{"id":"W3012228302","doi":"10.1002/cjce.23750","title":"Research on <scp>TE</scp> process fault diagnosis method based on <scp>DBN</scp> and dropout","year":2020,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Overfitting; Dropout (neural networks); Deep belief network; Artificial intelligence; Computer science; Process (computing); Deep learning; Machine learning; Fault (geology); Generalization; Nonlinear system; Representation (politics); Feature (linguistics); Pattern recognition (psychology); Artificial neural network; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001309447,0.0005733641,0.0006737126,0.0008562743,0.0005074193,0.0007609189,0.001021489,0.0009162024,0.001212468],"category_scores_gemma":[0.002402661,0.0002773162,0.0006632474,0.0006573691,0.000700833,0.001752089,0.0007062615,0.001250343,0.0002035609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001334238,"about_ca_system_score_gemma":0.001655045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01491433,"about_ca_topic_score_gemma":0.00631736,"domain_scores_codex":[0.9993528,0.00007885169,0.00004022061,0.0001716743,0.0002884539,0.00006797999],"domain_scores_gemma":[0.9990842,0.0002857025,0.000117311,0.00006987513,0.0003877728,0.00005505398],"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":[0.0004557667,0.0002244725,0.008969557,0.000289109,0.0001204039,0.0003178512,0.0001739287,0.4085183,0.02888136,0.01382311,0.003238345,0.5349878],"study_design_scores_gemma":[0.000004442243,0.00003067935,0.0005451579,0.000004177832,0.000007434052,0.00002901124,0.000008093495,0.9942538,0.004146896,0.0006456982,0.0003196959,0.000004935437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0425129,0.0005813829,0.9535612,0.0005410335,0.00007308327,0.00005011934,0.00004209586,0.0006861993,0.00195194],"genre_scores_gemma":[0.8853871,0.0006925951,0.1089407,0.0002043845,0.00005367952,0.00004988392,0.000187536,0.00005646753,0.004427558],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01491433,"threshold_uncertainty_score":0.02965504,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02230530519805363,"score_gpt":0.2682691692628726,"score_spread":0.245963864064819,"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."}}