{"id":"W2910708648","doi":"10.1016/j.aap.2019.01.007","title":"Expressway crash risk prediction using back propagation neural network: A brief investigation on safety resilience","year":2019,"lang":"en","type":"article","venue":"Accident Analysis & Prevention","topic":"Traffic and Road Safety","field":"Engineering","cited_by":70,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China; AAA Foundation for Traffic Safety","keywords":"Resilience (materials science); Crash; Engineering; Poison control; Microsimulation; Artificial neural network; Transport engineering; Risk assessment; Risk analysis (engineering); Computer science; Computer security; Machine learning","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":[0.0006993549,0.0006797587,0.0004173112,0.000565468,0.0002929192,0.0006019435,0.0007213647,0.0006333943,0.0009371682],"category_scores_gemma":[0.001826127,0.000217178,0.0004854255,0.0005559037,0.0003376823,0.001880997,0.0005843722,0.0008390002,0.0001628271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000352468,"about_ca_system_score_gemma":0.0005260477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007675588,"about_ca_topic_score_gemma":0.005223797,"domain_scores_codex":[0.9997552,0.000036839,0.00001861785,0.00008127625,0.00006664429,0.00004142437],"domain_scores_gemma":[0.9995573,0.000170738,0.00004989706,0.0000420464,0.0001604087,0.00001960997],"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":[0.0003374512,0.0003108187,0.04330755,0.000233617,0.0002256183,0.0006198926,0.0002548378,0.5535454,0.007548126,0.01020634,0.002654287,0.3807561],"study_design_scores_gemma":[0.000003408472,0.00008913666,0.008656238,0.00002456193,0.00006806363,0.00006801599,0.00006748766,0.9862673,0.001672594,0.002402292,0.0006637236,0.00001712101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5162548,0.006523408,0.464201,0.001511739,0.0004043091,0.00008668897,0.0002980094,0.000605822,0.01011421],"genre_scores_gemma":[0.9829869,0.001812246,0.01184632,0.00005668208,0.0001057703,0.00002057295,0.0001287008,0.00001622795,0.003026512],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007675588,"threshold_uncertainty_score":0.01526183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01304242029315536,"score_gpt":0.2234069741795452,"score_spread":0.2103645538863899,"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."}}