{"id":"W4403127310","doi":"10.1109/pesgm51994.2024.10688689","title":"Enhancing Power Quality Event Classification with AI Transformer Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Power Quality and Harmonics","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Concordia University","funders":"","keywords":"Computer science; Power quality; Transformer; Artificial intelligence; Engineering; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003831658,0.000704544,0.000522821,0.0005553489,0.0001458,0.0006210139,0.0007060624,0.0004355608,0.001216453],"category_scores_gemma":[0.001340493,0.0001607238,0.0004849445,0.0004784026,0.0001856901,0.0008362653,0.0005593094,0.0009230711,0.0005158365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004141451,"about_ca_system_score_gemma":0.0003663539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006117163,"about_ca_topic_score_gemma":0.005930965,"domain_scores_codex":[0.9998409,0.00002784524,0.000009089827,0.00004744695,0.00004741398,0.00002728578],"domain_scores_gemma":[0.9996884,0.0001321924,0.00003635765,0.00002872136,0.00009679945,0.00001765864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002400233,0.0002695353,0.00467997,0.00009277243,0.0000839461,0.0001205532,0.00005994851,0.4977026,0.01137342,0.004235689,0.005028015,0.4761135],"study_design_scores_gemma":[0.00000246425,0.000009806397,0.0002110267,0.000001945044,0.000005055194,0.00001030187,0.000002457449,0.9979697,0.0007145698,0.0008319074,0.0002390058,0.000001708089],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06989592,0.0009147131,0.9210781,0.0004182225,0.0001659622,0.00004450484,0.0002433626,0.002862755,0.004376393],"genre_scores_gemma":[0.9452139,0.0003269679,0.05098481,0.0002124456,0.00009888614,0.00002374576,0.0005469272,0.0000562574,0.002536067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006117163,"threshold_uncertainty_score":0.0121631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04146327127975001,"score_gpt":0.2974083834636971,"score_spread":0.2559451121839471,"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."}}