[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118538-en":3,"doc-seo-118538-105":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},118538,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Machine Learning Methods for Signal Processing with Applications to the Wireless Physical Layer","This multidisciplinary doctoral thesis studies and develops adaptive signal processing techniques that leverage prior knowledge about system and signal features to build accurate models of physical phenomena. It focuses on adaptive, data-efficient learning under noisy, low-data conditions typical of real wireless links, where intrinsic signal structure can be scarce and systems behave nonlinearly and time-variably. The work addresses low-rank denoising for mmWave channel estimation and deep learning-based user-target association for integrated sensing and communication (ISAC), supported by a multi-modal co-simulation environment and validated via experimental results for wireless physical-layer scenarios in high-mobility urban vehicular settings.","POLITE C NICO DI MILANO  \nScuola di Ingegneria Industriale e dell’Informazione Dipartimento di Elettronica, Informazione e Bioingegneria Doctoral Programme in Information Technology  \nMachine Learning Methods for Signal Processing with Applications to the Wireless Physical Layer  \nAdvisor: prof . matteo matteucci  \nCo-Advisor: dr . dario tagliaferri  \nTutor: prof . francesco amigoni  \nDoctoral Dissertation of:  \nlorenzo cazzella  \n2024-XXXVI Cycle  \nTo my family.  \nABSTRACT  \nThis multidisciplinary thesis—at the intersection of machine learning, signal processing, and wireless communications—aims to study and develop adaptive signal processing techniques that exploit prior knowledge on the features of systems and signals to produce accurate models of physical phenomena. The development of adaptive and data-efficient techniques in noisy and low-data settings is the goal of the recently emerged Machine Learning for Signal Processing research branch. Despite being noisy, real-world signals often retain intrinsic structures reflective of the physical systems that generated them. Nevertheless, the number of available observations that can be exploited to determine such hidden structure can be very limited, while physical systems can present complex nonlinear and time-variant behavior. Besides, highly computation-efficient methods are often required for applicability in challenging estimation settings. In this thesis, we tackle two of these estimation conditions: (i) the design of low-rank signal denoising methods by means of clustering-based and deep learning-based subspace estimation, with application to mmWave channel estimation in urban wireless vehicular communications, and (ii) the association of a radar target with the corresponding communication user in integrated sensing and communication (ISAC) systems, achieved by deep learning-based joint radar target detection and beam prediction and by performing data association in the beamspace. To obtain a realistic environment for the evaluation of the proposed methods, we integrated vehicular traffic, multi-sensor, V2X ray tracing channel simulation, and mmWave MIMO radar imaging in a single multi-modal co-simulation framework. We provide experimental results showcasing the effectiveness of the proposed techniques for the physical layer of wireless communications. We show that the design of adaptive techniques exploiting the representational power of machine learning and deep learning can lead to data-efficient estimation performance under the challenging high-mobility conditions of the wireless physical layer in urban vehicular settings, which can be instrumental in the context of the future 6G communications.  \nCONTRIBUTIONS  \nIn the following, we report the main contributions to the literature that have been published as part of the development of this thesis work.  \n1. Lorenzo Cazzella, Dario Tagliaferri, Marouan Mizmizi, Matteo Matteucci, Damiano Badini, Christian Mazzucco, and Umberto Spagnolini. Positionagnostic Algebraic Estimation of 6G V2X MIMO Channels via Unsupervised Learning. 2022 IEEE Wireless Communications and Networking Conference (WCNC), Austin, TX, USA, 2022, pp. 740-745.  \nDOI: 10.1109/WCNC51071.2022.9771914.  \nContributions: review of the background on clustering techniques; design and implementation of the proposed machine learning method; experimental results; manuscript co-writing and review.  \n2. Lorenzo Cazzella, Dario Tagliaferri, Marouan Mizmizi, Damiano Badini, Christian Mazzucco, Matteo Matteucci, and Umberto Spagnolini. Deep Learning of Transferable MIMO Channel Modes for 6G V2X Communications. In IEEE Transactions on Antennas and Propagation, vol. 70, no. 6, pp. 4127-4139, June 2022. DOI: 10.1109/TAP.2022.3169950.  \nContributions: review of the background on low-rank estimation methods; design and implementation of the proposed deep learning method; experimental results; manuscript co-writing and review.  \n3. Lorenzo Cazzella, Marouan Mizmizi, Dari","cbCaifnU5qYpnc15","https://ap.wps.com/l/cbCaifnU5qYpnc15","pdf",23356232,1,195,"English","en",105,"# Abstract\n# Contributions\n## Published contributions\n## Other contributions","[{\"question\":\"What core problem does the thesis address in wireless signal processing?\",\"answer\":\"It develops adaptive signal processing methods that exploit prior knowledge to create accurate physical-phenomena models from noisy observations, especially when data are limited.\"},{\"question\":\"Which two main estimation scenarios are tackled?\",\"answer\":\"Low-rank signal denoising for mmWave channel estimation using clustering/deep learning subspace methods, and radar target-to-user association in ISAC using deep learning for joint detection and beam prediction plus data association in beamspace.\"},{\"question\":\"How is a realistic evaluation environment created for the proposed methods?\",\"answer\":\"By integrating vehicular traffic, multi-sensor inputs, V2X ray tracing channel simulation, and mmWave MIMO radar imaging into a single multi-modal co-simulation framework, then validating physical-layer effectiveness through experimental results.\"}]","Machine Learning Methods for Signal Processing with Applications to the Wireless Physical Layer | PDF",1785684044,491,{"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},"machine-learning-methods-for-signal-processing-with-applications-to-the-wireless-physical-layer","",{"@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/machine-learning-methods-for-signal-processing-with-applications-to-the-wireless-physical-layer/118538/",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","2026-08-05","2026-08-02",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 core problem does the thesis address in wireless signal processing?","Question",{"text":76,"@type":77},"It develops adaptive signal processing methods that exploit prior knowledge to create accurate physical-phenomena models from noisy observations, especially when data are limited.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which two main estimation scenarios are tackled?",{"text":81,"@type":77},"Low-rank signal denoising for mmWave channel estimation using clustering/deep learning subspace methods, and radar target-to-user association in ISAC using deep learning for joint detection and beam prediction plus data association in beamspace.",{"name":83,"@type":74,"acceptedAnswer":84},"How is a realistic evaluation environment created for the proposed methods?",{"text":85,"@type":77},"By integrating vehicular traffic, multi-sensor inputs, V2X ray tracing channel simulation, and mmWave MIMO radar imaging into a single multi-modal co-simulation framework, then validating physical-layer effectiveness through experimental results.","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"]