{"id":"W2743768825","doi":"10.1155/2017/6937385","title":"Predicting Freeway Work Zone Delays and Costs with a Hybrid Machine-Learning Model","year":2017,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Traffic control and management","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"New Jersey Department of Transportation; U.S. Department of Transportation","keywords":"Work zone; Schedule; Support vector machine; Work (physics); Artificial neural network; Mean squared error; Computer science; Incentive; Work schedule; Machine learning; Artificial intelligence; Transport engineering; Operations research; Simulation; Engineering; Statistics; Mathematics","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":[0.00009610286,0.00009496832,0.0001481026,0.0000536361,0.0001180686,0.0000394645,0.00007839943,0.00001712786,0.000001895766],"category_scores_gemma":[0.000009233536,0.00008001552,0.00003234582,0.0000244578,0.000016273,0.0004410098,0.000001657722,0.0001954524,2.400278e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002583251,"about_ca_system_score_gemma":0.000007464657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000592491,"about_ca_topic_score_gemma":0.0001964524,"domain_scores_codex":[0.999444,0.000004396081,0.0002235841,0.00007052939,0.0001451109,0.000112386],"domain_scores_gemma":[0.9995935,0.00001634846,0.0001886045,0.00008238493,0.00005765578,0.00006152678],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0001380636,0.000008702997,0.007683404,0.00002680784,0.00005708951,0.0000447842,0.0004010259,0.9261509,0.000576263,0.00003657316,0.000005898493,0.06487046],"study_design_scores_gemma":[0.005824912,0.0003529956,0.5431941,0.0006631629,0.000299953,0.00003753427,0.0003496536,0.4475733,0.0003150603,0.000128402,0.000912994,0.0003479032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8409145,0.0004265221,0.1582224,0.00006034852,0.0001078594,0.00007479752,0.000005042961,0.00004417882,0.0001442818],"genre_scores_gemma":[0.9871361,0.0002896729,0.0124676,0.00000699766,0.00004533846,0.000003154297,0.000005228803,0.00001850966,0.00002736016],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5355107,"threshold_uncertainty_score":0.3262938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004514194566914979,"score_gpt":0.1910865063848152,"score_spread":0.1865723118179002,"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."}}