{"id":"W3107149018","doi":"10.1109/access.2020.3040165","title":"Crash Severity Prediction Using Two-Layer Ensemble Machine Learning Model for Proactive Emergency Management","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Traffic and Road Safety","field":"Engineering","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"King Fahd University of Petroleum and Minerals","keywords":"Crash; Computer science; Decision tree; Support vector machine; Machine learning; Ensemble learning; Artificial intelligence; Boosting (machine learning); Ensemble forecasting; Artificial neural network; Feedforward neural network; Dimensionality reduction; Data mining","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007060314,0.0001589362,0.0001482774,0.00004129334,0.0001457997,0.00003053991,0.0001794689,0.00005548164,0.00002779529],"category_scores_gemma":[0.000005062636,0.0001616767,0.00007010569,0.0001637226,0.000007670802,0.0003953408,0.00004853523,0.0001810096,0.000006608383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006291934,"about_ca_system_score_gemma":0.000008704335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001285588,"about_ca_topic_score_gemma":0.00001090171,"domain_scores_codex":[0.999162,0.00001416988,0.0002104415,0.0002367258,0.0001352664,0.0002413819],"domain_scores_gemma":[0.9997329,0.000008249245,0.0000369295,0.0001022371,0.00003565682,0.00008406835],"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":[0.0000331934,0.0000189468,0.001515993,0.0001810798,0.0001135395,0.000002030059,0.0004998626,0.9891371,0.001714716,0.00003871962,0.0008958583,0.00584902],"study_design_scores_gemma":[0.0004740901,0.00001565088,0.001790235,0.00001130793,0.00007127449,0.000001072086,0.00003415379,0.9948844,0.001965313,0.0001163475,0.0004619371,0.0001741661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2340894,0.00005658893,0.7625796,0.00004178279,0.0005606614,0.0004176655,0.00003390101,0.0004439478,0.001776551],"genre_scores_gemma":[0.9954205,0.00009540918,0.003943838,0.00003769517,0.0002291878,0.00005172194,0.00002005186,0.00004769316,0.0001538807],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7613311,"threshold_uncertainty_score":0.6592982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0695350917090362,"score_gpt":0.295815663402317,"score_spread":0.2262805716932808,"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."}}