{"id":"W4382994301","doi":"10.2139/ssrn.4498130","title":"Pseudo Oversampling Based on Feature Transformation and Fuzzy Membership Functions for Imbalanced and Overlapping Data","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Oversampling; Feature (linguistics); Transformation (genetics); Fuzzy logic; Artificial intelligence; Pattern recognition (psychology); Computer science; Data mining; Mathematics; Biology; Linguistics","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":[0.003069252,0.0004455787,0.001125812,0.001274019,0.0006188565,0.00105197,0.0009093128,0.0007007585,0.0007138671],"category_scores_gemma":[0.008894318,0.0002786998,0.0007094087,0.00161269,0.0007233184,0.001692854,0.001229329,0.001075095,0.0001565125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005712232,"about_ca_system_score_gemma":0.00065917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001561711,"about_ca_topic_score_gemma":0.001428482,"domain_scores_codex":[0.9983233,0.0004573161,0.000126265,0.0003246774,0.0006258178,0.0001425533],"domain_scores_gemma":[0.9965044,0.001942317,0.0002471328,0.0006974095,0.0005209019,0.00008789339],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001187475,0.0002392045,0.00553829,0.0002429784,0.0001373714,0.0002958388,0.0004583409,0.1515815,0.0365949,0.02686262,0.002235159,0.7746263],"study_design_scores_gemma":[0.00001226286,0.00006653384,0.001756795,0.00001064232,0.00002598837,0.0001481204,0.00004449787,0.9785544,0.005741139,0.01276678,0.0008604928,0.00001221193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05391413,0.0003838778,0.9449179,0.0001083649,0.00006028264,0.00003241084,0.00006886332,0.0002282303,0.0002859245],"genre_scores_gemma":[0.6139556,0.0003528669,0.3836741,0.0001027856,0.000177369,0.0001136643,0.0005081014,0.00007361412,0.00104183],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003069252,"threshold_uncertainty_score":0.01623195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05631966215033283,"score_gpt":0.3033271105729997,"score_spread":0.2470074484226668,"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."}}