[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125248-en":3,"doc-seo-125248-105":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},125248,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Machine Learning-Assisted Microstrip Antenna Design Featuring Extraordinary Polarization Purity","A high degree of polarization purity for microstrip antennas is explored, presenting a novel approach combining stepwise complex multi-unit defected ground geometry (DGG) development and machine learning-assisted global optimization. The proposed parallel surrogate model-assisted hybrid differential evolution for antenna synthesis (PSADEA) accelerates optimization by over 10× versus common global methods while yielding superior multi-performance designs. Results reduce cross-polarization across orthogonal and diagonal planes while keeping primary gain stable. C-band prototypes and a 4-element array demonstrate strong peak gain, improved XP levels, and high co-to-XP isolation.","Machine Learning-Assisted Microstrip Antenna Design Featuring Extraordinary Polarization Purity  \nSk Rafidul, Member, IEEE, Mobayode O. Akinsolu, Senior Member, IEEE, Bo Liu, Senior Member, IEEE, Chandrakanta Kumar, Senior Member, IEEE, and Debatosh Guha, Fellow, IEEE  \nAbstract—A high degree of polarization purity for microstrip antennas has been successfully explored. This, to the best of our knowledge, is the first of its kind and claims a two-fold novelty:(i) a stepwise development of complex multi-unit defected ground geometry (DGG) based on a thorough scientific analysis, and (ii) use of a machine learning-assisted global antenna optimization method, particularly, the parallel surrogate model-assisted hybrid differential evolution for antenna synthesis (PSADEA) algorithm, which is often more than 10 times faster than popular global optimization techniques, while obtaining superior results. They result in highly optimal solutions considering multiple performances, i.e., reduction in cross-pol (XP) radiations simultaneously over orthogonal (H-) and diagonal (D-) planes maintaining the primary gain unaffected. The proposed DGG has been satisfactorily tested with different patches and arrays fabricated in C-band. Typically, 7.5-8.0 dBi peak gain has been ensured along with 13-18 dB improvement in XP level over entire radiation planes. A 4-element array on an identical DGG promises over 40 dB co-to-XP isolation over the entire azimuth planes.  \nIndex Terms—Artificial intelligence, ground plane engineering, machine learning, microstrip antenna, polarization purity.  \nI. INTRODUCTION  \nO  \nPTIMAL signal transmission/reception by microstrip antennas hinges on maintaining polarization purity asa top priority [1], [2] . Although it naturally exhibits  \noutstanding polarization purity in its E-plane (azimuth φ=0°), the situation dramatically changes over the H- (φ=90°) and diagonal (φ=45° or D-) planes [3] . Several earlier endeavors explored engineering with feed [4]-[7], patch and layers [7] -[10], and ground plane (GP) [11]-[17] to mitigate the XP issue, especially across H-plane. However, it is more serious and equally challenging across D-planes [3] . A few studies [18]-[21] have recently addressed it of which [20], [21] compromised with the H-plane performance and the rest [18],  \nManuscript received November 27, 2024. This work is supported by the Scheme of Abdul Kalam Technology Innovation National Fellow of Indian National Academy of Engineering/Department of Science & Technology Science and Engineering Research Board (INAE/DST-SERB), Government of India. (Corresponding author: Sk Rafidul, [rafidul100@gmail.com](rafidul100@gmail.com)).  \nSk Rafidul and D. Guha is with the Institute of Radio Physics and Electronics, University of Calcutta, Kolkata 700009, India. D. Guha is also associated with the Department of Electronics & Communication Engineering, National Institute of Technology Jaipur, 302017, India.  \nM. O. Akinsolu is with the Faculty of Arts, Computing, and Engineering, Wrexham University, Wales, Wrexham LL11 2AW, U.K.  \nB. Liu is with the James Watt School of Engineering, University of Glasgow, Glasgow, Scotland, G12 8QQ U.K.  \nC. Kumar is with the Communication Systems Group, U R Rao Satellite Centre, Department of Space, Government of India, Bangalore 560017, India.  \n[19] encountered limitations in realizing arrays.  \nThe present investigation aims in alleviating all these shortcomings. A multi-parametric defected ground geometry (DGG) has been introduced. Its complexity along with multiple challenging goals (lowering XP on both D- and Hplanes maintaining the gain unaltered) makes the problem complex. Simple analysis or manual tuning thus becomes next to impossible to predict the optimum DGG solution.  \nPopular global optimization techniques (e.g., differential evolution (DE) and particle swarm optimization (PSO)) are not suitable due to suboptimal solutions and long optimization times. The present work, theref","cbCairRMdYSBuL64","https://ap.wps.com/l/cbCairRMdYSBuL64","pdf",1368850,1,6,"English","en",105,"# Introduction\n## Polarization purity challenge (E-, H-, and diagonal planes)\n## Machine learning-assisted global optimization\n# New Geometry: Conjecture and Development","[{\"question\":\"What is the main goal of the proposed microstrip antenna design?\",\"answer\":\"To achieve extraordinary polarization purity by reducing cross-polarization in both orthogonal (H-) and diagonal (D-) planes while maintaining the primary gain.\"},{\"question\":\"Why is a machine learning-assisted optimization method used instead of standard global optimizers?\",\"answer\":\"Differential evolution and particle swarm optimization can lead to suboptimal solutions and long optimization times for complex antenna structures, so the PSADEA method is adopted for faster and higher-quality optimization.\"},{\"question\":\"What performance improvements were reported for C-band prototypes and arrays?\",\"answer\":\"C-band prototypes typically achieve 7.5–8.0 dBi peak gain with 13–18 dB improvement in cross-polarization across radiation planes, and a 4-element array on the same DGG provides over 40 dB co-to-XP isolation across azimuth planes.\"}]","Machine Learning-Assisted Microstrip Antenna Design Featuring Extraordinary Polarization Purity | PDF",1785897706,15,{"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},"machine-learning-assisted-microstrip-antenna-design-featuring-extraordinary-polarization-purity","",{"@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/machine-learning-assisted-microstrip-antenna-design-featuring-extraordinary-polarization-purity/125248/",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 is the main goal of the proposed microstrip antenna design?","Question",{"text":75,"@type":76},"To achieve extraordinary polarization purity by reducing cross-polarization in both orthogonal (H-) and diagonal (D-) planes while maintaining the primary gain.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why is a machine learning-assisted optimization method used instead of standard global optimizers?",{"text":80,"@type":76},"Differential evolution and particle swarm optimization can lead to suboptimal solutions and long optimization times for complex antenna structures, so the PSADEA method is adopted for faster and higher-quality optimization.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance improvements were reported for C-band prototypes and arrays?",{"text":84,"@type":76},"C-band prototypes typically achieve 7.5–8.0 dBi peak gain with 13–18 dB improvement in cross-polarization across radiation planes, and a 4-element array on the same DGG provides over 40 dB co-to-XP isolation across azimuth planes.","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},[93,97,101,105,110,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]