{"id":"W4391743524","doi":"10.1371/journal.pone.0295144","title":"Ensemble learning based transmission line fault classification using phasor measurement unit (PMU) data with explainable AI (XAI)","year":2024,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Power Systems Fault Detection","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"North South University","keywords":"Phasor; Phasor measurement unit; Interpretability; Computer science; Units of measurement; Ensemble learning; Random forest; Decision tree; Electric power transmission; Transmission line; Fault (geology); Artificial intelligence; Data mining; Transmission (telecommunications); Electric power system; Pattern recognition (psychology); Machine learning; Power (physics); Engineering; Physics","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":[0.0005923017,0.0002128526,0.0002261119,0.0002103588,0.000136186,0.0001413688,0.000201731,0.0001086801,0.00004441343],"category_scores_gemma":[0.0000505597,0.0002002013,0.0000260171,0.0004870609,0.00001434148,0.0005278018,0.0000187057,0.000412577,0.00005064812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003019481,"about_ca_system_score_gemma":0.00009441147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006018921,"about_ca_topic_score_gemma":0.0000319643,"domain_scores_codex":[0.99823,0.00008196232,0.0002883859,0.0003933887,0.0007076238,0.000298677],"domain_scores_gemma":[0.9991616,0.00004001859,0.00003657545,0.0005102901,0.0001493561,0.00010215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000047578,0.00019445,0.00005663394,0.001474438,0.0002423353,0.00001773435,0.0002384098,0.04513196,0.9407669,0.000005950418,0.0001209616,0.01170263],"study_design_scores_gemma":[0.0003388615,0.00007922114,0.00001667983,0.001561915,0.0001679039,0.000005549869,0.00008215385,0.7908116,0.1887557,0.000003342467,0.01797243,0.0002046543],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0806157,0.001377956,0.9152193,0.0001809621,0.0001782819,0.0005102795,0.00001448672,0.001260869,0.0006421692],"genre_scores_gemma":[0.9942929,0.00003110306,0.005078068,0.00001225889,0.0001400729,0.00004580475,0.0001025837,0.00009904638,0.000198153],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9136772,"threshold_uncertainty_score":0.8163971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1709309612514925,"score_gpt":0.2786702140175337,"score_spread":0.1077392527660413,"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."}}