{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003459751,0.0008354759,0.002275321,0.001683773,0.001009371,0.001845399,0.002704738,0.001274182,0.001933405],"category_scores_gemma":[0.008440824,0.0005502289,0.0009103874,0.001846272,0.0009785598,0.00275455,0.002269727,0.001233348,0.0005597888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000802233,"about_ca_system_score_gemma":0.001880484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002057823,"about_ca_topic_score_gemma":0.001723796,"domain_scores_codex":[0.9967983,0.0009320449,0.0002527959,0.0007781643,0.000982031,0.0002567771],"domain_scores_gemma":[0.9963586,0.001222122,0.0002545009,0.0004606978,0.001409059,0.0002950207],"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":[0.001639234,0.0007076202,0.006430028,0.0003759164,0.0002074411,0.0002610811,0.0004925916,0.08814329,0.03360431,0.03125462,0.006746765,0.8301371],"study_design_scores_gemma":[0.00004927276,0.0001291301,0.0006533127,0.00001233975,0.00004476635,0.00009018806,0.00005159016,0.9873835,0.005211816,0.004971627,0.001382553,0.00001986875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008925039,0.0001687666,0.9898589,0.0001007956,0.00006891558,0.0001333929,0.00004110784,0.0003925008,0.0003106285],"genre_scores_gemma":[0.3742075,0.0004043767,0.6216086,0.0002680527,0.0003094089,0.0008371854,0.000501781,0.0001478414,0.001715396],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003459751,"threshold_uncertainty_score":0.01829714,"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."}}