{"id":"W4402571999","doi":"10.1109/phm61473.2024.00063","title":"Can graph neural networks outperform in supervised classification of noisy acoustic signals? An industrial case study of hydroelectric generator","year":2024,"lang":"en","type":"article","venue":"","topic":"Water Systems and Optimization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Hydro-Québec","funders":"","keywords":"Hydroelectricity; Generator (circuit theory); Computer science; Graph; Artificial neural network; Artificial intelligence; Signal generator; Speech recognition; Pattern recognition (psychology); Machine learning; Electrical engineering; Theoretical computer science; Engineering; Telecommunications","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":[0.002620125,0.001140272,0.0007089286,0.0009215758,0.0003618785,0.0009199515,0.0007325704,0.001435301,0.001126874],"category_scores_gemma":[0.007953593,0.0001715239,0.0004756056,0.0005663057,0.0006695074,0.001477887,0.000528179,0.0009221287,0.0004682114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000596985,"about_ca_system_score_gemma":0.0005361399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004700832,"about_ca_topic_score_gemma":0.007431084,"domain_scores_codex":[0.9990473,0.0004318986,0.00003839875,0.0002226642,0.0001552441,0.0001044665],"domain_scores_gemma":[0.9969468,0.001917662,0.0002398382,0.0002713028,0.0004979558,0.0001265218],"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":[0.001174496,0.0005422425,0.01997725,0.0005099847,0.0003030547,0.000573383,0.0001545487,0.6624945,0.008633316,0.004705548,0.007023393,0.2939082],"study_design_scores_gemma":[0.00001527324,0.0001831649,0.002485669,0.00002345336,0.00002733709,0.00004805469,0.00007130492,0.9893368,0.002667648,0.004419139,0.0007109668,0.00001123944],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8131024,0.003443421,0.1692386,0.002666089,0.0004549685,0.0001409198,0.0005319724,0.001473534,0.008948076],"genre_scores_gemma":[0.9767317,0.0002834456,0.02101805,0.0001584246,0.00005754055,0.0000201855,0.0004068333,0.00005034653,0.001273623],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004700832,"threshold_uncertainty_score":0.01385677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03302522523803908,"score_gpt":0.2277567947137994,"score_spread":0.1947315694757604,"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."}}