[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125942-en":3,"doc-seo-125942-105":31,"detail-sidebar-cat-0-en-105":93},{"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},125942,137451207643,"Noah","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Enhancing NLoS RIS-Aided Localization with Optimization and Machine Learning","This paper presents two machine learning-based optimization algorithms to improve position estimation in reconfigurable intelligent surface (RIS) aided localization for mobile user equipment under non-line-of-sight (NLoS) conditions. The proposed methods target extremely high accuracy, achieving sub-centimeter or sub-millimeter performance at 3.5 GHz. Simulations in an indoor 10 m by 10 m room with RIS tiles show substantial error reductions: under 30 cm in 90% of cases and under 5 mm in about 85% of cases. By comparing four optimization techniques, the study shows that combining a genetic algorithm (GA) and particle swarm optimization (PSO) yields the best localization results, enabling more reliable practical NLoS indoor localization.","Enhancing NLoS RIS-Aided Localization with Optimization and Machine Learning  \nRafael A. Aguiar􀀃†, Nuno Paulino􀀃† and Lu´􀀑s M. Pessoa􀀃†  \n􀀃 INESC TEC, Porto, Portugal  \n†Faculdade de Engenharia, Universidade do Porto, Portugal  \n{rafael.a.aguiar, nuno.m.paulino, [luis.m.pessoa](luis.m.pessoa}@inesctec.pt)[}](luis.m.pessoa}@inesctec.pt)[@inesctec.pt](luis.m.pessoa}@inesctec.pt)  \narXiv :2405 .01928v1 [ ee ss . SP] 3 May 2024  \nAbstract—This paper introduces two machine learning optimization algorithms to signi􀀂cantly enhance position estimation in Recon􀀂gurable Intelligent Surface (RIS) aided localization for mobile user equipment in Non-Line-of-Sight conditions. Leveraging the strengths of these algorithms, we present two methods capable of achieving extremely high accuracy, reaching sub-centimeter or even sub-millimeter levels at 3.5 GHz. The simulation results highlight the potential of these approaches, showing signi􀀂cant improvements in indoor mobile localization. The demonstrated precision and reliability of the proposed methods offer new opportunities for practical applications in real-world scenarios, particularly in Non-Line-of-Sight indoor localization. By evaluating four optimization techniques, we determine that a combination of a Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) results in localization errors under 30 cm in 90 % of the cases, and under 5 mm for close to 85 % of cases when considering a simulated room of 10 m by 10 m where two of the walls are equipped with RIS tiles.  \nIndex Terms—Recon􀀂gurable intelligent surfaces, localization, non-line-of-sight, machine learning, optimization  \nI. INTRODUCTION  \nRecon􀀂gurable Intelligent Surfaces (RIS) have gained signi􀀂cant attention in recent years due to their potential for highly relevant applications in the scope of 6G wireless communications [1] . A RIS has the advantage of being a lowpower solution. This low-power characteristic makes RISs a promising choice for energy-ef􀀂cient 6G wireless communication systems [2] . One of the especially interesting applications in which this technology shows great potential is localization in non-line-of-sight (NLoS) conditions [3], [4] . RISs have demonstrated the ability to overcome NLoS challenges by re􀀃ecting and manipulating wireless signals to achieve localization [5], a feature relevant for applications such as robot navigation, healthcare, and Industry 4.0 [6] . However, future applications expect localization accuracy within the centimeter [7] or even millimeter range [8], prompting recent works to focus on developing RIS-aided localization algorithms. These algorithms usually rely on a minimization of a cost function as the last step that results in the estimated position [9]–[11] .  \nThis work has been supported by the Smart Networks and Services Joint Undertaking (SNS JU) under the European Union’s Horizon Europe research and innovation programme under Grant Agreement No 10109710 (TERRAMETA), as well as by Component 5 - Capitalization and Business Innovation, integrated in the Resilience Dimension of the Recovery and Resilience Plan within the scope of the Recovery and Resilience Mechanism (MRR) of the European Union (EU), framed in the Next Generation EU, for the period 2021 - 2026, within project NEXUS, with reference 53.  \nIn this paper, we simulate NLoS RIS-based indoor localization of user equipment (UE) based on a mathematical model of the received re􀀃ections. We then apply to a cost function different optimization methods and compare the resulting localization error distributions.  \nThe paper is organized as follows. Section III introduces the problem formulation (Section III-A), its relation to the general system model (i.e., indoor location model and RIS tile architecture), and the evaluated optimization algorithms (Section III-B), including our proposed algorithms for improved accuracy. Section IV presents the experimental evaluation, describing the setup and speci􀀂c simulated room param","cbCaivEDpBbklxlm","https://ap.wps.com/l/cbCaivEDpBbklxlm","pdf",501661,5,1,6,"English","en",105,"# Introduction\n# Related Work\n# Proposed Approach\n# Experimental Evaluation\n## Optimization Setup and Algorithms","[{\"question\":\"What problem does the paper address in RIS-aided localization?\",\"answer\":\"The paper targets position estimation for mobile user equipment under non-line-of-sight (NLoS) conditions, where conventional localization can be insufficiently accurate.\"},{\"question\":\"Which optimization methods are proposed and evaluated?\",\"answer\":\"Two machine learning optimization algorithms are introduced, and four optimization techniques are compared, with GA and PSO combination producing the best accuracy in the reported simulations.\"},{\"question\":\"What localization accuracy results are reported in simulations?\",\"answer\":\"In a simulated 10 m by 10 m indoor room with RIS tiles, localization errors are under 30 cm in 90% of cases and under 5 mm in about 85% of cases.\"}]","Enhancing NLoS RIS-Aided Localization with Optimization and Machine Learning | PDF",1785902151,15,{"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":88,"head_meta":90,"extra_data":92,"updated_unix":29},"enhancing-nlos-ris-aided-localization-with-optimization-and-machine-learning","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/enhancing-nlos-ris-aided-localization-with-optimization-and-machine-learning/125942/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-25","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What problem does the paper address in RIS-aided localization?","Question",{"text":77,"@type":78},"The paper targets position estimation for mobile user equipment under non-line-of-sight (NLoS) conditions, where conventional localization can be insufficiently accurate.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"Which optimization methods are proposed and evaluated?",{"text":82,"@type":78},"Two machine learning optimization algorithms are introduced, and four optimization techniques are compared, with GA and PSO combination producing the best accuracy in the reported simulations.",{"name":84,"@type":75,"acceptedAnswer":85},"What localization accuracy results are reported in simulations?",{"text":86,"@type":78},"In a simulated 10 m by 10 m indoor room with RIS tiles, localization errors are under 30 cm in 90% of cases and under 5 mm in about 85% of cases.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,111,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"Comic",60,"comic",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":112,"show_sort_weight":113,"slug":114},"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":20,"slug":138},19,"General","general"]