{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009505644,0.0001972975,0.0001959623,0.0001791593,0.0001452855,0.0003888421,0.001804237,0.0001172319,0.000002630415],"category_scores_gemma":[0.00025937,0.0001870535,0.00002050643,0.0004426782,0.0001185026,0.001610931,0.0008110963,0.0001589242,0.00002036392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001634851,"about_ca_system_score_gemma":0.0002678889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008583171,"about_ca_topic_score_gemma":0.00002077636,"domain_scores_codex":[0.9979743,0.0001215595,0.0003620202,0.0008750313,0.00035332,0.0003137296],"domain_scores_gemma":[0.9967672,0.0001218813,0.0002097763,0.002534943,0.0002006068,0.0001656176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002509043,0.002081727,0.02269973,0.0004681924,0.0002519831,0.00003998082,0.002707403,0.00761491,0.2535246,0.3533604,0.03720111,0.319799],"study_design_scores_gemma":[0.0007929019,0.00002549523,0.001346138,0.00002526327,0.00000803959,0.000009247081,0.00008997217,0.9894975,0.003392991,0.00080888,0.003755402,0.0002481984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002313468,0.00006806561,0.9940267,0.001850133,0.0001782108,0.0003188658,0.00003130844,0.0007664552,0.0004467814],"genre_scores_gemma":[0.4378453,0.000005487748,0.5613011,0.0006023021,0.00002211457,0.000007751349,0.0001519746,0.0000135164,0.00005042551],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9818826,"threshold_uncertainty_score":0.7627822,"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."}}