{"id":"W2032136265","doi":"10.1016/j.jprocont.2012.12.008","title":"Development and industrial application of soft sensors with on-line Bayesian model updating strategy","year":2013,"lang":"en","type":"article","venue":"Journal of Process Control","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Syncrude (Canada); University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Syncrude","keywords":"Soft sensor; Computer science; Process (computing); Measure (data warehouse); Calibration; Data mining; Line (geometry); Bayesian probability; Particle filter; Bayesian inference; Maximization; Key (lock); Machine learning; Artificial intelligence; Kalman filter; Mathematical optimization; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001524957,0.0001041195,0.0002483761,0.00009084336,0.00003023838,0.00003076534,0.00006454031,0.00006678588,0.000006074579],"category_scores_gemma":[0.0000252053,0.00007621504,0.00002208394,0.00007744657,0.00001250766,0.0001582291,0.000001934275,0.0001835479,0.000001691381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002904739,"about_ca_system_score_gemma":0.00007410573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004479461,"about_ca_topic_score_gemma":0.000005560617,"domain_scores_codex":[0.9991549,0.00001317725,0.0004523316,0.0000671417,0.000202486,0.0001099917],"domain_scores_gemma":[0.9993907,0.00002903887,0.0002531203,0.00005339095,0.0001799793,0.00009375422],"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":[0.0001194583,0.00002242424,0.0002477209,0.00005791289,0.0001012326,0.00000114081,0.0002398231,0.9449371,0.005942813,0.00005918253,0.00002958542,0.04824166],"study_design_scores_gemma":[0.002562102,0.0001394685,0.00007286676,0.00006832059,0.00001688555,0.00002500129,0.0004023523,0.9933948,0.003074886,0.00005378151,0.0001007993,0.00008871582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.767848,0.00008329791,0.2312935,0.0000845489,0.00004853652,0.0002961049,0.000001705391,0.00002765201,0.0003166715],"genre_scores_gemma":[0.9992632,0.000001672697,0.000540341,0.00002597174,0.0001155702,0.00002469827,3.299426e-7,0.00001453243,0.00001365184],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2314153,"threshold_uncertainty_score":0.3107959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01503371609534524,"score_gpt":0.2300389494254514,"score_spread":0.2150052333301062,"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."}}