{"id":"W4413677485","doi":"10.1109/jiot.2025.3602828","title":"LDA-FedHAR: Federated Human Activity Recognition for Wearable Devices Through Local HAR Data Alignment","year":2025,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Carleton University","funders":"Foundation Research Project of Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Wearable computer; Activity recognition; Wearable technology; Artificial intelligence; Speech recognition; Embedded system","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001000885,0.001407909,0.001744259,0.001138974,0.0005232111,0.0008933261,0.00188425,0.0007649831,0.002090686],"category_scores_gemma":[0.002594864,0.0003741973,0.001173091,0.001587734,0.0004228292,0.001674602,0.00248404,0.001299682,0.002687054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003329244,"about_ca_system_score_gemma":0.000642612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003293513,"about_ca_topic_score_gemma":0.006402313,"domain_scores_codex":[0.9988951,0.0002715671,0.00005950413,0.0004718524,0.0001916937,0.0001101922],"domain_scores_gemma":[0.9994162,0.0001245561,0.00005308415,0.0002474246,0.0001104375,0.00004825252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006493559,0.0005438849,0.00622346,0.0002336109,0.0002969433,0.0002422799,0.0002825404,0.04781272,0.01495895,0.001864736,0.02435997,0.9025316],"study_design_scores_gemma":[0.0001073964,0.0002464622,0.006781905,0.00004443436,0.00007532856,0.0005578792,0.0002812262,0.9532719,0.0153885,0.01116383,0.01198916,0.00009187953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0245278,0.0009900312,0.957819,0.0002239922,0.0001893884,0.0001200048,0.001352479,0.01346557,0.001311719],"genre_scores_gemma":[0.500384,0.0008201484,0.4780291,0.0007728048,0.0002398265,0.0006680123,0.01129621,0.0005289669,0.007260834],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003293513,"threshold_uncertainty_score":0.006994069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09561594755256243,"score_gpt":0.3406293162412762,"score_spread":0.2450133686887138,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}