{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001385568,0.001058812,0.0006527521,0.0005932562,0.000214341,0.0004605453,0.000635839,0.0005828475,0.0008573054],"category_scores_gemma":[0.003465204,0.0004263578,0.0005762961,0.00065012,0.0001557655,0.0006291467,0.0003540306,0.0009157564,0.0004157749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004608844,"about_ca_system_score_gemma":0.0006282213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01387089,"about_ca_topic_score_gemma":0.009601732,"domain_scores_codex":[0.999613,0.0001543292,0.00003013641,0.00006275818,0.00009805927,0.00004167745],"domain_scores_gemma":[0.9988422,0.0007711099,0.00009410531,0.00004450199,0.0002293227,0.00001887097],"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":[0.0002316035,0.0001327411,0.006512152,0.00007247602,0.0001330572,0.0001166542,0.00003084902,0.9028705,0.003426148,0.0004475643,0.0006541007,0.08537215],"study_design_scores_gemma":[0.000002573469,0.00001728241,0.0003679814,0.000002627026,0.00000699783,0.000005019027,0.00000184661,0.9989523,0.0004795404,0.00009568042,0.00006552194,0.000002648231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3647808,0.001964606,0.6276016,0.0003555177,0.0001600236,0.0001159162,0.0004406879,0.002298496,0.002282399],"genre_scores_gemma":[0.9388698,0.0005263154,0.05695263,0.00006524643,0.00003548117,0.0001158367,0.0005084916,0.00005219858,0.002874041],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01387089,"threshold_uncertainty_score":0.02758032,"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."}}