{"id":"W2978345223","doi":"10.1016/j.aap.2019.105320","title":"Crash prediction based on traffic platoon characteristics using floating car trajectory data and the machine learning approach","year":2019,"lang":"en","type":"article","venue":"Accident Analysis & Prevention","topic":"Traffic and Road Safety","field":"Engineering","cited_by":69,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Platoon; Crash; Support vector machine; Engineering; Poison control; Transport engineering; Computer science; Simulation; Machine learning; Artificial intelligence; Control (management)","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":[0.0008932502,0.000187105,0.0003356416,0.0002287057,0.000178754,0.00008098049,0.0002197758,0.00009442047,0.00006701228],"category_scores_gemma":[0.00003230051,0.0001488917,0.0001632955,0.0004386023,0.00002475984,0.0002491932,0.00005428708,0.0003215139,0.000007430438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006736758,"about_ca_system_score_gemma":0.00001399078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002069721,"about_ca_topic_score_gemma":0.00007967981,"domain_scores_codex":[0.9986041,0.0001914845,0.0003939003,0.0003433323,0.0002806241,0.0001865981],"domain_scores_gemma":[0.9992241,0.0000965737,0.0001376537,0.00047589,0.00002307936,0.0000427462],"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":[0.0000338361,0.0000274868,0.1423117,0.00001539736,0.0004167615,4.675442e-7,0.000204605,0.8503188,0.0001359539,0.00001025459,0.000008795915,0.006515997],"study_design_scores_gemma":[0.0007494413,0.00001897832,0.1286364,0.00003454645,0.001246161,0.00000156908,0.0001184732,0.8689889,0.00001189305,0.000002084224,0.00006440887,0.0001271142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9134774,0.0002110023,0.08548836,0.00001021566,0.0001505103,0.0002847896,0.000005079746,0.000189066,0.0001835783],"genre_scores_gemma":[0.9975454,0.00009123519,0.0009946118,0.000009583087,0.0001042459,0.000005205482,0.001134419,0.00002885504,0.00008645293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08449375,"threshold_uncertainty_score":0.6071628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01502093610035866,"score_gpt":0.2248222376623602,"score_spread":0.2098013015620015,"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."}}