{"id":3485,"date":"2025-09-16T20:27:11","date_gmt":"2025-09-16T20:27:11","guid":{"rendered":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?page_id=3485"},"modified":"2025-09-16T20:27:11","modified_gmt":"2025-09-16T20:27:11","slug":"policy-driven-rf-denoising-for-adaptive-geolocation-fft-domain-filtering","status":"publish","type":"page","link":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/?page_id=3485","title":{"rendered":"Policy Driven RF Denoising for Adaptive Geolocation FFT-Domain Filtering"},"content":{"rendered":"\n<div data-wp-interactive=\"core\/file\" class=\"wp-block-file\"><object data-wp-bind--hidden=\"!state.hasPdfPreview\" hidden class=\"wp-block-file__embed\" data=\"http:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/Policy-Driven-RF-Denoising-for-Adaptive-Geolocation-FFT-Domain-Filtering-Benjamin-J-Gilbert-College-of-the-Mainland-1.pdf\" type=\"application\/pdf\" style=\"width:100%;height:600px\" aria-label=\"Embed of Policy Driven RF Denoising for Adaptive Geolocation FFT-Domain Filtering Benjamin J Gilbert College of the Mainland.\"><\/object><a id=\"wp-block-file--media-85ddc707-6964-4b76-ae37-315682793a97\" href=\"http:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/Policy-Driven-RF-Denoising-for-Adaptive-Geolocation-FFT-Domain-Filtering-Benjamin-J-Gilbert-College-of-the-Mainland-1.pdf\">Policy Driven RF Denoising for Adaptive Geolocation FFT-Domain Filtering Benjamin J Gilbert College of the Mainland<\/a><a href=\"http:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/Policy-Driven-RF-Denoising-for-Adaptive-Geolocation-FFT-Domain-Filtering-Benjamin-J-Gilbert-College-of-the-Mainland-1.pdf\" class=\"wp-block-file__button wp-element-button\" download aria-describedby=\"wp-block-file--media-85ddc707-6964-4b76-ae37-315682793a97\">Download<\/a><\/div>\n\n\n\n<p class=\"wp-block-paragraph\">We propose a policy-driven RF denoising framework<br>in which reinforcement learning (RL) adaptively controls FFT domain filters to minimize timing and correlation errors in<br>passive geolocation. Unlike static low-pass or notch filters, the<br>policy selects denoising actions in real time based on residual<br>time-difference-of-arrival (TDoA) error and correlation entropy,<br>providing a feedback loop that directly targets physical error<br>metrics. Experiments on synthetic RF sequences with and without<br>narrowband jammers demonstrate that the learned policies<br>converge rapidly and consistently outperform fixed filtering<br>strategies, yielding 28.6% reduction in TDoA residuals and 45%<br>improvement in jammer conditions across SNR sweeps. Ablation<br>on the entropy-weight \u03bb confirms its role in balancing timing<br>fidelity with spectral purity, with optimal performance at \u03bb = 0.5.<br>Before\/after spectrograms illustrate the qualitative suppression of<br>jammer tones and the restoration of signal structure. By framing<br>reinforcement learning as a controller for adaptive denoising, this<br>work extends classical signal processing approaches with data driven adaptability, while retaining interpretability, deployability,<br>and tight alignment with RF timing accuracy.<br>Index Terms\u2014RF signal processing, adaptive denoising, reinforcement learning, time-difference-of-arrival, geolocation, FFT<br>filtering, jammer suppression<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We propose a policy-driven RF denoising frameworkin which reinforcement learning (RL) adaptively controls FFT domain filters to minimize timing and correlation errors inpassive geolocation. Unlike static low-pass or notch filters, thepolicy selects denoising actions in real time based on residualtime-difference-of-arrival (TDoA) error and correlation entropy,providing a feedback loop that directly targets physical errormetrics. Experiments on&hellip;&nbsp;<\/p>\n","protected":false},"author":2,"featured_media":1986,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"neve_meta_sidebar":"","neve_meta_container":"","neve_meta_enable_content_width":"","neve_meta_content_width":0,"neve_meta_title_alignment":"","neve_meta_author_avatar":"","neve_post_elements_order":"","neve_meta_disable_header":"","neve_meta_disable_footer":"","neve_meta_disable_title":"","footnotes":""},"class_list":["post-3485","page","type-page","status-publish","has-post-thumbnail","hentry"],"_links":{"self":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages\/3485","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3485"}],"version-history":[{"count":0,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages\/3485\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/media\/1986"}],"wp:attachment":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3485"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}