{"id":"W3166976267","doi":"10.1109/ceidp49254.2020.9437463","title":"Application of Machine Learning in Discharge Classification","year":2020,"lang":"en","type":"article","venue":"","topic":"High voltage insulation and dielectric phenomena","field":"Materials Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Insulator (electricity); Support vector machine; Ceramic; Corona discharge; Partial discharge; Computer science; Electric power transmission; Corona (planetary geology); Materials science; Acoustics; Electrical engineering; Artificial intelligence; Engineering; Composite material; Voltage; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001908094,0.0007432774,0.0008099094,0.001777583,0.0002924948,0.001267438,0.0006443043,0.001117082,0.001131322],"category_scores_gemma":[0.00480558,0.0002631176,0.0005700538,0.001998746,0.0005799577,0.001013709,0.0004865,0.001121158,0.0007200526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004070503,"about_ca_system_score_gemma":0.000486225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001372235,"about_ca_topic_score_gemma":0.000779333,"domain_scores_codex":[0.9987316,0.0005543004,0.0001032081,0.0002067547,0.0003381362,0.00006601123],"domain_scores_gemma":[0.9972672,0.002014281,0.0001464503,0.0001902048,0.0003458416,0.00003595654],"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":[0.00008671753,0.0002353936,0.008788365,0.0003653909,0.0002073339,0.0001745221,0.0001108283,0.1597124,0.006748103,0.01139382,0.00317813,0.808999],"study_design_scores_gemma":[0.0000123145,0.000116892,0.002750841,0.00006730857,0.00002904784,0.0001434623,0.00005726548,0.9637575,0.007285171,0.01838391,0.007358891,0.00003740421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03946245,0.007319625,0.9437824,0.0009858503,0.0003184117,0.0001035888,0.0001947179,0.001028869,0.006804042],"genre_scores_gemma":[0.6729184,0.00538153,0.3168482,0.000258844,0.0004351004,0.0001427939,0.0003919541,0.00006534014,0.00355774],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001908094,"threshold_uncertainty_score":0.01009107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02392320161754857,"score_gpt":0.2528598816350936,"score_spread":0.228936680017545,"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."}}