{"id":"W2528898308","doi":"10.1007/s12652-016-0415-y","title":"Feature-level combination of skeleton joints and body parts for accurate aggressive and agitated behavior recognition","year":2016,"lang":"en","type":"article","venue":"Journal of Ambient Intelligence and Humanized Computing","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"","keywords":"Skeleton (computer programming); Computational intelligence; Feature (linguistics); Computer science; Artificial intelligence; Pattern recognition (psychology)","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":[0.0003729516,0.00009974522,0.0001950949,0.000155518,0.0001807003,0.00009231239,0.0001425046,0.00005130106,0.000002020552],"category_scores_gemma":[0.00008206453,0.00007307923,0.00004651347,0.0001052923,0.00007989765,0.0003479144,0.0000888412,0.00008652548,4.218506e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002009063,"about_ca_system_score_gemma":0.00001903722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004726297,"about_ca_topic_score_gemma":0.000001612211,"domain_scores_codex":[0.9991678,0.00003242797,0.0003742274,0.0001771638,0.000127597,0.0001207737],"domain_scores_gemma":[0.9982329,0.0001819103,0.0008952386,0.0000918591,0.0005327411,0.00006535955],"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":[0.00004957973,0.0001497631,0.0007137833,0.00004971252,0.00003624656,0.000006265614,0.0008334246,0.000002451215,0.02999746,0.01087951,0.000203347,0.9570785],"study_design_scores_gemma":[0.002762584,0.004395716,0.04929724,0.002385958,0.0002078689,0.001013278,0.0006455623,0.02824645,0.8163916,0.09247537,0.001398014,0.0007803849],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4594474,0.0001059376,0.5399373,0.0002562833,0.00006012151,0.0001675377,0.000003618037,0.00001404966,0.00000775394],"genre_scores_gemma":[0.9737899,0.0004049203,0.025684,0.00004388291,0.00003581303,0.000006839644,0.000001132286,0.000005541415,0.00002799359],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9562981,"threshold_uncertainty_score":0.2980085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06550070766336202,"score_gpt":0.3103618895993951,"score_spread":0.2448611819360331,"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."}}