{"id":240,"date":"2026-01-20T14:51:35","date_gmt":"2026-01-20T06:51:35","guid":{"rendered":"http:\/\/lasso.eee.sustech.edu.cn\/?page_id=240"},"modified":"2026-01-29T18:23:25","modified_gmt":"2026-01-29T10:23:25","slug":"%e5%8a%a8%e4%bd%9c%e8%af%86%e5%88%ab","status":"publish","type":"page","link":"http:\/\/lasso.eee.sustech.edu.cn\/?page_id=240","title":{"rendered":"\u52a8\u4f5c\u8bc6\u522b"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-page\" data-elementor-id=\"240\" class=\"elementor elementor-240\" data-elementor-post-type=\"page\">\n\t\t\t\t<div class=\"elementor-element elementor-element-656b06f e-flex e-con-boxed e-con e-parent\" data-id=\"656b06f\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-6331196 elementor-widget elementor-widget-heading\" data-id=\"6331196\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h1 class=\"elementor-heading-title elementor-size-default\">Human Activity Recognition<\/h1>\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-2cacece e-flex e-con-boxed e-con e-parent\" data-id=\"2cacece\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-d0f0c8a elementor-widget-divider--view-line elementor-widget elementor-widget-divider\" data-id=\"d0f0c8a\" data-element_type=\"widget\" data-widget_type=\"divider.default\">\n\t\t\t\t\t\t\t<div class=\"elementor-divider\">\n\t\t\t<span class=\"elementor-divider-separator\">\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-70859667 e-flex e-con-boxed e-con e-parent\" data-id=\"70859667\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-33dfde23 elementor-widget elementor-widget-text-editor\" data-id=\"33dfde23\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<div style=\"margin-bottom: 30px; padding: 30px; background: #f7fafc; border-radius: 12px; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.05); border: 1px dashed #cbd5e0;\"><h3 style=\"font-size: 20px; color: #2b6cb0; margin: 0px 0px 0px; font-weight: 600; text-align: left;\">\u00a0Simulation-Driven Performance Predictor and OPtimizer (SDP3)<\/h3><\/div><p><!-- \u6280\u672f\u65b9\u6848\u6a21\u677f --><\/p><div style=\"margin-bottom: 30px; padding: 30px; background: #f7fafc; border-radius: 12px; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.05); border: 1px dashed #cbd5e0;\"><h3 style=\"font-size: 20px; color: #2b6cb0; margin: 0 0 15px 0; font-weight: 600;\">Overview<\/h3><ul><li>This project proposes an SDP3 framework for the study of sensing-communication tradeoff with the particular application of human motion recognition. Specifically\uff1a<ol><li>The SDP3 data simulator with a data-driven hybrid channel model is proposed to generate the received sensing signals in a virtual environment.<\/li><li>The SDP3 performance predictor is then introduced to approximate the motion recognition accuracy via analytical expression with the simulated dataset of sensing signals.<\/li><li>The recognition accuracy and communication throughput tradeoff is characterized by the SDP3 performance optimizer.<\/li><\/ol><\/li><\/ul><p><img fetchpriority=\"high\" decoding=\"async\" class=\"aligncenter wp-image-545 size-full\" src=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72471-3.png\" alt=\"\" width=\"891\" height=\"403\" srcset=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72471-3.png 891w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72471-3-300x136.png 300w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72471-3-768x347.png 768w\" sizes=\"(max-width: 891px) 100vw, 891px\" \/><\/p><p style=\"text-align: center;\">Fig.1: The framework of the proposed DAHC model<\/p><\/div><p><!-- \u5b9e\u9a8c\u7ed3\u679c\u6a21\u677f --><\/p><div style=\"padding: 30px; background: #f7fafc; border-radius: 12px; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.05); border: 1px dashed #cbd5e0;\"><h3 style=\"font-size: 20px; color: #2b6cb0; margin: 0 0 15px 0; font-weight: 600;\">Result<\/h3><ul><li>It is demonstrated that the dataset generated by the SDP3 data simulator matches the experiment dataset in KL divergence, grayscale PMF and motion recognition accuracy. Hence, the sensing-communication tradeoff can be investigated without extensive experiments. It is also shown that the sensing and communication performance is balanced in the sensing\u0002communication adversarial zone of the A-T region, where both performance varies sensitively with respect to each other.<\/li><\/ul><p><img decoding=\"async\" class=\"size-full wp-image-547 aligncenter\" src=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72472-1.png\" alt=\"\" width=\"857\" height=\"619\" srcset=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72472-1.png 857w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72472-1-300x217.png 300w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72472-1-768x555.png 768w\" sizes=\"(max-width: 857px) 100vw, 857px\" \/><\/p><p style=\"text-align: center;\">Fig.2: Generated human motion datasets<\/p><p><img decoding=\"async\" class=\"wp-image-548 size-full aligncenter\" src=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72473.png\" alt=\"\" width=\"879\" height=\"480\" srcset=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72473.png 879w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72473-300x164.png 300w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72473-768x419.png 768w\" sizes=\"(max-width: 879px) 100vw, 879px\" \/><\/p><p style=\"text-align: center;\">Fig.3: The calibration results of DAHC model for walking in scenario 1 and 2.<\/p><p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-549 size-full\" src=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72474.png\" alt=\"\" width=\"884\" height=\"324\" srcset=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72474.png 884w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72474-300x110.png 300w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72474-768x281.png 768w\" sizes=\"(max-width: 884px) 100vw, 884px\" \/><\/p><p style=\"text-align: center;\">Fig.4: Comparison of recognition accuracy among the datasets generated by real experiments<\/p><\/div><p><!-- \u6837\u5f0f\u4f18\u5316 --><\/p><p><style>\n    div[style*=\"background: #f7fafc;\"]:hover {<br \/>      box-shadow: 0 6px 16px rgba(43, 108, 176, 0.15);<br \/>      transition: all 0.3s ease;<br \/>    }<br \/>    @media (max-width: 768px) {<br \/>      h2 { font-size: 24px !important; }<br \/>      h3 { font-size: 18px !important; }<br \/>      p, li { font-size: 14px !important; }<br \/>    }<br \/>  <\/style><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-3e37d38 e-flex e-con-boxed e-con e-parent\" data-id=\"3e37d38\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-deafdb8 elementor-widget-divider--view-line elementor-widget elementor-widget-divider\" data-id=\"deafdb8\" data-element_type=\"widget\" data-widget_type=\"divider.default\">\n\t\t\t\t\t\t\t<div class=\"elementor-divider\">\n\t\t\t<span class=\"elementor-divider-separator\">\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-b9ceaf3 e-flex e-con-boxed e-con e-parent\" data-id=\"b9ceaf3\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t<div class=\"elementor-element elementor-element-ff929d6 e-con-full e-flex e-con e-child\" data-id=\"ff929d6\" data-element_type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-5aee6c1 elementor-widget elementor-widget-text-editor\" data-id=\"5aee6c1\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<div style=\"margin-bottom: 30px; padding: 30px; background: #f7fafc; border-radius: 12px; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.05); border: 1px dashed #cbd5e0;\"><h3 style=\"font-size: 20px; color: #2b6cb0; margin: 0 0 0px 0; font-weight: 600;\">Human Activity Recognition Based on Wireless Channel Simulator<\/h3><\/div><p><!-- \u6280\u672f\u65b9\u6848\u6a21\u677f --><\/p><div style=\"margin-bottom: 30px; padding: 30px; background: #f7fafc; border-radius: 12px; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.05); border: 1px dashed #cbd5e0;\"><h3 style=\"font-size: 20px; color: #2b6cb0; margin: 0 0 15px 0; font-weight: 600;\">Overview<\/h3><ul><li>This project proposes a computer-vision-assisted simulation method to address the issue of training dataset acquisition for wireless hand gesture recognition. Specifically:<\/li><\/ul><ol><li style=\"list-style-type: none;\"><ol><li>This project addresses the critical issue of massive real-world data requirements for data-driven activity recognition. By leveraging a high-fidelity wireless channel simulator, it enables cost-effective generation of diverse human activity data for training.<\/li><li>An unsupervised sim-to-real transfer learning approach bridges the domain gap, enabling models trained on synthesized channel data to achieve significantly improved recognition accuracy when applied to actual measured data.<\/li><\/ol><\/li><\/ol><p><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-550 aligncenter\" src=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72475.png\" alt=\"\" width=\"764\" height=\"815\" srcset=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72475.png 764w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72475-281x300.png 281w\" sizes=\"(max-width: 764px) 100vw, 764px\" \/><\/p><p style=\"text-align: center;\">Fig.1: An Overview of the Simulation-Based Human Activity Recognition Methodology<\/p><p style=\"text-align: center;\"><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-551 aligncenter\" src=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72476.png\" alt=\"\" width=\"851\" height=\"727\" srcset=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72476.png 851w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72476-300x256.png 300w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72476-768x656.png 768w\" sizes=\"(max-width: 851px) 100vw, 851px\" \/> Fig.2: wireless channel simulator<\/p><\/div><p><!-- \u5b9e\u9a8c\u7ed3\u679c\u6a21\u677f --><\/p><div style=\"padding: 30px; background: #f7fafc; border-radius: 12px; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.05); border: 1px dashed #cbd5e0;\"><h3 style=\"font-size: 20px; color: #2b6cb0; margin: 0 0 15px 0; font-weight: 600;\">Result<\/h3><ul><li>Experimental results indicate that by first pre-training the model extensively on labeled synthetic data and then fine-tuning it with limited unlabeled real measurements, the simulation-to-real inference accuracy for human activity and gesture recognition can be boosted from 73% and 83% to 93.75% and 96%, respectively.<\/li><\/ul><p><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-565 aligncenter\" src=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724712.png\" alt=\"\" width=\"1025\" height=\"528\" srcset=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724712.png 1025w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724712-300x155.png 300w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724712-768x396.png 768w\" sizes=\"(max-width: 1025px) 100vw, 1025px\" \/><\/p><p style=\"text-align: center;\">Fig.3: Illustration of the simulated and experimental gesture dataset\u00a0<\/p><p><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-566 aligncenter\" src=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724713-scaled.jpg\" alt=\"\" width=\"2560\" height=\"1093\" srcset=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724713-scaled.jpg 2560w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724713-300x128.jpg 300w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724713-1024x437.jpg 1024w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724713-768x328.jpg 768w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724713-1536x656.jpg 1536w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724713-2048x875.jpg 2048w\" sizes=\"(max-width: 2560px) 100vw, 2560px\" \/><\/p><p style=\"text-align: center;\">Fig.4: Illustration of the simulated and experimental activity dataset\u00a0<\/p><p><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-564 aligncenter\" src=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724711.png\" alt=\"\" width=\"1441\" height=\"638\" srcset=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724711.png 1441w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724711-300x133.png 300w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724711-1024x453.png 1024w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724711-768x340.png 768w\" sizes=\"(max-width: 1441px) 100vw, 1441px\" \/><\/p><p style=\"text-align: center;\">Fig.5: Gesture Recognition Results: Before Fine-Tuning (Left) vs. After (Right) Fine-Tuning<\/p><p><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-567 aligncenter\" src=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724713.png\" alt=\"\" width=\"805\" height=\"334\" srcset=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724713.png 805w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724713-300x124.png 300w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724713-768x319.png 768w\" sizes=\"(max-width: 805px) 100vw, 805px\" \/><\/p><p style=\"text-align: center;\">Fig.6: Activity Recognition Results: Before Fine-Tuning (Left) vs. After (Right) Fine-Tuning<\/p><\/div><p><!-- \u6837\u5f0f\u4f18\u5316 --><\/p><p><style>\n    div[style*=\"background: #f7fafc;\"]:hover {<br \/>      box-shadow: 0 6px 16px rgba(43, 108, 176, 0.15);<br \/>      transition: all 0.3s ease;<br \/>    }<br \/>    @media (max-width: 768px) {<br \/>      h2 { font-size: 24px !important; }<br \/>      h3 { font-size: 18px !important; }<br \/>      p, li { font-size: 14px !important; }<br \/>    }<br \/>  <\/style><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-555b6cd e-flex e-con-boxed e-con e-parent\" data-id=\"555b6cd\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-8e3aa53 elementor-widget-divider--view-line elementor-widget elementor-widget-divider\" data-id=\"8e3aa53\" data-element_type=\"widget\" data-widget_type=\"divider.default\">\n\t\t\t\t\t\t\t<div class=\"elementor-divider\">\n\t\t\t<span class=\"elementor-divider-separator\">\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-6755597 e-flex e-con-boxed e-con e-parent\" data-id=\"6755597\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-36a3de9 elementor-widget elementor-widget-text-editor\" data-id=\"36a3de9\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<div style=\"margin-bottom: 30px; padding: 30px; background: #f7fafc; border-radius: 12px; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.05); border: 1px dashed #cbd5e0;\"><h3 style=\"font-size: 20px; color: #2b6cb0; margin: 0 0 0px 0; font-weight: 600;\">Passive Motion Detection via mmWave Communication System<\/h3><\/div><p><!-- \u6280\u672f\u65b9\u6848\u6a21\u677f --><\/p><div style=\"margin-bottom: 30px; padding: 30px; background: #f7fafc; border-radius: 12px; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.05); border: 1px dashed #cbd5e0;\"><h3 style=\"font-size: 20px; color: #2b6cb0; margin: 0 0 15px 0; font-weight: 600;\">Overview<\/h3><ul style=\"font-size: 16px; color: #718096; line-height: 1.8; padding-left: 20px; margin: 0; font-style: italic;\"><li>This project proposes an integrated passive sensing and communication system working in 60 GHz band, and the sensing performance is investigated in an application of hand gesture recognition. Specifically:<ol><li>A hardware setup featuring a single transmitter and a receiver with two RF chains enables analog beamforming. The transmitter emits a communication stream via dual beams: one for the main link and another directed at a gesture target. The receiver captures both signals separately for subsequent joint processing.<\/li><li>Through cross-ambiguity coherent processing of the two received signals, time-Doppler spectrograms of hand gestures are generated. A dataset containing three gesture types is built using both LoS and NLoS reference channels. This dataset is used to train a neural network model for motion detection and classification.<\/li><\/ol><\/li><\/ul><p><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-554 aligncenter\" src=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72479.png\" alt=\"\" width=\"481\" height=\"247\" srcset=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72479.png 481w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u72479-300x154.png 300w\" sizes=\"(max-width: 481px) 100vw, 481px\" \/><\/p><p style=\"text-align: center;\">Fig.1: Block diagram of system implementation<\/p><p><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-569 aligncenter\" src=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724714.png\" alt=\"\" width=\"826\" height=\"527\" srcset=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724714.png 826w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724714-300x191.png 300w, http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/\u56fe\u724714-768x490.png 768w\" sizes=\"(max-width: 826px) 100vw, 826px\" \/><\/p><p style=\"text-align: center;\">Fig.2: Experiment Layout.<\/p><\/div><p><!-- \u5b9e\u9a8c\u7ed3\u679c\u6a21\u677f --><\/p><div style=\"padding: 30px; background: #f7fafc; border-radius: 12px; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.05); border: 1px dashed #cbd5e0;\"><h3 style=\"font-size: 20px; color: #2b6cb0; margin: 0 0 15px 0; font-weight: 600;\">Result<\/h3><ul><li>It is shown by experiments that passive sensing in 60 GHz has a good resolution on the micro-Doppler effect of hand gestures as the classification accuracy is greater than 90%. It is also robust to link blockage as good classification accuracy can be achieved even the NLoS path is used as the reference channel.<\/li><\/ul><div style=\"width: 800px;\" class=\"wp-video\"><video class=\"wp-video-shortcode\" id=\"video-240-1\" width=\"800\" height=\"600\" preload=\"metadata\" controls=\"controls\"><source type=\"video\/mp4\" src=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/demo-1.mp4?_=1\" \/><a href=\"http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/demo-1.mp4\">http:\/\/lasso.eee.sustech.edu.cn\/wp-content\/uploads\/2026\/01\/demo-1.mp4<\/a><\/video><\/div><p style=\"text-align: left;\">\u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0Demo<\/p><\/div><p><!-- \u6837\u5f0f\u4f18\u5316 --><\/p><p><style>\n    div[style*=\"background: #f7fafc;\"]:hover {<br \/>      box-shadow: 0 6px 16px rgba(43, 108, 176, 0.15);<br \/>      transition: all 0.3s ease;<br \/>    }<br \/>    @media (max-width: 768px) {<br \/>      h2 { font-size: 24px !important; }<br \/>      h3 { font-size: 18px !important; }<br \/>      p, li { font-size: 14px !important; }<br \/>    }<br \/>  <\/style><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Human Activity Recognition \u00a0Simulation-Driven Performance Predictor and OPtimizer (SDP3) Overview This project proposes an SDP3 framework for the stud&hellip;<\/p>\n<p> <a class=\"more-link\" href=\"http:\/\/lasso.eee.sustech.edu.cn\/?page_id=240\">\u7ee7\u7eed\u9605\u8bfb<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":36,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-240","page","type-page","status-publish"],"_links":{"self":[{"href":"http:\/\/lasso.eee.sustech.edu.cn\/index.php?rest_route=\/wp\/v2\/pages\/240","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/lasso.eee.sustech.edu.cn\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/lasso.eee.sustech.edu.cn\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/lasso.eee.sustech.edu.cn\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/lasso.eee.sustech.edu.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=240"}],"version-history":[{"count":47,"href":"http:\/\/lasso.eee.sustech.edu.cn\/index.php?rest_route=\/wp\/v2\/pages\/240\/revisions"}],"predecessor-version":[{"id":604,"href":"http:\/\/lasso.eee.sustech.edu.cn\/index.php?rest_route=\/wp\/v2\/pages\/240\/revisions\/604"}],"up":[{"embeddable":true,"href":"http:\/\/lasso.eee.sustech.edu.cn\/index.php?rest_route=\/wp\/v2\/pages\/36"}],"wp:attachment":[{"href":"http:\/\/lasso.eee.sustech.edu.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=240"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}