{"id":"W4388874216","doi":"10.1145/3625156.3625169","title":"Handling Data Imbalance In Linear Modelling of Fatality Rate of Auto Collision","year":2023,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"","keywords":"Collision; Computer science; Data modeling; Data mining; Machine learning; Predictive modelling; Artificial intelligence; Computer security; Database","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":[0.001446546,0.00007801002,0.0002015378,0.0001763508,0.00002446709,0.00001929968,0.001741463,0.00005078105,0.000002490843],"category_scores_gemma":[0.0001317299,0.00007267145,0.00001855005,0.001155132,0.00004322678,0.0007143358,0.0008962001,0.00008260265,0.00001092276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001860077,"about_ca_system_score_gemma":0.00007262058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002150968,"about_ca_topic_score_gemma":0.00001428509,"domain_scores_codex":[0.9987353,0.00006863318,0.0004593451,0.0003921151,0.0001849744,0.0001596204],"domain_scores_gemma":[0.9977954,0.0001589138,0.0001808192,0.001735926,0.0001024355,0.0000264745],"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":[0.0001194793,0.0007173745,0.02776382,0.0009605986,0.00006251029,0.00003536197,0.002367089,0.33928,0.2795106,0.304343,0.01473879,0.03010145],"study_design_scores_gemma":[0.0001162592,0.00001216525,0.001858878,0.00005534759,9.127679e-7,2.75701e-7,0.00001380157,0.8941969,0.101197,0.002142946,0.0003397557,0.00006572332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03181631,0.00001850209,0.9671527,0.0002267646,0.00007636802,0.000141399,0.00008902659,0.0002630844,0.0002158446],"genre_scores_gemma":[0.728554,0.0001135325,0.2710454,0.00002809663,0.000008043327,0.000005529628,0.0001270938,0.000005147739,0.0001130746],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6967377,"threshold_uncertainty_score":0.3236101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.153931589735171,"score_gpt":0.338425445121476,"score_spread":0.184493855386305,"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."}}