[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83337-en":3,"doc-seo-83337-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83337,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Generalization Theory for Through-the-Wall Radar Human Activity Recognition","Through-the-wall radar (TWR) human activity recognition (HAR) enables non-line-of-sight indoor sensing for security monitoring and emergency rescue, yet structured distribution shifts from person variation, observation-view variation, and wall-condition variation significantly weaken generalization. The work proposes a rigorous generalization-analysis framework for TWR HAR by building unified source-to-target learning models for kinematics, echo generation, image formation, feature representation, and bounded-weight neural networks. It derives a target-domain generalization bound, decomposes the structured shift, and analyzes tightening effects via low-dimensional physical representations, multi-source training, and parameter-space coverage, validated by simulated and measured experiments.","arXiv :2607 .08 144v 1 [ cs .IT] 9 Jul 2026  \nGeneralization Theory for Through-the-Wall Radar  \nHuman Activity Recognition  \nWeicheng Gao ID, Graduate Student Member, IEEE  \nAbstract  \nThrough-the-wall radar (TWR) human activity recognition (HAR) is important for non-line-of-sight indoor sensing, security monitoring, and emergency rescue. However, structured distribution shifts caused by person variation, observation-view variation, and wall-condition variation severely degrade recognition generalization, while the origin of the target-domain error still lacks a rigorous theoretical explanation. To address this issue, a generalization-analysis framework for TWR HAR is proposed in this paper. First, models for indoor human kinematics, TWR echo generation, radar image formation, feature representation, and boundedweight neural networks are established within a unified source-to-target learning formulation. Then, the source risk, target risk, empirical risk, and admissible physical domain descriptor are defined, and a unified target-domain generalization bound is derived. Next, the structured shift term is decomposed into cross-person, cross-view, and cross-wall components, and the bound-tightening effects of physical low-dimensional representations, multi-source training, and parameter-space coverage are analyzed. Simulated and measured experiments jointly support the resulting theoretical analysis and illustrate its application value.  \nIndex Terms  \nThrough-the-wall radar (TWR), human activity recognition (HAR), micro-Doppler signature, generalization error bound.  \nI. INTRODUCTION  \nThrough-the-wall radar (TWR) human activity recognition (HAR) is intended to recognize human motions from radar echoes collected under non-line-of-sight sensing conditions. Unlike optical cameras and wearable sensors, TWR can preserve sensing capability when the body is hidden by occlusion, weak illumination, smoke, or wall obstruction. This capability has supported studies on real-time through-the-wall activity recognition [1], single-channel ultrawideband pose estimation [2], radar-systemagnostic HAR [3], through-the-wall posture reconstruction [4], range-max enhanced behind-the-wall micro-Doppler analysis [5], channel-capacity-aware fine-grained multiple-input multiple-output (MIMO) classification [6], mixed convolutional neural network (CNN) multi-spectrogram recognition [7], and time-frequency-enhanced through-wall localization [8] . A broader review of recent TWR HAR development was also reported in [9] . However, the main difficulty of TWR HAR is not merely empirical classification accuracy. The training and testing data are often separated by structured distribution shifts induced by radar propagation, human motion, and observation geometry. Three representative difficulties are cross-person generalization, crossview generalization, and cross-wall generalization. In cross-person generalization, body structure, gait pattern, limb swing, motion velocity, and motion phase change the micro-Doppler features and radar-image distribution, as also reflected in subjectdependent activity-classification and fine-grained recognition studies [10] . In cross-view generalization, human motion direction and radar view angle modify the radial-velocity projection, Doppler frequency shift, micro-Doppler signature, and Doppler-time representation, which is closely related to multistatic orientation-sensitive and lightweight multiview radar recognition [11]–[13] . In cross-wall generalization, wall material, thickness, permittivity, loss, and structure alter the through-wall propagation operator, causing attenuation, multipath, clutter, low signal-to-noise ratios, and changed noise statistics, as reported in measured MIMO through-the-wall HAR experiments [14] .  \nExisting radar HAR and TWR HAR methods were mostly designed to improve empirical recognition performance. Handcrafted micro-Doppler descriptors and time-frequency pipelines [15], [16], deep recurrent","cbCaiocmTRrpZG8b","https://ap.wps.com/l/cbCaiocmTRrpZG8b","pdf",29990590,3,1,38,"English","en",105,"# Introduction\n## Cross-person generalization\n## Cross-view generalization\n## Cross-wall generalization\n# Proposed generalization-analysis framework\n## Unified source-to-target learning formulation\n## Risk definitions and generalization bound\n## Structured shift decomposition and bound tightening analysis\n# Experiments and results\n## Simulated and measured validation","[{\"question\":\"Why does generalization degrade in through-the-wall radar (TWR) human activity recognition?\",\"answer\":\"Structured distribution shifts caused by person variation, observation-view variation, and wall-condition variation change radar-image distributions and micro-Doppler features, leading to large generalization error.\"},{\"question\":\"What is the core contribution of the paper’s generalization-analysis framework?\",\"answer\":\"It establishes unified models for TWR HAR within a source-to-target learning formulation, defines source/target/empirical risks, and derives a unified target-domain generalization bound.\"},{\"question\":\"How is the structured shift term handled in the proposed theory?\",\"answer\":\"The framework decomposes the structured shift into cross-person, cross-view, and cross-wall components, then analyzes how low-dimensional physical representations, multi-source training, and parameter-space coverage tighten the bound.\"}]",1784186844,96,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"generalization-theory-for-through-the-wall-radar-human-activity-recognition","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/generalization-theory-for-through-the-wall-radar-human-activity-recognition/83337/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why does generalization degrade in through-the-wall radar (TWR) human activity recognition?","Question",{"text":75,"@type":76},"Structured distribution shifts caused by person variation, observation-view variation, and wall-condition variation change radar-image distributions and micro-Doppler features, leading to large generalization error.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the core contribution of the paper’s generalization-analysis framework?",{"text":80,"@type":76},"It establishes unified models for TWR HAR within a source-to-target learning formulation, defines source/target/empirical risks, and derives a unified target-domain generalization bound.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the structured shift term handled in the proposed theory?",{"text":84,"@type":76},"The framework decomposes the structured shift into cross-person, cross-view, and cross-wall components, then analyzes how low-dimensional physical representations, multi-source training, and parameter-space coverage tighten the bound.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]