{"id":"W2784250169","doi":"10.1109/ceidp.2017.8257557","title":"Condition monitoring of oil-filled transformers using unsupervised classification techniques","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Power Transformer Diagnostics and Insulation","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Transformer; Dissolved gas analysis; Transformer oil; Feature vector; Condition monitoring; Computer science; Fuzzy logic; Pattern recognition (psychology); Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001575895,0.0002725844,0.0003659315,0.000225938,0.00008665487,0.00007093159,0.0002227907,0.0004027811,0.00004041057],"category_scores_gemma":[0.00001790995,0.0002919599,0.0001548114,0.00005221414,0.00005403584,0.0002449179,0.00002070723,0.0003151192,0.000002637586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001417934,"about_ca_system_score_gemma":0.00006667632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009529982,"about_ca_topic_score_gemma":0.000005428124,"domain_scores_codex":[0.9988104,0.00001457606,0.0005129483,0.0002320443,0.0002255276,0.0002045641],"domain_scores_gemma":[0.9992696,0.00003790737,0.0001264251,0.0003708104,0.0001347232,0.00006051941],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000518067,0.0001757216,0.007575075,0.009603622,0.0005799399,0.000004575644,0.001344251,0.03652311,0.704415,0.001239932,0.0001058695,0.2383811],"study_design_scores_gemma":[0.0005824312,0.00004174936,0.01512644,0.005218285,0.0002681817,0.000002471592,0.0001668035,0.2623715,0.7140065,0.001034278,0.0003269534,0.0008544668],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7297539,0.0007001618,0.2168197,0.00005026046,0.002016237,0.0007390582,0.000210632,0.000818498,0.04889157],"genre_scores_gemma":[0.9884471,0.003761066,0.007289663,0.000002120535,0.0001370832,0.00006994806,0.0002139571,0.00005710422,0.00002195544],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2586932,"threshold_uncertainty_score":0.9999533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04728995972111614,"score_gpt":0.296575969396902,"score_spread":0.2492860096757858,"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."}}