{"id":"W4302025110","doi":"10.36227/techrxiv.21215069.v1","title":"Intelligent Human Anomaly Identification and Classification in Crowded Scenes via Multi-fused Features and Restricted Boltzmann Machines","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Stochastic gradient descent; Word error rate; Cluster analysis; Classifier (UML); Anomaly detection; Boltzmann machine; Restricted Boltzmann machine; Gradient descent; Feature engineering; Machine learning; Data mining; Deep learning; Artificial neural network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003376547,0.0002864566,0.0002734842,0.0005804866,0.0003862448,0.0004961322,0.0007521251,0.0002329156,0.00002527646],"category_scores_gemma":[0.00002791029,0.0002920205,0.00006167616,0.0005322959,0.00009431808,0.0002318507,0.001292025,0.0005681113,0.000003190469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001215989,"about_ca_system_score_gemma":0.00004617624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001147028,"about_ca_topic_score_gemma":0.0005093045,"domain_scores_codex":[0.9977598,0.0001553348,0.0005963517,0.001057971,0.0002297888,0.000200794],"domain_scores_gemma":[0.9984319,0.00005731365,0.0003735226,0.0009462317,0.0001033945,0.00008766451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00007104444,0.002023471,0.08100212,0.0007876547,0.0001811498,0.00002979831,0.004297728,0.0006420147,0.3273719,0.221845,0.004162805,0.3575853],"study_design_scores_gemma":[0.0002510422,0.00005494015,0.8537206,0.00003078824,0.00001869263,0.00002270884,0.00007382184,0.1262022,0.006527071,0.01156273,0.001060875,0.0004745149],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2124059,0.000590671,0.7831298,0.001284764,0.0001643663,0.001304984,0.00001594091,0.0006790943,0.0004244719],"genre_scores_gemma":[0.9633642,0.000437753,0.03352997,0.00009285175,0.00003498267,0.0007842086,0.0001145179,0.00002231791,0.001619181],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7727185,"threshold_uncertainty_score":0.9999532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03872463888272461,"score_gpt":0.315026686421234,"score_spread":0.2763020475385095,"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."}}