[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121819-en":3,"doc-seo-121819-105":30,"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":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},121819,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Investigating Two-Stage Machine Learning Techniques for Heart Arrhythmia Classification - Thesis","Heart arrhythmia classification is fundamental for diagnosing and guiding treatment of cardiac disorders. This thesis investigates the effectiveness of a two-stage machine-learning strategy for automatic classification, emphasizing Atrial Fibrillation (AF) and Ventricular Arrhythmia (VA). Four models are developed and evaluated using the UK BioBank dataset and the benchmark UCI arrhythmia dataset, addressing performance gaps with sequential design choices. Contributions include a two-stage classifier, ensemble-learning methods, and a DNN-based framework. Results show notable improvements, up to total F1 scores of 0.87, by combining a voting classifier with XGBoost and Naive Bayes/SGD, isolation-forest outlier removal, and SMOTE oversampling to mitigate class imbalance and enhance discrimination for minority classes. ","INVESTIGATING TWO-STAGE MACHINE LEARNING TECHNIQUES FOR HEART ARRHYTHMIA  \nCLASSIFICATION  \nPage 1 of 169  \nMarch 1, 2024  \nThesis submitted in fulfillment of the requirements for the degree of  \nDoctor of Philosophy  \nSchool of Electronic Engineering and Computer Science Queen Mary University Of London  \nBy Mercedeh Jafarkhanloo Rezaei  \nDoctor of Philosophy Declaration  \nI, Mercedeh Jafarkhanloo Rezaei, confirm that the research included within this thesis is my work or that where it has been carried out in collaboration with, or supported by others, this is duly acknowledged below and my contribution indicated. Previously published material is also acknowledged below.  \nI attest that I have exercised reasonable care to ensure that the work is original, and does not to the best of my knowledge break any UK law, infringe any third party’s copyright or other Intellectual Property Rights, or contain any confidential material.  \nI accept that the College has the right to use plagiarism detection software to check the electronic version of the thesis. I confirm that this thesis has not been previously submitted for the award of a degree by this or any other university.  \nThe copyright of this thesis rests with the author and no quotation from it or information derived from it may be published without the prior written consent of the author.  \nSignature:  \nMercedeh Jafarkhanloo Rezaei Date: 31st May 2023  \nDetails of collaboration:  \nThe collaborators and the UK BioBank data providers are listed below: Professor Patricia Munroe and Dr. Julia Ramírez  \nPage 3 of 169  \nAbstract  \nHeart arrhythmia classification plays a crucial role in diagnosing and treating cardiac conditions. This study focuses on investigating the efficacy of a two-stage approach for automatic heart arrhythmia classification with a specific focus on Atrial Fibrillation (AF) and Ventricular Arrhythmia (VA) using machine-learning techniques. The research aims to address existing gaps in the field and propose sequential solutions to improve classification performance. Four distinct models are introduced and thoroughly evaluated on the UK BioBank dataset and the benchmark UCI arrhythmia dataset. The primary contributions include the proposal of the two-stage classifier, the development of ensemble learning methodologies, and the introduction of a deep neural network (DNN)-based framework for heart arrhythmia classification. The proposed models exhibit significant improvements in overall classification performance. Additionally, effective strategies for handling class imbalance are explored, leading to improved discrimination ability for under-represented classes. The findings suggest that the combination of a voting classifier consisting of (XGBoost and Naive Bayes (NB) and Stochastic Gradient Descent (SGD)), outlier removal using isolation forest (IF), and oversampling using synthetic minority oversampling technique (SMOTE) is optimal for heart arrhythmia classification. The research presented in this study contributes to the advancement of automated heart arrhythmia classification, offering cost-effective solutions for healthcare and timely treatment.  \nTotal F1 scores up to 0.87 are achieved, demonstrating significant improvements in heart arrhythmia classification. The combination of a voting classifier, outlier removal using IF, andoversampling using SMOTE is identified as optimal for classification performance. Effective strategies for handling class imbalance improve discrimination ability for under-represented classes. These results underscore the potential of machine-learning techniques in improving heart arrhythmia classification and hold promise for the development of efficient and accurate automated diagnostic systems.  \nPage 4 of 169  \nAcknowledgments  \nI express my sincere gratitude to my supervisors and collaborators for their steadfast support, guidance, and encouragement throughout my academic journey. In particular, I would like to express my sincer","cbCaimpjsxAmnKmZ","https://ap.wps.com/l/cbCaimpjsxAmnKmZ","pdf",1841879,1,169,"English","en",105,"","[{\"question\":\"What is the main goal of this thesis?\",\"answer\":\"To investigate the effectiveness of a two-stage machine-learning approach for automatic heart arrhythmia classification, with a focus on Atrial Fibrillation (AF) and Ventricular Arrhythmia (VA).\"},{\"question\":\"Which datasets and models are used for evaluation?\",\"answer\":\"Four distinct models are evaluated on the UK BioBank dataset and the benchmark UCI arrhythmia dataset.\"},{\"question\":\"How does the proposed method handle class imbalance?\",\"answer\":\"It uses oversampling with SMOTE to improve discrimination for under-represented classes, together with outlier removal using isolation forest and ensemble voting.\"}]","Investigating Two-Stage Machine Learning Techniques for Heart Arrhythmia Classification - Thesis | PDF",1785807024,426,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":25,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":28},"investigating-two-stage-machine-learning-techniques-for-heart-arrhythmia-classification-thesis",{"@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/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/investigating-two-stage-machine-learning-techniques-for-heart-arrhythmia-classification-thesis/121819/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"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":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What is the main goal of this thesis?","Question",{"text":74,"@type":75},"To investigate the effectiveness of a two-stage machine-learning approach for automatic heart arrhythmia classification, with a focus on Atrial Fibrillation (AF) and Ventricular Arrhythmia (VA).","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Which datasets and models are used for evaluation?",{"text":79,"@type":75},"Four distinct models are evaluated on the UK BioBank dataset and the benchmark UCI arrhythmia dataset.",{"name":81,"@type":72,"acceptedAnswer":82},"How does the proposed method handle class imbalance?",{"text":83,"@type":75},"It uses oversampling with SMOTE to improve discrimination for under-represented classes, together with outlier removal using isolation forest and ensemble voting.","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":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"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":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},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"]