{"id":3483,"date":"2025-09-19T19:43:00","date_gmt":"2025-09-19T19:43:00","guid":{"rendered":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?page_id=3483"},"modified":"2025-09-19T19:43:00","modified_gmt":"2025-09-19T19:43:00","slug":"on-device-rf-filtering-compression-for-wearables","status":"publish","type":"page","link":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/?page_id=3483","title":{"rendered":"On-Device RF Filtering &amp; Compression for Wearables"},"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=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/09\/On-Device-RF-Filtering-Compression-for-Wearables.pdf\" type=\"application\/pdf\" style=\"width:100%;height:600px\" aria-label=\"Embed of On-Device RF Filtering &amp; Compression for Wearables.\"><\/object><a id=\"wp-block-file--media-f7ad75d4-8731-4e5f-ad50-4454da2aa2d2\" href=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/09\/On-Device-RF-Filtering-Compression-for-Wearables.pdf\">On-Device RF Filtering &#038; Compression for Wearables<\/a><a href=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/09\/On-Device-RF-Filtering-Compression-for-Wearables.pdf\" class=\"wp-block-file__button wp-element-button\" download aria-describedby=\"wp-block-file--media-f7ad75d4-8731-4e5f-ad50-4454da2aa2d2\">Download<\/a><\/div>\n\n\n\n<p class=\"wp-block-paragraph\">Head-mounted augmented-reality (AR) devices are<br>increasingly used by first responders and military medics to<br>visualize radio-frequency (RF) tracks, casualty vitals and threat<br>signatures in real time. These platforms operate under severe<br>resource constraints: the computational budget is on the order<br>of tens of milliseconds, the power budget is under one watt, and<br>the thermal headroom is limited by the user\u2019s skin. Prior work<br>demonstrated that RF\u2013AR situational awareness can be achieved<br>within \u223c200 ms end-to-end on uncompressed networks. However,<br>the neural networks used for classification and localization are<br>heavily over-parameterized, leading to energy-intensive inference<br>and lengthy stalls on battery-powered wearables. To tackle this<br>problem, we present a pipeline for on-device RF filtering and<br>compression that combines quantization, sparsity and knowledge<br>distillation to shrink models without compromising mission utility. Quantization reduces the precision of weights and activations,<br>lowering memory footprints and enabling faster integer arithmetic [1], while magnitude-based pruning removes unimportant<br>parameters and accelerates inference [2]. Recent studies show<br>that pruning and quantization jointly diminish computational<br>and memory requirements [3] but must be applied carefully<br>because their effects are non-orthogonal [4]. We further employ<br>teacher\u2013student knowledge distillation, transferring knowledge<br>from a high-capacity \u201dteacher\u201d network to a lightweight \u201dstudent\u201d model [5], [6]. Our experiments on Jetson-class edge devices<br>and Pixel-8 smartphones sweep multiple quantization bit-widths<br>and sparsity levels, producing accuracy\u2013latency\u2013power Pareto<br>curves. At 50 ms median latency and 0.9 W average power, our<br>distilled INT8\/70 % sparse student attains within 1 % of baseline<br>accuracy, yielding &gt;5\u00d7 energy savings. Hardware-aware model<br>compression techniques [7] and adaptive bit-width selection [8]<br>enable deployment on resource-constrained wearable platforms.<br>We release our code, datasets and measurement harness to foster<br>reproducible research in RF\u2013AR compression.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Head-mounted augmented-reality (AR) devices areincreasingly used by first responders and military medics tovisualize radio-frequency (RF) tracks, casualty vitals and threatsignatures in real time. These platforms operate under severeresource constraints: the computational budget is on the orderof tens of milliseconds, the power budget is under one watt, andthe thermal headroom is limited by the user\u2019s skin.&hellip;&nbsp;<\/p>\n","protected":false},"author":2,"featured_media":3552,"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-3483","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\/3483","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=3483"}],"version-history":[{"count":0,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages\/3483\/revisions"}],"wp:attachment":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3483"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}