{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000223782,0.0006346639,0.0006913237,0.001283807,0.0001749412,0.000298231,0.0004436146,0.0004823846,0.001423005],"category_scores_gemma":[0.0005569434,0.0002238484,0.0004093631,0.0009418422,0.0001645514,0.0003761954,0.0004320147,0.0004007495,0.001169645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001263785,"about_ca_system_score_gemma":0.000381399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00183509,"about_ca_topic_score_gemma":0.004827401,"domain_scores_codex":[0.9997867,0.00002254523,0.00001027605,0.00005916425,0.00007663692,0.00004480371],"domain_scores_gemma":[0.9997463,0.0000395665,0.00004874646,0.00003460695,0.0001011178,0.00002973887],"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":[0.0004137878,0.0002537708,0.01801185,0.0001426529,0.0001105955,0.0001945035,0.00006354119,0.008328935,0.2769144,0.000323273,0.003822753,0.6914199],"study_design_scores_gemma":[0.00003685218,0.0004572517,0.126526,0.0000433638,0.0002020361,0.001266259,0.0001331336,0.7930673,0.07285865,0.001394446,0.003949613,0.00006500739],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3523285,0.001270894,0.6375557,0.0001603123,0.0001693777,0.0001299108,0.001224724,0.004125931,0.003034649],"genre_scores_gemma":[0.8871418,0.0005035283,0.1079952,0.00007491435,0.00007114989,0.00008526108,0.001180309,0.0001256373,0.002822228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00183509,"threshold_uncertainty_score":0.004760385,"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."}}