{"id":"W2141041164","doi":"10.3141/2432-11","title":"Use of Support Vector Machine Models for Real-Time Prediction of Crash Risk on Urban Expressways","year":2014,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of Education and Child Care","funders":"Program for New Century Excellent Talents in University; Federal Highway Administration","keywords":"Support vector machine; Computer science; Data mining; Crash; Naive Bayes classifier; Transferability; Logistic regression; Artificial neural network; Machine learning; Bayes' theorem; Bayesian probability; Artificial intelligence; Logit","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":[0.001440106,0.000980905,0.0006784794,0.001040715,0.000218246,0.0007867508,0.0008111526,0.000631889,0.000424818],"category_scores_gemma":[0.00469344,0.0002448864,0.0004981696,0.0007083936,0.0002123748,0.001225604,0.0004193766,0.0007861283,0.0001766545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003808017,"about_ca_system_score_gemma":0.0005975674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005477615,"about_ca_topic_score_gemma":0.003873339,"domain_scores_codex":[0.9992989,0.0002426265,0.00006624113,0.000148698,0.000183226,0.00006033785],"domain_scores_gemma":[0.9982927,0.0009193146,0.0002239457,0.0001284395,0.0003844287,0.0000511811],"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":[0.0002522054,0.000301425,0.03272299,0.000101347,0.0001383557,0.0001498054,0.00009500896,0.7879902,0.00515337,0.001296126,0.0006040569,0.1711951],"study_design_scores_gemma":[0.000002713748,0.00004552291,0.001284925,0.000003489399,0.000007484042,0.000009961232,0.00001184775,0.9976717,0.0006322841,0.0002557644,0.00006913806,0.000005169959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4220725,0.0005429537,0.57502,0.0001882292,0.00007158947,0.00007265675,0.000217683,0.0008500947,0.000964311],"genre_scores_gemma":[0.9704835,0.0001164059,0.02890004,0.00001343784,0.00001403265,0.00003620667,0.0001365415,0.000009514142,0.0002902909],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005477615,"threshold_uncertainty_score":0.01089144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07149990440614011,"score_gpt":0.3137051595843043,"score_spread":0.2422052551781642,"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."}}