{"id":"W4224292371","doi":"10.1007/s00521-022-07219-z","title":"Deep learning for high-impedance fault detection and classification: transformer-CNN","year":2022,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Power Systems Fault Detection","field":"Engineering","cited_by":39,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Robustness (evolution); Transformer; High impedance; Pattern recognition (psychology); Deep learning; Fault detection and isolation; Machine learning; Electrical impedance; Engineering; Voltage","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002849371,0.0006161829,0.0003529726,0.0003432668,0.0001412817,0.000515137,0.0006905934,0.0004852217,0.002611193],"category_scores_gemma":[0.000994939,0.0002323488,0.0003034947,0.0005502601,0.0001991265,0.0008619928,0.0006067398,0.0008386787,0.0007368792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005591934,"about_ca_system_score_gemma":0.0004707452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0101174,"about_ca_topic_score_gemma":0.01367067,"domain_scores_codex":[0.9999013,0.00001486189,0.000004138313,0.00002810877,0.00002788572,0.00002370317],"domain_scores_gemma":[0.9998143,0.00005441393,0.00002023265,0.00002977909,0.00006715719,0.00001416213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003739331,0.0001350535,0.003262425,0.0001504867,0.00009782054,0.0001596719,0.00005308114,0.2584571,0.02839325,0.009415899,0.01385776,0.6856436],"study_design_scores_gemma":[0.000003851506,0.00001617347,0.0003044628,0.00000442615,0.000008492767,0.00002891353,0.000005023028,0.9929322,0.004013769,0.001867281,0.0008124008,0.000003072842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06747537,0.001411583,0.9236139,0.0004054704,0.0001416938,0.00003234527,0.0003960273,0.002150708,0.004372896],"genre_scores_gemma":[0.8738494,0.0007384316,0.115909,0.0001614932,0.00006806751,0.00002510302,0.0007583504,0.0001181971,0.008371925],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0101174,"threshold_uncertainty_score":0.02011704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01156703851866786,"score_gpt":0.2404674816392711,"score_spread":0.2289004431206032,"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."}}