{"id":"W4232713644","doi":"10.1109/tpwrd.2002.1022786","title":"Pattern recognition applications for power system disturbance classification","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Power Delivery","topic":"Power Quality and Harmonics","field":"Engineering","cited_by":91,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Military College of Canada; University of Waterloo","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Wavelet transform; Feature extraction; Computer science; Multiresolution analysis; Euclidean distance; Wavelet; k-nearest neighbors algorithm; Wavelet packet decomposition; Artificial neural network; Discrete wavelet transform","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":[],"consensus_categories":[],"category_scores_codex":[0.00009859978,0.0001939196,0.0001674683,0.0001266713,0.0002078015,0.0000507265,0.0001443711,0.0001471916,0.000217809],"category_scores_gemma":[0.000001247089,0.0002216657,0.0001564907,0.0001931159,0.00003447367,0.0002300995,4.875062e-7,0.000215777,0.0007275479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002121372,"about_ca_system_score_gemma":0.000006688356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004772277,"about_ca_topic_score_gemma":0.000007842336,"domain_scores_codex":[0.9989516,0.00002646844,0.0003245544,0.0002756285,0.0001629899,0.0002587346],"domain_scores_gemma":[0.9993011,0.000105413,0.00004824888,0.000357226,0.00009576558,0.00009221732],"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":[0.0002530373,0.00288436,0.00003464671,0.002380194,0.001285941,0.00002149953,0.007264779,0.03893708,0.02332835,0.001481275,0.0471433,0.8749855],"study_design_scores_gemma":[0.00430529,0.0006591366,0.0009708076,0.0006494628,0.0006121703,0.000109426,0.002747652,0.6916901,0.04267405,0.0004172086,0.2519693,0.003195353],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009869893,0.0002509716,0.9836233,0.0001167199,0.0009353942,0.0006762199,0.0006263208,0.0007037015,0.003197495],"genre_scores_gemma":[0.9979843,0.0001694753,0.0005207452,0.0001313716,0.0000375008,0.0008384374,0.00002907205,0.00005104484,0.0002379946],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9881145,"threshold_uncertainty_score":0.93514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04537264374810577,"score_gpt":0.2230594488496425,"score_spread":0.1776868051015367,"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."}}