{"id":"W4382119007","doi":"10.1109/tim.2023.3289547","title":"A WiFi-Based Method for Recognizing Fine-Grained Multiple-Subject Human Activities","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Indoor and Outdoor Localization Technologies","field":"Engineering","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Support vector machine; Computer science; Random forest; Artificial intelligence; Pattern recognition (psychology); Naive Bayes classifier; Feature (linguistics); Decision tree; Linear discriminant analysis; Feature extraction; Activity recognition; F1 score; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003296474,0.0001682624,0.0001486262,0.0004715232,0.000309645,0.00004985735,0.00005819211,0.00008355729,0.00001992956],"category_scores_gemma":[0.00001458515,0.0001752963,0.00007886226,0.0003736568,0.00003019215,0.0001147244,5.5131e-7,0.0001060545,0.000006677275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001452567,"about_ca_system_score_gemma":0.00002212754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001417189,"about_ca_topic_score_gemma":0.0001868083,"domain_scores_codex":[0.9990779,0.00003192843,0.0002325926,0.0001919272,0.0002494543,0.0002162501],"domain_scores_gemma":[0.9996498,0.00008645284,0.00003409549,0.0001205695,0.00006464026,0.0000444488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001402471,0.000101903,0.00009553807,0.0004131438,0.0002284129,0.000001356799,0.001132082,0.1660278,0.320148,0.0003489064,0.0009318288,0.5104309],"study_design_scores_gemma":[0.002142485,0.0001524115,0.0001525181,0.00007050556,0.00005211676,0.000001104578,0.0009745451,0.1495697,0.8452851,0.0001852099,0.001173517,0.0002407711],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05182782,0.0000113722,0.945531,0.0001518356,0.0004962137,0.0005459549,0.00005273896,0.001184154,0.0001989186],"genre_scores_gemma":[0.9915987,0.00002394826,0.007614851,0.00007685944,0.00001940469,0.0005100113,0.00002522915,0.00003496243,0.00009608251],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9397708,"threshold_uncertainty_score":0.7148376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05817660343010973,"score_gpt":0.2862673068865761,"score_spread":0.2280907034564664,"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."}}