{"id":"W3211602915","doi":"10.1007/s11227-021-04177-6","title":"A binary PSO-based ensemble under-sampling model for rebalancing imbalanced training data","year":2021,"lang":"en","type":"article","venue":"The Journal of Supercomputing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Artificial intelligence; Ensemble learning; Machine learning; Sampling (signal processing); Selection (genetic algorithm); Binary number; Binary classification; Data mining; Pattern recognition (psychology); Support vector machine; Mathematics","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":[0.00340501,0.0001843621,0.0003605657,0.0001334576,0.0004010186,0.00021197,0.002778367,0.00007336003,0.000001680997],"category_scores_gemma":[0.0005045829,0.000146259,0.00010721,0.0004548247,0.00005036182,0.001021084,0.0006305681,0.0004044227,0.000001407492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001069594,"about_ca_system_score_gemma":0.0007650533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000437432,"about_ca_topic_score_gemma":0.000004728076,"domain_scores_codex":[0.9978592,0.0001853615,0.0007639088,0.0003517713,0.0004140462,0.0004256907],"domain_scores_gemma":[0.9963803,0.001146134,0.0004444549,0.001447301,0.0004884768,0.00009328985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007593414,0.0001745305,0.0001496452,0.0001334915,0.0001182357,0.0000382554,0.005360699,0.3882485,0.4825023,0.01168326,0.003157313,0.1083579],"study_design_scores_gemma":[0.000516972,0.00005446681,0.0001471423,0.0002538899,0.00002843721,0.0002253729,0.000610971,0.9814115,0.01154358,0.004729029,0.0003047159,0.000173966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03204818,0.0003533516,0.9637471,0.003258025,0.0002567651,0.0001349411,0.00001951769,0.0001292684,0.00005287614],"genre_scores_gemma":[0.5338466,0.00002022673,0.465314,0.0006352442,0.0001352646,0.00000128429,0.00002124669,0.00001507535,0.00001106555],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.593163,"threshold_uncertainty_score":0.5964267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2111408925881917,"score_gpt":0.3510560927424298,"score_spread":0.1399152001542381,"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."}}