{"id":"W3000555836","doi":"10.1016/j.knosys.2020.105534","title":"GEV-NN: A deep neural network architecture for class imbalance problem in binary classification","year":2020,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"ca_institutions":"Microsoft (Canada)","funders":"Ministry of Science ICT and Future Planning; National Research Foundation of Korea","keywords":"Computer science; Component (thermodynamics); Artificial intelligence; Binary classification; Artificial neural network; Class (philosophy); Binary number; Deep learning; Gumbel distribution; Set (abstract data type); Architecture; Encoder; Machine learning; Pattern recognition (psychology); Support vector machine; Mathematics; Extreme value theory; Statistics","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":[0.002474495,0.0007520145,0.001094213,0.0008524111,0.0004621549,0.0008637144,0.001888075,0.001385467,0.002912266],"category_scores_gemma":[0.004796416,0.0004913126,0.0005556393,0.001226716,0.000504036,0.001971289,0.001739214,0.002331751,0.001091249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008265458,"about_ca_system_score_gemma":0.0009966969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005014446,"about_ca_topic_score_gemma":0.006513739,"domain_scores_codex":[0.9992631,0.0002132383,0.00004679808,0.0001883786,0.0002080296,0.00008048738],"domain_scores_gemma":[0.9989032,0.0004708614,0.00007566933,0.0001919827,0.0002971621,0.00006113787],"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":[0.0005376564,0.0002106764,0.004172465,0.0002052492,0.000212851,0.0001111215,0.0001008643,0.2020566,0.004977276,0.01569911,0.02078691,0.7509292],"study_design_scores_gemma":[0.00001566056,0.00003495821,0.0003952283,0.00002404564,0.00001824499,0.00002912145,0.00001283118,0.9809213,0.001460155,0.01514385,0.00193815,0.000006459999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02516262,0.001617169,0.9665186,0.000549232,0.0002924782,0.00007460588,0.0007217123,0.003281465,0.001782078],"genre_scores_gemma":[0.5393928,0.001090572,0.4462967,0.0008946005,0.0002632166,0.0002452837,0.00325534,0.0004448501,0.008116522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005014446,"threshold_uncertainty_score":0.01308656,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03650985385406229,"score_gpt":0.27218487379926,"score_spread":0.2356750199451977,"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."}}