{"id":513,"date":"2026-11-06T02:00:42","date_gmt":"2026-11-05T23:00:42","guid":{"rendered":"https:\/\/senthipoli.upb.ro\/?post_type=publicatie&#038;p=513"},"modified":"2026-11-06T02:18:19","modified_gmt":"2026-11-05T23:18:19","slug":"a-cross-session-benchmark-for-device-free-presence-detection-using-wi-fi-channel-state-information","status":"publish","type":"publicatie","link":"https:\/\/senthipoli.upb.ro\/en\/publicatii\/a-cross-session-benchmark-for-device-free-presence-detection-using-wi-fi-channel-state-information\/","title":{"rendered":"A Cross-Session Benchmark for Device-Free Presence Detection Using Wi-Fi Channel State Information"},"content":{"rendered":"<p class=\"wp-block-paragraph\">Wi-Fi Channel State Information (CSI) enables device-free presence sensing, but models trained in one session often degrade when the link geometry or room changes. We evaluate binary presence detection with a strict leave-one-session-out (LOSO) protocol over six sessions designed to induce controlled shifts (receiver displacement\/rotation, height change, corner placement, non-line-of-sight (NLoS) obstruction, and cross-room transfer). Each sample is a beacon-window CSI amplitude map (52 subcarriers \u00d7 8 beacons) processed with per-window normalization. Using identical windows, we benchmark a lightweight convolutional neural network (CNN) against a radial basis function (RBF) kernel support vector machine (SVM) across three representations: RAW amplitude, RAW plus temporal differences, and compact two-dimensional fast Fourier transform images. Beyond mean accuracy, we report false positives and false negatives to expose failure modes under shift. Results show that cross-room transfer is consistently the hardest condition and that errors are dominated by missed detections, highlighting the need for lightweight calibration or domain-robust training for deployment.<\/p>","protected":false},"featured_media":0,"template":"","meta":{"_kadence_starter_templates_imported_post":false,"_chips_autori":"Andrei \u021aaga, R\u0103zvan Cr\u0103ciunescu, R\u0103zvan Mihai, Mihnea Udrea, Constantin Pintilie","_chips_revista":"2026 IEEE International Black Seas Conference on Communications and Networking (BlackSeaCom)","_chips_data_accept":"","_chips_an_publicare":"2026","_chips_doi":"https:\/\/doi.org\/10.1109\/BlackSeaCom69760.2026.11598391","_chips_publicat_confirmat":true,"_chips_doi_provizoriu":false,"_chips_quartila":"","_chips_factor_impact":"","_chips_link_extern":"","_chips_link_pdf":"https:\/\/senthipoli.upb.ro\/wp-content\/uploads\/2026\/11\/A_Cross-Session_Benchmark_for_Device-Free_Presence_Detection_Using_Wi-Fi_Channel_State_Information.pdf","iawp_total_views":3,"footnotes":""},"tip_publicatie":[6],"tema_cercetare":[16],"class_list":["post-513","publicatie","type-publicatie","status-publish","hentry","tip_publicatie-conferinta","tema_cercetare-t7"],"blocksy_meta":{"styles_descriptor":{"styles":{"desktop":"","tablet":"","mobile":""},"google_fonts":[],"version":8}},"_links":{"self":[{"href":"https:\/\/senthipoli.upb.ro\/en\/wp-json\/wp\/v2\/publicatie\/513","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/senthipoli.upb.ro\/en\/wp-json\/wp\/v2\/publicatie"}],"about":[{"href":"https:\/\/senthipoli.upb.ro\/en\/wp-json\/wp\/v2\/types\/publicatie"}],"version-history":[{"count":1,"href":"https:\/\/senthipoli.upb.ro\/en\/wp-json\/wp\/v2\/publicatie\/513\/revisions"}],"predecessor-version":[{"id":514,"href":"https:\/\/senthipoli.upb.ro\/en\/wp-json\/wp\/v2\/publicatie\/513\/revisions\/514"}],"wp:attachment":[{"href":"https:\/\/senthipoli.upb.ro\/en\/wp-json\/wp\/v2\/media?parent=513"}],"wp:term":[{"taxonomy":"tip_publicatie","embeddable":true,"href":"https:\/\/senthipoli.upb.ro\/en\/wp-json\/wp\/v2\/tip_publicatie?post=513"},{"taxonomy":"tema_cercetare","embeddable":true,"href":"https:\/\/senthipoli.upb.ro\/en\/wp-json\/wp\/v2\/tema_cercetare?post=513"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}