{"id":4172,"date":"2025-10-24T15:16:52","date_gmt":"2025-10-24T15:16:52","guid":{"rendered":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?page_id=4172"},"modified":"2025-10-24T15:16:52","modified_gmt":"2025-10-24T15:16:52","slug":"csi%e2%86%92voxel-wi-fi-sensing-as-a-low-cost-fmri-proxy","status":"publish","type":"page","link":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/?page_id=4172","title":{"rendered":"CSI\u2192Voxel: Wi-Fi Sensing as a Low-Cost fMRI Proxy"},"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\/10\/Wi-Fi-Sensing-as-a-Low-Cost-fMRI-Proxy-CSI-Voxel-Engine.pdf\" type=\"application\/pdf\" style=\"width:100%;height:600px\" aria-label=\"Embed of Wi-Fi Sensing as a Low-Cost fMRI Proxy CSI Voxel Engine.\"><\/object><a id=\"wp-block-file--media-f7b97160-ec62-4b51-8f87-af51004b6bba\" href=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/10\/Wi-Fi-Sensing-as-a-Low-Cost-fMRI-Proxy-CSI-Voxel-Engine.pdf\">Wi-Fi Sensing as a Low-Cost fMRI Proxy CSI Voxel Engine<\/a><a href=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/10\/Wi-Fi-Sensing-as-a-Low-Cost-fMRI-Proxy-CSI-Voxel-Engine.pdf\" class=\"wp-block-file__button wp-element-button\" download aria-describedby=\"wp-block-file--media-f7b97160-ec62-4b51-8f87-af51004b6bba\">Download<\/a><\/div>\n\n\n\n<p class=\"wp-block-paragraph\">Functional magnetic resonance imaging (fMRI) provides<br>high-resolution, voxel-wise measurements of brain activity, but<br>acquiring large-scale fMRI datasets is expensive, immobile,<br>and time-consuming. At the same time, commodity wireless<br>devices continually capture channel state information (CSI)<br>\u2014 a rich, multi-dimensional signal that reflects environmental<br>changes and human motion. This paper investigates whether<br>carefully processed CSI can serve as a low-cost, portable<br>proxy for coarse voxel-wise neural activation in controlled<br>experimental paradigms.<br>Our goal is not to replace fMRI, but to explore whether CSI<br>contains enough information to reconstruct low-dimensional<br>summaries of neural activity and to detect block-like activation<br>patterns under controlled conditions. If successful, such a<br>proxy could enable inexpensive, mobile monitoring and rapid<br>prototyping of neuroimaging-inspired interfaces.<br>Challenges. Mapping CSI to voxel-like signals presents<br>several technical challenges: (i) differing sampling rates and<br>clocks (Wi-Fi CSI is sampled at high frequency while fMRI<br>TRs are much slower), (ii) unknown and time-varying delays<br>(clock offsets and drift) between sensors, (iii) heterogeneity<br>across subcarriers and receiving antennas, and (iv) severe,<br>structured noise due to multipath and non-neural motion.<br>Addressing these requires robust preprocessing, alignment,<br>and decoder design that tolerate misalignment and domain<br>mismatch.<br>Approach. We present a simulation-led pipeline that synthesizes paired CSI and voxel-like time series under controlled<br>offsets and drift, applies alignment and time-warping to synchronize signals, and trains simple linear decoders to predict<br>voxel activity from aggregated CSI features. The pipeline<br>produces three primary figures: (1) alignment timelines (before\/after), (2) per-voxel correlation distributions, and (3) ROC<br>curves for block-activity detection. All scripts and synthetic<br>data are provided so results are reproducible and the pipeline<br>can be reused as a test harness.<br>Contributions. This work makes four concrete contributions:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>A compact, reproducible simulation and processing<br>pipeline that generates paired CSI and voxel signals with<br>configurable offsets and drift.<\/li>\n\n\n\n<li>A lightweight alignment method (lag estimation + linear<br>time-warp) that corrects clock offsets and drift between<br>modalities.<\/li>\n\n\n\n<li>An empirical evaluation showing that aggregated CSI<br>features, coupled with simple ridge decoders, recover<br>coarse voxel activity and detect block activations with<br>non-trivial AUC in simulation.<\/li>\n\n\n\n<li>A small, self-contained LaTeX project (scripts, figures,<br>and captions) that demonstrates the pipeline and provides<br>a press-style build target for rapid iteration.<br>Outline. The remainder of the paper is organized as follows.<br>Section II describes the synthetic data generation, feature extraction, and alignment procedures. Section III details the experimental settings and evaluation metrics. Section ?? presents<br>the alignment, correlation, and ROC figures, and Section ??<br>discusses limitations and next steps toward real-world CSI-tovoxel evaluation.<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Functional magnetic resonance imaging (fMRI) provideshigh-resolution, voxel-wise measurements of brain activity, butacquiring large-scale fMRI datasets is expensive, immobile,and time-consuming. At the same time, commodity wirelessdevices continually capture channel state information (CSI)\u2014 a rich, multi-dimensional signal that reflects environmentalchanges and human motion. This paper investigates whethercarefully processed CSI can serve as a low-cost, portableproxy for coarse&hellip;&nbsp;<\/p>\n","protected":false},"author":2,"featured_media":4174,"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-4172","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\/4172","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=4172"}],"version-history":[{"count":0,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages\/4172\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/media\/4174"}],"wp:attachment":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4172"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}