{"id":"W3087735403","doi":"10.1016/j.inffus.2020.09.004","title":"Preprocessed dynamic classifier ensemble selection for highly imbalanced drifted data streams","year":2020,"lang":"en","type":"article","venue":"Information Fusion","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"Narodowym Centrum Nauki; Narodowe Centrum Nauki","keywords":"Computer science; Preprocessor; Data stream mining; Data mining; Data stream; Classifier (UML); Concept drift; Artificial intelligence; Data pre-processing; Selection (genetic algorithm); Ensemble learning; Dynamic data; Estimator; Machine learning; Pattern recognition (psychology); Statistics; Mathematics; Database","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":[0.0002251234,0.0001347071,0.0001323138,0.0001009718,0.0001474589,0.0002935898,0.001303268,0.00009606579,0.000008635553],"category_scores_gemma":[0.0002500275,0.0001288947,0.00002632994,0.0005053616,0.00001486151,0.005377856,0.000527617,0.0001026321,0.00007127533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004867827,"about_ca_system_score_gemma":0.0001094897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001944569,"about_ca_topic_score_gemma":0.00001105378,"domain_scores_codex":[0.9988332,0.00002074964,0.0003736981,0.0003093863,0.0002631746,0.000199758],"domain_scores_gemma":[0.9986796,0.00005521581,0.0002590831,0.0007227323,0.0001982543,0.00008509073],"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":[0.0001503815,0.00006857749,0.0003111991,0.000238968,0.00002665746,6.428328e-7,0.002970529,0.0002937671,0.02302857,0.005263176,0.1119065,0.8557411],"study_design_scores_gemma":[0.0004420607,0.0001631418,0.000396194,0.00002662653,0.000006225328,0.000003615725,0.00003885105,0.9196119,0.01021067,0.0004962476,0.06844109,0.0001633236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009743171,0.000005813461,0.9849818,0.002401076,0.0001141592,0.0004963059,0.0001060932,0.001155037,0.0009965427],"genre_scores_gemma":[0.7684672,0.00001640686,0.2275961,0.001366482,0.000044346,0.00006659194,0.002393361,0.000009316464,0.00004019279],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9193182,"threshold_uncertainty_score":0.5256172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03278250398426191,"score_gpt":0.2801424785524984,"score_spread":0.2473599745682365,"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."}}