{"id":"W2133077909","doi":"10.1109/tdei.2011.6118628","title":"Particle swarm optimization feature selection for the classification of conducting particles in transformer oil","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Dielectrics and Electrical Insulation","topic":"Power Transformer Diagnostics and Insulation","field":"Engineering","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Particle swarm optimization; Feature selection; Transformer oil; Pattern recognition (psychology); Classifier (UML); Partial discharge; Computer science; Artificial intelligence; Transformer; Data mining; Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001089431,0.0004497036,0.0008065919,0.0008475892,0.0003192562,0.0005821117,0.0003635831,0.0004819434,0.0003403244],"category_scores_gemma":[0.00266916,0.0002277393,0.0004825155,0.0007243007,0.0003038157,0.0003615663,0.0002340276,0.0004108578,0.0001245316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004034221,"about_ca_system_score_gemma":0.0004827464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003883801,"about_ca_topic_score_gemma":0.001774903,"domain_scores_codex":[0.9997148,0.00009739742,0.00002512761,0.00004010952,0.00009559689,0.00002692687],"domain_scores_gemma":[0.9993439,0.0003669159,0.000053379,0.00003379206,0.0001819712,0.00002001585],"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":[0.0003992793,0.0001842841,0.004539369,0.0001121477,0.00009084981,0.0001255892,0.000152695,0.5733653,0.02095208,0.00263399,0.002139061,0.3953053],"study_design_scores_gemma":[0.0000107598,0.00002721221,0.0008199025,0.000002378532,0.000005375144,0.00001018446,0.000008474672,0.9972915,0.001387069,0.0002705941,0.0001628219,0.000003667484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1626941,0.0004403517,0.8350677,0.0002434812,0.00007087729,0.00008833582,0.000089339,0.0004964317,0.0008093147],"genre_scores_gemma":[0.7737242,0.0001645197,0.2248043,0.00004144485,0.00003735933,0.0001537974,0.0001932381,0.00003587218,0.0008452609],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003883801,"threshold_uncertainty_score":0.007722378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05472572116938798,"score_gpt":0.2472473459219794,"score_spread":0.1925216247525914,"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."}}