{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008395862,0.0006999106,0.0009335201,0.001317391,0.0005359775,0.001529743,0.001359117,0.0008497172,0.001207478],"category_scores_gemma":[0.03485997,0.0004344621,0.001001485,0.001383044,0.0008346603,0.001667793,0.001234226,0.002051868,0.0004971687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234744,"about_ca_system_score_gemma":0.001209375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01431087,"about_ca_topic_score_gemma":0.00852234,"domain_scores_codex":[0.9973015,0.001292999,0.0001534192,0.0005946478,0.0003902043,0.0002672811],"domain_scores_gemma":[0.9848509,0.01159603,0.001241311,0.001106753,0.001003607,0.0002015222],"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":[0.0003640339,0.00014984,0.1205808,0.0001124093,0.0001597591,0.0002934141,0.0003988559,0.8031042,0.0008997449,0.008397574,0.002385634,0.06315379],"study_design_scores_gemma":[0.000004099054,0.00003128299,0.005460999,0.00001362112,0.00001046862,0.00003759903,0.00005513659,0.9896386,0.0002335397,0.004161565,0.0003433978,0.000009702485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4133743,0.0008456606,0.5795119,0.001632318,0.0002184244,0.0002213097,0.001558506,0.0006146541,0.002023043],"genre_scores_gemma":[0.9699292,0.0002942311,0.02627066,0.0001268316,0.00008863569,0.0001569288,0.00137106,0.00005967711,0.001702789],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01431087,"threshold_uncertainty_score":0.04440212,"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."}}