{"id":"W2132458875","doi":"10.1109/tdei.2012.6180233","title":"Artificial neural networks with stepwise regression for predicting transformer oil furan content","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Dielectrics and Electrical Insulation","topic":"Power Transformer Diagnostics and Insulation","field":"Engineering","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Transformer oil; Furan; Transformer; Artificial neural network; Dissolved gas analysis; Water content; Environmental science; Pulp and paper industry; Process engineering; Petroleum engineering; Chemistry; Engineering; Waste management; Voltage; Computer science; Electrical engineering; Machine learning; Organic chemistry","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":[0.0001662833,0.0002600222,0.0002268661,0.0002347064,0.00030403,0.00006135784,0.00005274264,0.0001900427,0.000006304831],"category_scores_gemma":[0.000008103733,0.0002147518,0.00008663072,0.0005707892,0.00002565502,0.0003967597,2.095015e-7,0.0003514994,0.000001151427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001015007,"about_ca_system_score_gemma":0.00001261126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001285494,"about_ca_topic_score_gemma":0.00001184751,"domain_scores_codex":[0.9985914,0.00002347399,0.000370212,0.000210483,0.0002214512,0.0005829677],"domain_scores_gemma":[0.9993161,0.0002506291,0.00004577578,0.0001057933,0.00008689785,0.0001948107],"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":[0.000533925,0.0002972956,0.0007715818,0.00006333696,0.0001052958,7.354739e-7,0.0003430728,0.2349997,0.01100549,0.0003980019,0.00002300152,0.7514586],"study_design_scores_gemma":[0.0006974394,0.0005475172,0.003552024,0.00003591289,0.0001300178,0.000009706457,0.00001343769,0.9762748,0.01815625,0.00003607568,0.0002402082,0.0003066081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3854191,0.0005140746,0.6131554,0.00004700366,0.0003244549,0.0002459764,0.00001430599,0.0001405012,0.0001391501],"genre_scores_gemma":[0.9983585,0.0008296552,0.0003366944,0.00005821817,0.0001778294,0.0001306006,0.00002896908,0.00005278944,0.00002670106],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.751152,"threshold_uncertainty_score":0.8757325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02828671567274895,"score_gpt":0.2325031597826222,"score_spread":0.2042164441098732,"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."}}