{"id":"W4323654755","doi":"10.18280/isi.280117","title":"Ensemble Model for Multiclass Imbalanced Data Using Cluster Computing of Spark","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"SPARK (programming language); Cluster (spacecraft); Computer science; Artificial intelligence; Data mining; Machine learning; Operating system","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001009824,0.0001473569,0.0002289535,0.0003119884,0.0002044919,0.000206614,0.001339732,0.00009301375,3.908499e-7],"category_scores_gemma":[0.0004368588,0.0001517269,0.00004400248,0.0007027596,0.00007710555,0.005209332,0.0007163363,0.00007671929,0.00001492532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001492026,"about_ca_system_score_gemma":0.000127761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002106967,"about_ca_topic_score_gemma":0.000003598881,"domain_scores_codex":[0.9983959,0.00003917167,0.0007237603,0.00024,0.0002722125,0.000328932],"domain_scores_gemma":[0.9976967,0.0001739305,0.0005328327,0.001185176,0.0003618747,0.00004950566],"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":[0.0001276737,0.000116004,0.001548429,0.002958095,0.0001404642,0.000001746297,0.02648493,0.3215639,0.04987261,0.07651472,0.02119642,0.499475],"study_design_scores_gemma":[0.0003485537,0.00002112074,0.00042986,0.0001023626,0.000006585841,0.000005620489,0.0001175075,0.9866924,0.00759952,0.004092993,0.0004201462,0.0001633866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02296989,0.000007854042,0.9751332,0.00006129063,0.0002091135,0.0005755043,0.0001597141,0.0006140411,0.0002693585],"genre_scores_gemma":[0.6198567,0.000004770797,0.3795619,0.00009036417,0.00001968398,0.00001976178,0.0004200361,0.000008044257,0.00001874611],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6651285,"threshold_uncertainty_score":0.6187244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08354625269483926,"score_gpt":0.3163365770340787,"score_spread":0.2327903243392395,"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."}}