{"id":"W3025289572","doi":"10.1007/s00500-020-05023-2","title":"A design of information granule-based under-sampling method in imbalanced data classification","year":2020,"lang":"en","type":"article","venue":"Soft Computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Support vector machine; Classifier (UML); Exploit; Artificial intelligence; Sampling (signal processing); Machine learning; Data mining; k-nearest neighbors algorithm; Oversampling; Suite; Data sampling; Pattern recognition (psychology); Bandwidth (computing)","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":[0.001396362,0.0001436237,0.0002407212,0.0001923973,0.00007564647,0.0001277542,0.002009125,0.00007980884,0.000001724609],"category_scores_gemma":[0.0005233448,0.0001557695,0.00002557954,0.00105655,0.00003407925,0.001386307,0.0004686557,0.000207593,0.00001258295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006433963,"about_ca_system_score_gemma":0.0001919231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001473581,"about_ca_topic_score_gemma":6.656615e-7,"domain_scores_codex":[0.9980938,0.0002434633,0.0006826694,0.0004313207,0.0003102625,0.000238429],"domain_scores_gemma":[0.9976024,0.0006210016,0.0005051637,0.001066093,0.0001403681,0.00006498762],"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":[0.00008913013,0.0001593608,0.002705652,0.0003818861,0.00002894733,0.000002200035,0.003731816,0.2637667,0.07674161,0.06891296,0.000847131,0.5826326],"study_design_scores_gemma":[0.0003892819,0.00003697332,0.002997887,0.00005885615,0.000003256091,0.000001073123,0.00007984656,0.98766,0.007001875,0.001375519,0.0002435533,0.0001518911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002516599,0.00001655239,0.997121,0.00163673,0.00006440496,0.0003708489,0.00001548199,0.0004580026,0.00006533508],"genre_scores_gemma":[0.4244153,0.000001337189,0.574788,0.0006262946,0.0000160657,0.000005051736,0.000142483,0.000005217298,2.333073e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7238933,"threshold_uncertainty_score":0.6352096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1669404679454376,"score_gpt":0.354027070377746,"score_spread":0.1870866024323084,"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."}}