{"id":"W1499280929","doi":"10.1109/tdei.2015.004731","title":"Neural network approach to separate aging and moisture from the dielectric response of oil impregnated paper insulation","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Dielectrics and Electrical Insulation","topic":"Power Transformer Diagnostics and Insulation","field":"Engineering","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"Université du Québec à Chicoutimi","keywords":"Moisture; Dielectric response; Accelerated aging; Dielectric; Artificial neural network; Transformer; Materials science; Transformer oil; Pressboard; Composite material; Electrical insulation paper; Environmental science; Electronic engineering; Electrical engineering; Engineering; Voltage; Computer science; Optoelectronics; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003526369,0.000247354,0.0002523781,0.0002281065,0.0001904499,0.00007936296,0.00009882927,0.0001852048,0.000001921376],"category_scores_gemma":[0.00005235465,0.0002071908,0.00005375215,0.001691288,0.00002927654,0.0002442806,0.000001911601,0.0003941504,0.000001988968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001101217,"about_ca_system_score_gemma":0.00003758116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001361966,"about_ca_topic_score_gemma":0.00001232529,"domain_scores_codex":[0.9985269,0.0001268644,0.0003991545,0.0002939997,0.0002915965,0.0003614979],"domain_scores_gemma":[0.9989034,0.0005313753,0.00005983424,0.000186581,0.0001364953,0.0001823362],"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":[0.000657695,0.0001479582,0.0005062752,0.00002032398,0.0001142444,0.000001118314,0.001024004,0.8405375,0.02717393,0.0004237886,0.0001566121,0.1292366],"study_design_scores_gemma":[0.0008089819,0.0003764808,0.06483534,0.00002576863,0.00009381059,0.000005060718,0.00001297535,0.9280541,0.004326385,0.0006379946,0.0005375287,0.000285569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7576488,0.00233566,0.2388756,0.0001752401,0.0002015991,0.0002518402,0.00002122101,0.0001170089,0.0003730554],"genre_scores_gemma":[0.9981217,0.001062013,0.0004140331,0.0001978866,0.00007645095,0.00004229203,0.00002431846,0.00003662778,0.00002471506],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2404729,"threshold_uncertainty_score":0.8448995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01647941111427132,"score_gpt":0.2238447337778483,"score_spread":0.207365322663577,"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."}}