{"id":"W4312307467","doi":"10.1109/tdei.2022.3230377","title":"Influence of Data Balancing on Transformer DGA Fault Classification With Machine Learning Algorithms","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Dielectrics and Electrical Insulation","topic":"Power Transformer Diagnostics and Insulation","field":"Engineering","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Transformer; Dissolved gas analysis; Machine learning; Algorithm; Artificial intelligence; Engineering; Computer science; Statistical classification; Reliability engineering; Data mining; Electrical engineering; Voltage","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":[0.006263619,0.000925687,0.0008650388,0.0008188382,0.0006211367,0.001169522,0.0006264834,0.0008568926,0.0003359604],"category_scores_gemma":[0.025817,0.0002073553,0.0004963682,0.00081816,0.0006765256,0.001594694,0.001037543,0.0008076348,0.0001950979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005860095,"about_ca_system_score_gemma":0.0006532535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002661795,"about_ca_topic_score_gemma":0.001337504,"domain_scores_codex":[0.9958534,0.002122096,0.0004028531,0.0005473752,0.0008495629,0.0002248067],"domain_scores_gemma":[0.9873565,0.008780812,0.000732892,0.001251905,0.001678335,0.0001994773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001846306,0.0005772864,0.02532981,0.0001775151,0.0001801654,0.0002141929,0.0002520129,0.5131671,0.01499711,0.001506507,0.0008797423,0.4408723],"study_design_scores_gemma":[0.00003636255,0.0003695391,0.005464437,0.00002405993,0.00005210911,0.00007822951,0.0001613075,0.9734783,0.01869445,0.001032631,0.0005914528,0.00001718506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7788145,0.001884192,0.2147707,0.0006027961,0.0001538355,0.0001462373,0.0001011915,0.0009632609,0.00256323],"genre_scores_gemma":[0.9677747,0.0001673319,0.0314176,0.00007558341,0.00002677959,0.0000406636,0.0001906611,0.0000373175,0.0002693403],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006263619,"threshold_uncertainty_score":0.03312558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02071224454799879,"score_gpt":0.2395064579240676,"score_spread":0.2187942133760687,"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."}}