{"id":"W2169074127","doi":"10.1109/icsmc.1998.727521","title":"Using misclassified training samples to improve classification","year":2002,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Classifier (UML); Computer science; Training set; Artificial intelligence; Pattern recognition (psychology); Machine learning; Test set; Data mining","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":[0.006652494,0.001991271,0.002633546,0.003529991,0.001008595,0.002392208,0.002151096,0.001497768,0.001407373],"category_scores_gemma":[0.03368432,0.0005876077,0.0008436543,0.001697155,0.0009870812,0.00331401,0.001274896,0.002055723,0.001368055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006975945,"about_ca_system_score_gemma":0.0009048075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002503566,"about_ca_topic_score_gemma":0.003171617,"domain_scores_codex":[0.9939348,0.001413644,0.0007122144,0.001022332,0.002637822,0.0002791552],"domain_scores_gemma":[0.9722354,0.013644,0.001921665,0.004938193,0.006888831,0.0003719421],"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":[0.0008565871,0.0004529682,0.0152428,0.0003117728,0.0002026551,0.0003156115,0.0006225326,0.05498323,0.02657504,0.003080833,0.003535173,0.8938208],"study_design_scores_gemma":[0.0001018515,0.0004526483,0.008892788,0.0001693736,0.000250259,0.0008797998,0.0003264606,0.8894961,0.0798465,0.008384251,0.01105446,0.0001455483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1165886,0.001018803,0.8780295,0.0005385681,0.0004224206,0.0002349744,0.0001423004,0.001709309,0.001315491],"genre_scores_gemma":[0.4738784,0.0004600051,0.5215995,0.0005079008,0.0002552597,0.0001789577,0.0005472148,0.0002793313,0.002293481],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006652494,"threshold_uncertainty_score":0.03518212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2821125264670423,"score_gpt":0.3297281373931616,"score_spread":0.04761561092611938,"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."}}