[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124351-en":3,"doc-seo-124351-105":30,"detail-sidebar-cat-0-en-105":83},{"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},124351,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Unit Cell Design for Space-Fed Surfaces Via Kernel-Based Machine Learning Regression - Research","A kernel-based machine learning regression framework enables automatic design and optimization of antenna unit cells (UCs) without resorting to brute-force full-wave simulations. Least-Squares Support Vector Machines (LS-SVM) are trained from a small set of parametric electromagnetic simulations to produce closed-form surrogate models of the UC responses. These surrogates accelerate design-space exploration by enabling fast optimizer iterations. The resulting optimal UC geometry is validated through a full three-layer transmitarray antenna design, achieving a 32 dB peak gain at 30 GHz with about 50% efficiency, 14% 1-dB bandwidth, and 28% 3-dB bandwidth.","POLITECNICO DI TORINO  \nRepository ISTITUZIONALE  \nUnit Cell Design for Space-Fed Surfaces Via Kernel-Based Machine Learning Regression  \nOriginal  \nUnit Cell Design for Space-Fed Surfaces Via Kernel-Based Machine Learning Regression / Beccaria, M. ; Soleimani, N. ; Trinchero, R. ; Pirinoli, P.. - (2025) . (Intervento presentato al convegno 2025 URSI International Symposium on Electromagnetic Theory, EMTS 2025 tenutosi a Bologna (Ita) nel 23-27 June 2025)[10 .46620/URSIEMTS25/JDLD6926] .  \nAvailability:  \nThis version is available at: 11583/3002866 since: 2025-09-08T14:51:38Z  \nPublisher: URSI  \nPublished  \nDOI:10.46620/URSIEMTS25/JDLD6926  \nTerms of use:  \nThis article is made available under terms and conditions as specified in the corresponding bibliographic description in the repository  \nPublisher copyright  \n(Article begins on next page)  \n04 October 2025  \nURSI-B EMTS 2025, Bologna, 23 – 27 June  \nUnit Cell Design for space-fed antenna via Kernel-based Machine Learning Regression  \nMichele Beccaria, Nazanin Soleimani, Riccardo Trinchero and Paola Pirinoli  \nPolitecnico di Torino, Torino, Italy; e-mail: {michele.beccaria, nazanin.soleimani, riccardo.trinchero, paola.pirinoli}@polito.it  \nAbstract  \nThis work explores a novel approach for the automatic design and optimization of unit cells (UCs) via kernel-based machine learning regression. Traditional UC optimization relies on brute-force full-wave simulations, which are computationally expensive and time-consuming. The proposed method uses the Least-Squares Support Vector Machines (LS-SVM) regression to build surrogate models, enabling the efficient design space exploration. The optimal UC geometry obtained by the proposed optimization methodology is then validated through the complete design of a three-layer Transmitarray Antenna (TA), achieving a 32 dB peak gain at 30 GHz with approximately 50% efficiency, a 1-dB bandwidth of 14%, and a 3-dB bandwidth of 28% .  \n1 Introduction and Motivation  \nThe increasing demand for advanced antenna technologies in evolving scenarios such as 5G/6G, small satellites, SATCOM on the move, automotive radar, and surveillance radar has shifted the focus from traditional microwave frequencies to millimeter-wave bands, often requiring wideband, multi-band, or reconfigurability. Reflectarray (RA) [1] -[3] and Transmitarray (TA) [4]-[7] antennas have emerged as promising solutions, offering planar or flexible designs, cost-effectiveness, ease of fabrication, high efficiency, and precise control over amplitude, phase, and polarization.  \nAt the core of these technologies, including more recent radiating surfaces such as Smart Electromagnetic Skins (SESs) [8], lies the design of the Unit Cell (UC), which is dictated by application-specific technological and electromagnetic requirements. Typically, UC optimization relies on a brute-force approach using full-wave simulations, a process that can take days or even weeks to achieve optimal performance, making the overall design highly inefficient and time-consuming.  \nIn this scenario, Machine Learning (ML) approaches can be seen as promising solutions to reduce the computational cost of the overall optimization task [7, 9, 10, 11] . The underlying idea is to use supervise data-driven ML techniques to build an accurate and fast-to-evaluate surrogate model able to approximate the behavior of a generic EM parametric structure provided by full-wave simulations [7, 10, 13] . The above surrogate model is built via ML regressions (e.g.,  \nkernel methods, artificial neural networks, etc.) from the results of a “small” set of parametric simulations of the considered EM structure [13, 14] . The obtained surrogate model is available in closed-form, and thus it can be suitably employed within the optimizer iterations [10, 13], asan extremely efficient alternative to the more computationally expensive full-wave simulations.  \nIn this work, the choice to apply the surrogate model to a UC for the design of a Tra","cbCaioOE7ggSUla0","https://ap.wps.com/l/cbCaioOE7ggSUla0","pdf",2448257,1,5,"English","en",105,"# 1 Introduction and Motivation\n# 2 Proposed Method for Unit Cell design","[{\"question\":\"How is the optimized unit cell validated?\",\"answer\":\"The optimized UC geometry is validated by designing a complete three-layer transmitarray antenna and comparing its performance metrics against the target results.\"}]","Unit Cell Design for Space-Fed Surfaces Via Kernel-Based Machine Learning Regression - Research | PDF",1785821779,13,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":28},"unit-cell-design-for-space-fed-surfaces-via-kernel-based-machine-learning-regression-research","",{"@graph":36,"@context":77},[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/unit-cell-design-for-space-fed-surfaces-via-kernel-based-machine-learning-regression-research/124351/",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","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"How is the optimized unit cell validated?","Question",{"text":75,"@type":76},"The optimized UC geometry is validated by designing a complete three-layer transmitarray antenna and comparing its performance metrics against the target results.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,101,106,111,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":21,"slug":129},19,"General","general"]