{"id":"W3006171834","doi":"10.1016/j.aap.2020.105468","title":"A comparison between Artificial Neural Network and Hybrid Intelligent Genetic Algorithm in predicting the severity of fixed object crashes among elderly drivers","year":2020,"lang":"en","type":"article","venue":"Accident Analysis & Prevention","topic":"Traffic and Road Safety","field":"Engineering","cited_by":101,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; McMaster University","funders":"","keywords":"Artificial neural network; Genetic algorithm; Crash; Poison control; Injury prevention; Human factors and ergonomics; Artificial intelligence; Machine learning; Computer science; Engineering; Medicine; Medical emergency","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":[0.0002735326,0.0001524437,0.0004037575,0.00009810658,0.0000833927,0.00004045527,0.0001596845,0.00005597666,0.00002985611],"category_scores_gemma":[0.00001904892,0.0001345362,0.0002166985,0.0007006885,0.00004364695,0.000128324,0.00006546861,0.0002216032,0.000001873037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003401023,"about_ca_system_score_gemma":0.00000861102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001707132,"about_ca_topic_score_gemma":0.001781352,"domain_scores_codex":[0.9985983,0.0001419351,0.0006095475,0.0002260232,0.0002109389,0.0002132444],"domain_scores_gemma":[0.9995326,0.00008854362,0.0001437503,0.000142863,0.00002489148,0.00006739358],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00000406702,0.00000868092,0.5879536,0.000004319183,0.0003128416,0.000001389251,0.0005324871,0.3271638,0.000007510368,6.169083e-7,0.00002882355,0.08398187],"study_design_scores_gemma":[0.00006614136,0.00003048392,0.5563816,0.00001414399,0.0005475469,2.824286e-7,0.0002550221,0.442397,0.0001987607,0.00003379456,0.000005046934,0.00007020537],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8929002,0.0003582018,0.1063303,0.00005044418,0.00006710537,0.000210704,0.000001072214,0.00007029516,0.00001164632],"genre_scores_gemma":[0.9988789,0.00008722585,0.0007893131,0.00000568152,0.0001699247,0.000008953771,0.00004343763,0.00001254249,0.000004033425],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1152332,"threshold_uncertainty_score":0.5486227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01807287918058703,"score_gpt":0.2518705339149624,"score_spread":0.2337976547343754,"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."}}