{"id":"W4399939387","doi":"10.1109/tii.2024.3413355","title":"Development of an Automated Global Crash Prediction Model With Adaptive Feature Selection of Deep Neural Networks","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial neural network; Artificial intelligence; Feature selection; Selection (genetic algorithm); Feature (linguistics); Machine learning; Feature extraction; Crash; Data modeling; Pattern recognition (psychology); 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":[0.000111256,0.0001686694,0.0001694683,0.0001972208,0.00006553651,0.00003489428,0.0000883145,0.000246773,0.00000579386],"category_scores_gemma":[8.194627e-7,0.0001539347,0.00004717178,0.0005724441,0.00003335237,0.0005494247,0.00000111445,0.00036264,9.130152e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001871029,"about_ca_system_score_gemma":0.00005330209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003714824,"about_ca_topic_score_gemma":0.00004303154,"domain_scores_codex":[0.9990531,0.00001302847,0.0004656745,0.00007914934,0.0002344723,0.0001546362],"domain_scores_gemma":[0.9996939,0.00001249599,0.00006320499,0.0001075713,0.00006099564,0.00006181232],"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":[0.00006785073,0.00003968747,0.000001761654,0.00005804183,0.0001479178,3.078851e-7,0.0004849001,0.9058411,0.00003909481,0.00005212374,0.00100156,0.09226568],"study_design_scores_gemma":[0.0003984504,0.0002304812,0.00001987927,0.0001050702,0.00009013832,0.000008064594,0.0002735502,0.9941801,0.004454681,0.000003029347,0.000115861,0.0001207017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03244778,0.000005535076,0.9609751,0.000006013396,0.0005724166,0.0003395006,0.00007698298,0.005020323,0.0005563594],"genre_scores_gemma":[0.9747568,0.000009408323,0.02510122,0.000007716841,0.0000355089,0.00003974522,0.00002364734,0.00001714495,0.000008770943],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9423091,"threshold_uncertainty_score":0.6277274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01888792321933891,"score_gpt":0.2363015278456997,"score_spread":0.2174136046263608,"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."}}