{"id":"W4386534860","doi":"10.1016/j.aap.2023.107286","title":"An integrated approach of machine learning and Bayesian spatial Poisson model for large-scale real-time traffic conflict prediction","year":2023,"lang":"en","type":"article","venue":"Accident Analysis & Prevention","topic":"Traffic and Road Safety","field":"Engineering","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"British Columbia Institute of Technology; University of British Columbia","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Heilongjiang Province; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Traffic conflict; Poison control; Machine learning; Artificial intelligence; Bayesian probability; Random forest; Poisson regression; Data mining; Engineering; Traffic congestion; Transport engineering; Floating car data","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":[0.001460953,0.0007197134,0.001537046,0.001211346,0.0004847733,0.0008939059,0.002569273,0.001101655,0.001505117],"category_scores_gemma":[0.0033598,0.0005793234,0.001169397,0.001549852,0.0003409604,0.001643764,0.00121595,0.001200374,0.0005121581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006163209,"about_ca_system_score_gemma":0.001648853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01579169,"about_ca_topic_score_gemma":0.01306392,"domain_scores_codex":[0.9992029,0.0002068247,0.00005359345,0.0002159033,0.0002143762,0.0001063958],"domain_scores_gemma":[0.998702,0.0007085197,0.0001037363,0.00007951205,0.0003413873,0.00006482657],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006704492,0.0001712009,0.003755446,0.00005731807,0.000127975,0.00007239563,0.00003968224,0.8732948,0.0009454159,0.005354558,0.001483991,0.1146302],"study_design_scores_gemma":[9.491625e-7,0.00000422121,0.0001101286,8.922826e-7,0.00000408994,0.000003703579,0.000002170457,0.9989806,0.00004330651,0.0007846327,0.00006349947,0.000001872954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01890766,0.0004244053,0.9789683,0.0002061972,0.0000832821,0.00002910802,0.0001088104,0.0005005674,0.0007717538],"genre_scores_gemma":[0.7624551,0.0007246296,0.2320103,0.0002571377,0.0002923382,0.0002021398,0.0008364148,0.0001120685,0.003109962],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01579169,"threshold_uncertainty_score":0.03139955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009566829466147493,"score_gpt":0.2483894700757289,"score_spread":0.2388226406095814,"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."}}