[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83417-en":3,"doc-seo-83417-105":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":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":13,"seo_description":14,"update_tm":28,"read_time":29},83417,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Deep Learning for Joint Narrowband Interference Cancellation and Soft Demodulation in OFDM Systems","Narrowband interference (NBI) disrupts orthogonal frequency-division multiplexing (OFDM) by corrupting subcarriers and undermining classical soft demodulation, driving unreliable log-likelihood ratios (LLRs), decoder saturation, and severe error floors. A unified deep learning framework jointly cancels NBI and performs robust soft demodulation: NBI-CNet estimates and removes multi-tone interference in a single physics-informed forward pass, while LLR-CNet whitens non-Gaussian residuals into well-calibrated soft metrics. Simulations show elimination of error floors with coding gain exceeding 3 dB and robustness to interferer-estimation errors and varying FFT sizes without retraining.","Deep Learning for Joint Narrowband Interference Cancellation and Soft Demodulation in  \nOFDM Systems  \nEmmanouil Kavvousanos∗ , Francky Catthoor† and Vassilis Paliouras∗  \n∗Department of Electrical and Computer Engineering, University of Patras, Greece †Department of Electrical and Computer Engineering, National Technical University of Athens, Greece  \n9 Jul 2026  \nAbstract—Narrowband interference (NBI) severely degrades orthogonal frequency-division multiplexing (OFDM) systems by corrupting subcarriers and rendering classical soft demodulation ineffective. Conventional compressed-sensing (CS) mitigation exhibits high sequential latency and leaves structured, non-Gaussian residuals that cause log-likelihood ratio (LLR) unreliability, decoder saturation, and severe error floors when employing classical Gaussian demappers. We resolve this pipeline mismatch using a unified deep learning framework for joint NBI cancellation and robust soft demodulation. First, NBI-CNet employs a physics-informed convolutional architecture to estimate NBI parameters and remove multi-tone interference in a single forward pass. Without requiring prior knowledge of the active interferer count, NBI-CNet reduces computational complexity by up to 60% (N=2048, Q=64) compared to the state-of-the-art EOMP-IDS algorithm. Second, LLR-CNet acts as a structural whitener by mapping non-Gaussian post-mitigation residuals onto well-calibrated soft metrics. Simulations demonstrate that this joint framework eliminates the error floors inherent to  \narXiv :2607 .08717v1  \ncoding gain exceeding 3 dB. Finally, the architecture circumventsthe 2 × 10 −4 error floor triggered by interferer-estimation errors, while its scale-invariant design enables robust generalization across arbitrary FFT sizes without retraining.  \nI. INTRODUCTION  \nTHE transition toward fifth-generation (5G), beyond-5G,  \nand sixth-generation (6G) wireless networks features an exponential increase in device density and heterogeneous architectures designed for services like URLLC, mMTC, and eMBB [1]–[3] . This evolution integrates terrestrial cellular networks with UAVs [4], satellite multibeam systems [5], and integrated sensing and communication [6] . While these multi-tier layouts enhance global connectivity and spectrum utilization, they introduce severe interference challenges. As the RF spectrum becomes congested, the primary performance bottleneck shifts from a noise-limited to an interference-limited regime [7], necessitating robust detection and mitigation frameworks. This challenge is especially critical in the 6G FR3 upper midband (7.125–24.25 GHz), which offers substantial bandwidth but requires strict coexistence with incumbent satellite and defense services [8], [9] . Dense terrestrial base stations can  \ngenerate severe RFI toward satellite receivers via unintended sidelobe leakage and multipath reflections [9] . Consequently, realizing the full potential of the FR3 spectrum demands multidimensional spectrum management to protect incumbentsand mitigate inter-tier and intra-network interference [8], [10] .  \nWithin this congested landscape, narrowband interference (NBI) poses an acute threat to wideband communication systems [11], particularly those utilizing orthogonal frequency division multiplexing (OFDM) [12], [13] . This threat natively arises where uncoordinated narrowband transmitters (such as dense IoT networks, legacy broadcasting, or industrial sensors) overlap with this wideband spectrum [14], [15] . This coexistence is increasingly prevalent in unlicensed bands, power line communications (PLC), and scenarios like NB-IoT sharing in-band LTE spectrum [16]–[18] . In OFDM architectures, NBI disrupts subcarrier orthogonality. Because uncoordinated transmissions are typically asynchronous to the receiver’s grid, their power inevitably leaks across adjacent subcarriers, degrading data recovery across a wide bandwidth [12], [19] . This degradation is exacerbated when closely spaced to","cbCaikuDL9F4h95K","https://ap.wps.com/l/cbCaikuDL9F4h95K","pdf",643943,5,1,17,"English","en",105,"# Introduction\n## Motivation: 5G/6G and interference-limited operation\n## Why NBI is harmful to OFDM\n## Limits of static NBI models\n## Existing NBI mitigation approaches","[{\"question\":\"Why does narrowband interference severely degrade OFDM performance?\",\"answer\":\"NBI destroys subcarrier orthogonality by leaking power into adjacent subcarriers, which degrades data recovery across wide bandwidths. Closely spaced tones can further cause overlapping spectral effects that limit classical suppression methods.\"},{\"question\":\"What is the key contribution of the proposed deep learning framework?\",\"answer\":\"It unifies NBI cancellation and robust soft demodulation to fix the mismatch between interference mitigation outputs and classical Gaussian-based soft metrics. The approach uses NBI-CNet for physics-informed parameter estimation and LLR-CNet for structural whitening of non-Gaussian residuals.\"},{\"question\":\"How does the method reduce computational complexity and error floors?\",\"answer\":\"NBI-CNet estimates NBI parameters and removes multi-tone interference in a single forward pass, reducing computation by up to 60% versus a state-of-the-art EOMP-IDS method for the stated setting. The joint design eliminates inherent error floors and is robust to interferer-estimation errors while generalizing across FFT sizes without retraining.\"}]",1784187458,43,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"deep-learning-for-joint-narrowband-interference-cancellation-and-soft-demodulation-in-ofdm-systems","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"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/deep-learning-for-joint-narrowband-interference-cancellation-and-soft-demodulation-in-ofdm-systems/83417/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"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","2026-07-25","2026-07-16",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},"Why does narrowband interference severely degrade OFDM performance?","Question",{"text":76,"@type":77},"NBI destroys subcarrier orthogonality by leaking power into adjacent subcarriers, which degrades data recovery across wide bandwidths. Closely spaced tones can further cause overlapping spectral effects that limit classical suppression methods.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What is the key contribution of the proposed deep learning framework?",{"text":81,"@type":77},"It unifies NBI cancellation and robust soft demodulation to fix the mismatch between interference mitigation outputs and classical Gaussian-based soft metrics. The approach uses NBI-CNet for physics-informed parameter estimation and LLR-CNet for structural whitening of non-Gaussian residuals.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the method reduce computational complexity and error floors?",{"text":85,"@type":77},"NBI-CNet estimates NBI parameters and removes multi-tone interference in a single forward pass, reducing computation by up to 60% versus a state-of-the-art EOMP-IDS method for the stated setting. The joint design eliminates inherent error floors and is robust to interferer-estimation errors while generalizing across FFT sizes without retraining.","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":25},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,128,131,135],{"id":21,"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":20,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"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":20,"slug":138},19,"General","general"]