{"id":"W3217408054","doi":"10.1155/2021/4486149","title":"A Bayesian Neural Network-Based Method to Calibrate Microscopic Traffic Simulators","year":2021,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Calibration; Computer science; Heuristic; Artificial neural network; Bayesian probability; Genetic algorithm; Microsimulation; Algorithm; Traffic simulation; Mathematical optimization; Simulation; Statistics; Machine learning; Artificial intelligence; Mathematics; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001151826,0.0001159647,0.0001931423,0.0001139497,0.00003051023,0.00002239636,0.0000746882,0.00004671339,0.00001588292],"category_scores_gemma":[0.000004939543,0.000120358,0.0001055634,0.0003335118,0.000006173914,0.0002369062,9.767223e-7,0.0001544933,8.846107e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000037825,"about_ca_system_score_gemma":0.00002696518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.125831e-7,"about_ca_topic_score_gemma":0.00002691653,"domain_scores_codex":[0.9991463,0.0000292183,0.0004109031,0.00009868827,0.0001539303,0.0001609058],"domain_scores_gemma":[0.9996101,0.00003127597,0.00007954732,0.00008676568,0.00008314042,0.0001092237],"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":[0.00002655482,0.00001872647,0.0001139225,0.00003807612,0.00002797748,0.00005984483,0.0001618362,0.9588344,0.007162938,0.00003870506,0.0007997864,0.03271729],"study_design_scores_gemma":[0.003703484,0.0005129769,0.04483343,0.0004913334,0.0003037302,0.00002725606,0.0004067126,0.8435709,0.07010592,0.0003054353,0.03503473,0.0007040605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2360456,0.0001877751,0.7625532,0.0001588403,0.000501772,0.00009552889,0.000005539175,0.0004251251,0.00002658174],"genre_scores_gemma":[0.8478039,0.00002949381,0.1517861,0.0002468251,0.00008391773,0.000003986186,0.00001523741,0.000022705,0.000007856592],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6117583,"threshold_uncertainty_score":0.4908055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005869988070895124,"score_gpt":0.2498259647790873,"score_spread":0.2439559767081922,"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."}}