{"id":"W4390716046","doi":"10.1016/j.engappai.2024.107845","title":"Effect of feature optimization on performance of machine learning models for predicting traffic incident duration","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Outlier; Artificial intelligence; Feature selection; Support vector machine; Machine learning; Feature (linguistics); Predictive modelling; Data mining; Heteroscedasticity; Feature engineering; Principal component analysis; Artificial neural network; Skewness; Deep learning; Statistics","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":[0.0002625678,0.0001137012,0.0001497219,0.0002577456,0.00002855161,0.00001236207,0.000114133,0.00006380902,0.000001980522],"category_scores_gemma":[0.00003756732,0.0001158991,0.00006222062,0.0003484253,0.00001944539,0.0001245036,0.00001198217,0.0001344423,8.549339e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003355634,"about_ca_system_score_gemma":0.000006365565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002100082,"about_ca_topic_score_gemma":5.983998e-7,"domain_scores_codex":[0.9992795,0.000008555881,0.0003620141,0.0001307002,0.0001255934,0.00009362309],"domain_scores_gemma":[0.9995667,0.0001641715,0.00005818602,0.0001366924,0.00005359417,0.00002064957],"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":[0.00001858698,0.0000134558,0.000004106678,0.0009431058,0.00002372349,4.688777e-8,0.0001257513,0.9011883,0.003739861,0.004760372,0.00002142151,0.08916126],"study_design_scores_gemma":[0.00001471666,0.0002238692,0.000003310726,0.0001468019,0.00002581282,5.810593e-7,0.00001213807,0.8318603,0.1675173,0.00001296313,0.0001203606,0.00006187151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0671031,0.0002111551,0.9307975,0.00001504428,0.0001035992,0.0005787516,0.00001820421,0.001099879,0.00007283732],"genre_scores_gemma":[0.987089,0.0002005094,0.01232436,5.960385e-7,0.00004002744,0.0002718212,0.00003925522,0.00002636829,0.000008099136],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9199859,"threshold_uncertainty_score":0.4726229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009946180141275898,"score_gpt":0.2392507090197534,"score_spread":0.2293045288784775,"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."}}