{"id":"W2884313434","doi":"10.1049/hve.2018.5048","title":"Towards automated statistical partial discharge source classification using pattern recognition techniques","year":2018,"lang":"en","type":"article","venue":"High Voltage","topic":"High voltage insulation and dielectric phenomena","field":"Materials Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba; Powertech Labs (Canada)","funders":"Korea Food and Drug Administration; University of Manitoba","keywords":"Partial discharge; Pattern recognition (psychology); Classifier (UML); Computer science; Artificial intelligence; Probabilistic logic; Statistical classification; Data mining; Feature extraction; Fuzzy logic; Naive Bayes classifier; Voltage; Support vector machine; Engineering","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004711197,0.0002038137,0.0002320468,0.0001334966,0.0003073547,0.0001525517,0.0001861303,0.0001318667,0.002954619],"category_scores_gemma":[0.0001671871,0.0001847264,0.00003739625,0.0002753673,0.000208811,0.0003209832,0.00005962623,0.0001112536,0.001530318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001284478,"about_ca_system_score_gemma":0.00007111127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004122323,"about_ca_topic_score_gemma":0.00001420617,"domain_scores_codex":[0.9981937,0.0001429512,0.0004649804,0.0004472325,0.000331171,0.0004199014],"domain_scores_gemma":[0.9991261,0.00005651433,0.0002078271,0.0002958016,0.0001602009,0.0001535885],"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":[0.00004221339,0.000109476,0.0003448018,0.00001957751,0.000004926305,0.000003835699,0.0003450955,0.000001238862,0.9679825,0.0008534483,0.001815149,0.02847779],"study_design_scores_gemma":[0.0007552235,0.0003656622,0.0168888,0.00007823834,0.00007163241,0.0000193957,0.00008557425,0.1780041,0.7844374,0.002833105,0.01568489,0.0007759908],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4923545,0.00000747788,0.5052516,0.00005087944,0.0003162787,0.0002278824,0.0001132339,0.0009612072,0.0007168806],"genre_scores_gemma":[0.9888277,0.000005141531,0.009812622,0.0003027604,0.0006727107,0.0000449795,0.0001857627,0.00003297278,0.000115341],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4964732,"threshold_uncertainty_score":0.9992471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04003061014864647,"score_gpt":0.3001864776188852,"score_spread":0.2601558674702388,"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."}}