[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124769-en":3,"doc-seo-124769-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"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},124769,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","HSI Data Unmixing Using Machine Learning Techniques - Doctoral Thesis","Hyperspectral image (HSI) unmixing estimates scene endmembers and their abundances from hyperspectral camera measurements. Recent deep learning unmixing methods often reuse generic CNN designs, without ensuring physically meaningful results. This thesis proposes unmixing networks built via algorithm unrolling for an ADMM solver derived from a constrained sparse regression under a linear mixture model. To enhance physical validity, a blind unmixing framework based on double DIP is introduced and trained end-to-end with a composite loss, together with unfolding sub-networks for endmember and abundance estimation. Experiments on synthetic and real HSI data demonstrate state-of-the-art performance against competing approaches.","HSI DATA UNMIXING USING MACHINE LEARNING TECHNIQUES  \nCHAO ZHOU  \nUNIVERSITY COLLEGE LONDON DEPARTMENT OF ELECTRONIC AND ELECTRICAL  \nENGINEERING  \nSubmitted to University College London (UCL) in partial fulfilment of the requirements for the award of the degree  \nof Doctor of Philosophy.  \nWord count: 44861 Thesis submission date: 24 March 2023  \nDeclaration  \nI, Chao Zhou, confirm that the work presented in this thesis is my own. Where information has been derived from other sources, I confirm that this has been indicated in the thesis.  \nAbstract  \nHyperspectral image (HSI) unmixing is a challenging research problem that tries to identify the constituent components, known as endmembers, and their corresponding proportions, known as abundances, in the scene by analysing images captured by hyperspectral cameras. Recently, many deep learning based unmixing approaches have been proposed with the surge of machine learning techniques, especially convolutional neural networks (CNN) . However, most of these methods rely on the general-purpose CNN structures and it is unclear how to design an efficient network for unmixing purposes. In this work, we first address the structural issue by proposing new unmixing networks that leverage algorithm unrolling techniques to the Alternating Direction Method of Multipliers (ADMM) solver of a constrained sparse regression problem underlying a linear mixture model. However, like many other methods in the literature, there is no guarantee that the network could generate physically meaningful unmixing results. To solve this problem, we proposed a novel blind unmixing network using double DIP techniques (BUDDIP) which consists of two DIP sub-networks to estimate the endmember and abundance respectively, which are coined as EDIP and ADIP. The network is trained in an end-to-end manner by minimizing a novel composite loss function. Finally, we propose a novel unmixing algorithm that can address both issues, simultaneously. Specifically, we first propose a novel MatrixConv Unmixing (MCU) Model for endmember and abundance estimation, respectively, which can be solved via certain iterative solvers. We then unroll these  \nsolvers to build two unfolding based sub-networks, which are coined as UEDIP and UADIP, to generate the estimation of endmember and abundance, respectively. The overall network is then constructed by assembling these two sub-networks. To further improve the unmixing quality, we also add explicitly a regulariser for endmember and abundance estimation, respectively. Experimental results on both synthetic and real HSI data show that the proposed method achieves state-ofthe-art performance compared to other unmixing approaches.  \nImpact Statement  \nHSI data is a valuable tool for characterizing the materials present in a given scene, but the process of unmixing the data to accurately identify these materials can be complex and challenging. The successful application of machine learning techniques in various research areas has inspired the development of many machine learning-based algorithms for HSI unmixing purposes. However, most of these methods rely on the general-purpose CNN structure and lack the ability to guarantee the generation of physically meaningful unmixing results. Hence, it is necessary to develop new unmixing networks that are designed specifically for HSI unmixing problems and can effectively deliver physically meaningful unmixing results.  \nIn this work, we solve the above problems by proposing a novel framework that can build network structures specifically for unmixing purposes and generate physically meaningful unmixing results by leveraging the guidance provided by existing unmixing algorithms. Our approach has the potential to significantly advance the state-of-the-arts in HSI data analysis, as it allows for more accurate and efficient characterization of the materials present in a given scene. This has numerous practical applications in various domains, such as remote sensing","cbCaihq04Ejp8Rqa","https://ap.wps.com/l/cbCaihq04Ejp8Rqa","pdf",11741020,1,207,"English","en",105,"## Abstract\n## Impact Statement\n## Research Paper Declaration Form","[{\"question\":\"What problem does the thesis address?\",\"answer\":\"The thesis addresses hyperspectral image (HSI) unmixing, aiming to identify endmembers and estimate their abundances from hyperspectral measurements.\"},{\"question\":\"How does the proposed method improve network design for unmixing?\",\"answer\":\"It designs unmixing networks using algorithm unrolling of an ADMM solver tied to a constrained sparse regression model underlying a linear mixture model.\"},{\"question\":\"How is physically meaningful unmixing enforced?\",\"answer\":\"It introduces a blind unmixing framework using double DIP (BUDDIP) with two DIP sub-networks to estimate endmembers and abundances, trained end-to-end with a novel composite loss function and additional regularization.\"}]","HSI Data Unmixing Using Machine Learning Techniques - Doctoral Thesis | PDF",1785894459,522,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"hsi-data-unmixing-using-machine-learning-techniques-doctoral-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@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/hsi-data-unmixing-using-machine-learning-techniques-doctoral-thesis/124769/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address?","Question",{"text":75,"@type":76},"The thesis addresses hyperspectral image (HSI) unmixing, aiming to identify endmembers and estimate their abundances from hyperspectral measurements.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method improve network design for unmixing?",{"text":80,"@type":76},"It designs unmixing networks using algorithm unrolling of an ADMM solver tied to a constrained sparse regression model underlying a linear mixture model.",{"name":82,"@type":73,"acceptedAnswer":83},"How is physically meaningful unmixing enforced?",{"text":84,"@type":76},"It introduces a blind unmixing framework using double DIP (BUDDIP) with two DIP sub-networks to estimate endmembers and abundances, trained end-to-end with a novel composite loss function and additional regularization.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]