VOCs) from sweat samples. Sweat samples are collected while participants watch neutral and fear-evoking videos, then models are trained on dispersion-plot intensity features to classify fear-related versus neutral odours. Results show robust, high-accuracy performance, with top models achieving up to 83% in leave-one-out evaluation.","\u003Cp>Maureen Githaiga  \u003C/p>\u003Cp>CLASSIFICATION OF EMOTION-BASED BODYODOUR USING MACHINE LEARNINGAPPROACHES  \u003C/p>\u003Cp>A Comparative Study Using Differential Mobility Spectrometry(DMS)Data  \u003C/p>\u003Cp>Master of Science ThesisFaculty of Information Technology and Communication SciencesNovember 2024  \u003C/p>\u003Cp>i  \u003C/p>\u003Cp>ABSTRACT  \u003C/p>\u003Cp>Maureen Githaiga:Classification of Emotion-Based Body Odour Using Machine Learning Ap-proaches  \u003C/p>\u003Cp>Master of Science ThesisTampere UniversityData ScienceNovember 2024  \u003C/p>\u003Cp>Emotions affect us in our daily lives,influencing how we communicate,the decisions we make,and our behaviour.The physiological responses triggered by these emotions,such as sweat-ing,have become an interesting area of study,particularly in understanding how they manifestand what they reveal about different emotions.Differential Mobility Spectrometry(DMS),a formof electronic nose technology that mimics the human nose,has been applied to investigate thechemical composition of different Volatile Organic Compounds (VOCs).Machine learning algo-rithms have been leveraged successfully to analyze and distinguish different VOCs based on theirDMS measurements.  \u003C/p>\u003Cp>This study aims to classify body odour from sweat samples using measurements from theDMS electronic nose.We seek to determine whether changes in sweat composition caused byexposure to emotion-evoking situations can provide insight into emotion-related responses.  \u003C/p>\u003Cp>Sixty composite super-donor samples were created from sweat samples collected from 16 par-ticipants while they watched neutral and fear-evoking videos.These samples were analyzed usingDMS,which generates dispersion plots.The points of maximum intensity in the dispersion plotswere used as input features.Various machine learning algorithms,including Support Vector Ma-chines(SVM),Linear Discriminant Analysis (LDA),Decision Tree,Random Forest,and k-NearestNeighbor Searching(k-NN),were employed.Leave-one-out (LOOCV),leave-one-participant out(LOPOCV),3-fold and 5-fold cross-validation methods were used for evaluation.  \u003C/p>\u003Cp>The models showed high accuracy,with the SVMsigmoid kernel and LDA achieving 83%accu-racy in LOOCV,k-NN achieving 82%in LOPOCV,random forest achieving 80%in LOOCV,3-foldand 5-fold cross-validation,and SVM with RBF kernel achieving 79%in LOPOCV.LDA and SVMwith the RBF kernel emerged as the top-performing models,demonstrating robust performancewithout overfitting,in contrast to others that exhibited varying degrees of overfitting.Overall,themodels demonstrated a significant ability to distinguish between odours associated with fear andneutral emotional states.  \u003C/p>\u003Cp>The study's findings suggest that machine learning algorithms can effectively identify pat-terns in sweat composition linked to different emotions,offering insights into how physiologicalresponses relate to emotions.This study highlights the potential of electronic nose technology inemotion detection and contributes to the ongoing research on the relationship betweenemotions,physiological responses and body odour.  \u003C/p>\u003Cp>Keywords:Machine Learning,Differential Mobility Spectrometry,Electronic Nose,Body Odour,Emotions,Classification  \u003C/p>\u003Cp>The originality of this thesis has been checked using the Turnitin OriginalityCheck service.  \u003C/p>\u003Cp>PREFACE  \u003C/p>\u003Cp>l am profoundly grateful to God for seeing me through my master's degree and the com-pletion of this thesis.My deepest appreciation goes to my supervisor,Prof.Martti Juhola,for providing me with the thesis topic opportunity and for his invaluable guidance through-out the process.I also extend my gratitude to the Emotions,Sociality,and Computing(ESC)research group for providing the necessary materials and valuable instructionsthat were instrumental in completing this work.Special thanks to Dr.Philipp Müller for hisexpertise and assistance on this topic.  \u003C/p>\u003Cp>I want to thank my friends and acquaintances for being a great support system along theway.I am equally grateful to my family for their understanding,prayers,and unwaveringsupport.Lastly,I applaud myself for showing resilience,believin\u003C/p>","cbCaiqkfDa11E0xW","https://ap.wps.com/l/cbCaiqkfDa11E0xW","pdf",5736709,5,1,79,"English","en",105,"# Introduction\n## Research Objectives\n# Background\n## Overview on Differential Mobility Spectrometry\n# Contents","","CLASSIFICATION OF EMOTION-BASED BODYODOUR USING MACHINE LEARNINGAPPROACHES | PDF",1787313892,199,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":28,"keywords":27,"description":14,"schema_data":35,"social_meta":70,"head_meta":72,"extra_data":74,"updated_unix":29},"classification-of-emotion-based-body-odour-using-machine-learning-approaches-a-comparative-study-using-differential-mobility-spectrometry-dms-data",{"@graph":36,"@context":69},[37,54],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"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":28,"@type":43,"position":53},"https://docshare.wps.com/document/classification-of-emotion-based-body-odour-using-machine-learning-approaches-a-comparative-study-using-differential-mobility-spectrometry-dms-data/128275/",4,{"url":52,"name":28,"@type":55,"author":56,"headline":28,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-26","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction","https://schema.org",{"og:url":52,"og:type":71,"og:title":28,"og:site_name":59,"og:description":14},"article",{"robots":73,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":76},[77,81,85,89,93,98,103,106,111,114,118],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":78,"show_sort_weight":79,"slug":80},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":82,"show_sort_weight":83,"slug":84},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Comic",60,"comic",{"id":94,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},6,"Technology",50,"technology",{"id":99,"doc_module":4,"doc_module_name":46,"category_name":100,"show_sort_weight":101,"slug":102},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":104,"slug":105},30,"research-report",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},9,"Religion & Spirituality",20,"religion-spirituality",{"id":109,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":109,"slug":113},"World Cup","world-cup",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":115,"slug":117},10,"Lifestyle","lifestyle",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":20,"slug":121},19,"General","general"]