{"id":"W2294246171","doi":"10.5220/0005595502260234","title":"SCUT: Multi-Class Imbalanced Data Classification using SMOTE and Cluster-based Undersampling","year":2015,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Undersampling; Computer science; Class (philosophy); Cluster (spacecraft); Support vector machine; Artificial intelligence; Data mining; Multi-label classification; Pattern recognition (psychology); Computer network","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":[0.004934186,0.001318648,0.001723906,0.002238544,0.001174724,0.001218105,0.002146319,0.001765804,0.0009735911],"category_scores_gemma":[0.008991519,0.000601944,0.001682231,0.001477776,0.001099721,0.001321511,0.001800539,0.002419544,0.0004962764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001083261,"about_ca_system_score_gemma":0.002084604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006777094,"about_ca_topic_score_gemma":0.009557269,"domain_scores_codex":[0.9982698,0.000600612,0.0001313201,0.0003104745,0.000519762,0.0001678994],"domain_scores_gemma":[0.9966525,0.001548704,0.0003063965,0.0004636285,0.0008779867,0.0001507102],"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":[0.000919441,0.0006142012,0.01061152,0.000357544,0.0005229737,0.0002280285,0.0003482784,0.5244824,0.01054303,0.007679086,0.01418823,0.4295053],"study_design_scores_gemma":[0.00001670829,0.0000345601,0.0003601915,0.000007161501,0.000009038105,0.00001690585,0.00001446693,0.9963763,0.001375669,0.001169999,0.0006129005,0.000005992155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05118486,0.0005368831,0.9420434,0.0003908524,0.0002290101,0.0004049253,0.0003163185,0.00395708,0.0009366328],"genre_scores_gemma":[0.3319378,0.0002552495,0.6616488,0.000483011,0.0002038577,0.0007294163,0.002599428,0.0003118632,0.001830611],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006777094,"threshold_uncertainty_score":0.02609479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3499846869511297,"score_gpt":0.3807716212091559,"score_spread":0.03078693425802626,"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."}}