[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128367-en":3,"doc-seo-128367-105":30,"detail-sidebar-cat-0-en-105":92},{"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},128367,962085571259,"Theodora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Toward Effective and Generalisable Machine Learning for Biosignal Time Series - Doctoral Thesis","Biosignal time series from wearable devices, including ECG, EEG, and IMUs, support continuous monitoring of physiology and behaviour, enabling personalised health tracking, earlier disease detection, and scalable cost-effective care. Real-world analysis remains difficult because signals are often sparse or irregular, contain missing values, and provide limited labels, while many SOTA models rely on clean, regularly sampled data with clinically verified annotations. This thesis develops self-supervised representation learning, domain adaptation, and foundation modelling to improve generalisation across tasks and datasets, validated across diverse healthcare applications from daily monitoring to clinical settings.","Toward e!ective and generalisable machine learning for biosignal time  \nseries  \nYu Wu  \nRobinson College  \nSeptember 2025  \nThis thesis is submitted for the degree of Doctor of Philosophy at the Department of  \nComputer Science and Technology  \nDeclaration  \nThis thesis is the result of my own work and includes nothing which is the outcome of work done in collaboration except as declared in the preface and specified in the text. It is not substantially the same as any work that has already been submitted, or is being concurrently submitted, for any degree, diploma or other qualification at the University of Cambridge or any other University or similar institution except as declared in the preface and specified in the text. It does not exceed the prescribed word limit for the relevant Degree Committee.  \nAbstract  \nBiosignal time series collected from wearable devices, such as electrocardiograms (ECG), electroencephalograms (EEG), and Inertial Measurement Units (IMUs), enable continuous monitoring of human physiology and behaviour. Using these signals provides unique opportunities to advance personalised health monitoring, improve early disease detection, and support the development of scaleable and cost-e!ective healthcare solutions. However, analysing such data presents significant challenges due to its complex nature, as signals are often sparse, irregular, contain missing values, and lack su”cient labels. In contrast, existing state-of-the-art methods are typically developed and validated on clean, regularly sampled biosignals with clinically verified ground-truth annotations, which limits their e!ectiveness and leads to performance degradation when applied to real-world data. Moreover, most existing models for biosignal time series are developed and evaluated in-domain, where both training and testing are conducted on the same dataset or under the same data collection protocol. Therefore, such models often fail to generalise to new scenarios in real-world healthcare deployments due to distributional shifts across tasks or deployment settings.  \nThis thesis addresses these challenges by developing machine learning methods tailored for biosignal time series that focus on self-supervised representation learning, domain adaptation, and foundation modelling for generalisation across tasks and datasets. We demonstrate the e”cacy of these methods on a wide range of real-world healthcare tasks, from daily cardio-fitness monitoring to clinical applications.  \nFirst, to address the scarcity of labelled data and the inherent complexity of biosignal time series, we propose a contrastive self-supervised learning framework specifically designed for biosignals, collected across diverse sources, ranging from wearable devices to clinical monitoring systems. Inspired by the success of contrastive learning in computer vision, our method captures the temporal and structural characteristics of biosignals without relying on labels. Then, our new training pipeline learns more e!ective representations from unlabelled data and improves the downstream task performance. This performance remains comparable to state-of-the-art methods, even when only a small fraction of labelled data is available, thus enhancing label e”ciency.  \nSecond, to improve model robustness under distribution shifts, we develop a domain  \nadaptation framework with multiple discriminators during fine-tuning. This method learns domain-invariant representations that generalise across source and target domains with di!ering label distributions, which is a common issue in healthcare due to the high cost and scarcity of gold-standard annotations. We validate this approach on a VO2 max prediction task and demonstrate improved adaptation performance under real-world domain shifts.  \nFinally, motivated by the growing success of foundation models in language and vision, we introduce a general-purpose foundation model tailored for biosignal time series to alleviate data complexity and improve m","cbCaiqGJxMI3c0eI","https://ap.wps.com/l/cbCaiqGJxMI3c0eI","pdf",18742491,1,142,"English","en",105,"# Abstract\n# Proposed Approaches\n## Contrastive self-supervised learning\n## Domain adaptation with multiple discriminators\n## Biosignal foundation model\n# Key Challenges and Contributions","[{\"question\":\"What problem does the thesis target in biosignal time series machine learning?\",\"answer\":\"It targets poor generalisation in real-world healthcare due to sparse or irregular signals, missing values, limited labels, and distribution shifts between deployment settings.\"},{\"question\":\"How does the thesis improve performance when labeled data is scarce?\",\"answer\":\"It proposes a contrastive self-supervised learning framework designed for biosignals, learning temporal and structural representations from unlabelled data to enhance label efficiency.\"},{\"question\":\"How does the thesis handle domain shifts between training and deployment?\",\"answer\":\"It introduces a domain adaptation framework using multiple discriminators during fine-tuning to learn domain-invariant representations under differing label distributions.\"}]","Toward Effective and Generalisable Machine Learning for Biosignal Time Series - Doctoral Thesis | PDF",1785947119,358,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"toward-effective-and-generalisable-machine-learning-for-biosignal-time-series-doctoral-thesis","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"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":13,"@type":43,"position":53},"https://docshare.wps.com/document/toward-effective-and-generalisable-machine-learning-for-biosignal-time-series-doctoral-thesis/128367/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"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","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the thesis target in biosignal time series machine learning?","Question",{"text":76,"@type":77},"It targets poor generalisation in real-world healthcare due to sparse or irregular signals, missing values, limited labels, and distribution shifts between deployment settings.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the thesis improve performance when labeled data is scarce?",{"text":81,"@type":77},"It proposes a contrastive self-supervised learning framework designed for biosignals, learning temporal and structural representations from unlabelled data to enhance label efficiency.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the thesis handle domain shifts between training and deployment?",{"text":85,"@type":77},"It introduces a domain adaptation framework using multiple discriminators during fine-tuning to learn domain-invariant representations under differing label distributions.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]