[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128189-en":3,"doc-seo-128189-105":31,"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":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},128189,2336475104042,"Skyler","https://ap-avatar.wpscdn.com/avatar/22000c4c32af1715be0?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786537525561427321",8,"Research & Report","Human Interfaces with Machine Learning Recognition Systems - PhD Thesis Abstract","Building large-scale datasets is increasingly automated, yet labeling remains a rapidly growing bottleneck in time and interactive effort, especially for feature-rich data structures and demanding domain-specific modeling. This thesis investigates deep learning supervision strategies to strengthen inductive bias, then applies them to steel manufacturing. It presents a generative-model-based semi-supervised clustering approach with varying supervision from labels or expert-driven active learning using decision-support visualisations. It also develops a representation-distance acquisition function for active learning, improving data refinement by correcting bounding-box errors to produce dense segmentation, while studying different interaction levels. Finally, it models hierarchical label systems using encapsulation and semantic sub-classification relations via graph-based deep learning to solve classification and segmentation.","Human Interfaces with Machine Learning Recognition Systems  \nConnor Clarkson  \nSubmitted to Swansea University in fulfilment of the requirements for the Degree of Doctor of Philosophy  \nSchool of Mathematics and Computer Science  \nSwansea University  \nJune 3, 2025  \nCopyright: The author, Connor Clarkson, 2025  \nDistributed under the terms of a Creative Commons Attribution 4.0 License (CC BY 4 .0) .  \nDeclarations  \nThis work has not previously been accepted in substance for any degree and is not being concurrently submitted in candidature for any degree.  \nThis thesis is the result of my own investigations, except where otherwise stated. Other sources are acknowledged by footnotes giving explicit references. A bibliography is appended.  \nI hereby give consent for my thesis, if accepted, to be available for photocopying and for interlibrary loan, and for the title and summary to be made available to outside organisations. Signed      (candidate)  \nDate    \n03/06/2025  \nI would like to dedicate this thesis to Lillian Doreen Morgan and Rebecca L. Clarkson.  \nAbstract  \nBuilding large pools of data has become a relatively straightforward task, with many automated ways of obtaining different sources of data. Labelling such data has resulted in becoming an exponential problem, both in terms of time and in the form of an interaction-heavy task. This task only becomes exponential with feature-rich structures of data and labelling systems, as well as requiring more advanced expertise for many different domains of a task to model. A prominent set of techniques utilising this data, and large networks have reformed machine learning into what we call deep learning today. Within this field, we can form levels of supervision that allow for stronger signals of inductive bias for both deep network architecturesand in the training scheme. In this work, we explore both types with the target application and domain being the manufacturing of steel.  \nFirstly, we present an exploratory approach to assist in decision-making for the task of clustering by utilising the feature-rich representations provided by generative models. By forming itas a semi-supervised problem we can provide varying degrees of supervision to enhance performance as a form of inductive bias into the training scheme. Supervision can be formalised into labels from data or in an active learning setting where we request help from an expert. If we are required to make a request, then we must provide information and visualisations so that an accurate decision can be made.  \nFollowing this, in our second body of work we extend on an active learning setting by introducing a new acquisition function based on the distance from different representations. We apply it to a data refinement strategy where we fix mistakes in bounding-box labelled datasets to form a dense segmentation. Different forms of user interaction provide different levels of information to the training scheme, we explore the effects of these user interactions on the performance of this refinement task.  \nLastly, we apply stronger forms of inductive bias into the network architecture by modelling hierarchical labelling systems, where such relationships between labels form an abstraction and fine-grained level of the data. Inspired by the structure of human cognition and perception where we recognise patterns of various levels of abstraction to define an object. By invoking an explicit form of deep learning with feature-rich structures like graphs we can model these interconnected labels. We define two types of hierarchical relationships: the first is a break-up of the physical or geometric structure of the object, referred to as an encapsulation relationship. The second is sub-classification relationships which are semantic relations of labels provided by domain knowledge of what we are trying to capture in the dataset. We utilise both to solve classification and segmentation tasks.  \nAcknowledgements  \nFirst and foremost I would l","cbCaifvzBV220Ozr","https://ap.wps.com/l/cbCaifvzBV220Ozr","pdf",7285872,2,1,163,"English","en",105,"# Abstract\n## Data labeling and supervision strategies\n## Generative-model semi-supervised clustering\n## Active learning acquisition and dense segmentation refinement\n## Hierarchical label systems and graph-based modeling\n## Applications to steel manufacturing","[{\"question\":\"Why does labeling become an exponential challenge in machine learning projects?\",\"answer\":\"Labeling scales poorly in time and interaction effort, especially when data is feature-rich and the task requires advanced, domain-specific expertise to model accurately.\"},{\"question\":\"How does the thesis support clustering using generative model representations?\",\"answer\":\"It formulates clustering as a semi-supervised problem using feature-rich representations from generative models, enabling varying degrees of supervision via labels or expert assistance in an active learning setting.\"},{\"question\":\"What is the role of hierarchical labeling in the final part of the work?\",\"answer\":\"It introduces hierarchical label relationships—encapsulation and semantic sub-classification—then uses graph-based deep learning to model these abstractions for classification and segmentation tasks.\"}]","Human Interfaces with Machine Learning Recognition Systems - PhD Thesis Abstract | PDF",1785945416,411,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"human-interfaces-with-machine-learning-recognition-systems-phd-thesis-abstract","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/human-interfaces-with-machine-learning-recognition-systems-phd-thesis-abstract/128189/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"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":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","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},"Why does labeling become an exponential challenge in machine learning projects?","Question",{"text":76,"@type":77},"Labeling scales poorly in time and interaction effort, especially when data is feature-rich and the task requires advanced, domain-specific expertise to model accurately.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the thesis support clustering using generative model representations?",{"text":81,"@type":77},"It formulates clustering as a semi-supervised problem using feature-rich representations from generative models, enabling varying degrees of supervision via labels or expert assistance in an active learning setting.",{"name":83,"@type":74,"acceptedAnswer":84},"What is the role of hierarchical labeling in the final part of the work?",{"text":85,"@type":77},"It introduces hierarchical label relationships—encapsulation and semantic sub-classification—then uses graph-based deep learning to model these abstractions for classification and segmentation tasks.","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":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]