{"id":"W2982556568","doi":"10.1002/cjce.23669","title":"Deep neural network based recursive feature learning for nonlinear dynamic process monitoring","year":2019,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Autocorrelation; Artificial neural network; Computer science; Benchmark (surveying); Fault detection and isolation; Predictability; Process (computing); Principal component analysis; Artificial intelligence; Noise (video); Nonlinear system; Feature (linguistics); Noise reduction; Pattern recognition (psychology); Recurrent neural network; Dynamic data; Machine learning; Deep learning; Algorithm; Mathematics; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001893623,0.0001525817,0.0002289843,0.00008455101,0.00006194472,0.00006548037,0.0002301285,0.0001139121,0.000008852138],"category_scores_gemma":[0.0001019694,0.0001274047,0.0001297047,0.0001844338,0.00001169722,0.00008468638,0.000002933365,0.0006589328,0.000003328409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002338674,"about_ca_system_score_gemma":0.0000770668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002561451,"about_ca_topic_score_gemma":0.00004680158,"domain_scores_codex":[0.9991779,0.00001023466,0.0002230767,0.00007945057,0.0001302093,0.0003791443],"domain_scores_gemma":[0.9993588,0.0001128883,0.00006541593,0.00009901308,0.0001035801,0.0002602724],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000127761,7.51764e-7,0.00016523,0.00007731395,0.00003975131,0.000004949523,0.00009989843,0.9890934,0.00972963,0.000004546782,0.0000356745,0.0007360617],"study_design_scores_gemma":[0.0004289564,0.0000335955,0.00004399113,0.0001443492,0.00002224691,0.00005548289,0.00004238883,0.9913887,0.005728588,0.00001178295,0.00195317,0.0001467077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9861078,0.001839877,0.008229909,0.0003739145,0.002938577,0.000322354,0.000003346268,0.00009798423,0.00008629631],"genre_scores_gemma":[0.9985515,9.703388e-7,0.0006203558,0.0000191692,0.0007180315,0.00000929357,0.000002333689,0.00005011601,0.00002818355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01244381,"threshold_uncertainty_score":0.5195414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003400465189036944,"score_gpt":0.191355699971153,"score_spread":0.1879552347821161,"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."}}