{"id":"W1970461315","doi":"10.1016/j.isatra.2015.04.001","title":"Process monitoring using kernel density estimation and Bayesian networking with an industrial case study","year":2015,"lang":"en","type":"article","venue":"ISA Transactions","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":94,"is_retracted":false,"has_abstract":false,"ca_institutions":"Suncor Energy (Canada); University of Alberta","funders":"","keywords":"Principal component analysis; Dimensionality reduction; Kernel density estimation; Gaussian process; Artificial intelligence; Kernel principal component analysis; Computer science; Kernel (algebra); Pattern recognition (psychology); Dimension (graph theory); Fault detection and isolation; Independent component analysis; Bayesian probability; Reduction (mathematics); Machine learning; Data mining; Gaussian; Kernel method; Mathematics; Statistics; Support vector machine","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":[0.003224585,0.0006687616,0.00063558,0.00125929,0.0005574894,0.001013167,0.001190699,0.002047415,0.0009848197],"category_scores_gemma":[0.008984648,0.000423704,0.0006967813,0.001165475,0.0008034548,0.00116446,0.0006836313,0.0007101819,0.000119713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009593236,"about_ca_system_score_gemma":0.0005724999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01644909,"about_ca_topic_score_gemma":0.01203947,"domain_scores_codex":[0.9987282,0.0006702506,0.00006279352,0.0001762729,0.0002695709,0.00009299763],"domain_scores_gemma":[0.9914956,0.006955863,0.0004015913,0.0004333969,0.0005995282,0.0001140215],"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":[0.0006907755,0.0006707851,0.02565003,0.00012105,0.0001086477,0.001793517,0.0002439692,0.9071108,0.001399217,0.008551087,0.0009924672,0.05266771],"study_design_scores_gemma":[0.00002117935,0.00006466478,0.002277526,0.000004840234,0.00001949692,0.0001387348,0.00004257427,0.9952467,0.0005344709,0.00146805,0.0001715147,0.00001017673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7951928,0.0005146855,0.1986828,0.0006380081,0.00002766657,0.0001427262,0.0002347698,0.0003622895,0.004204195],"genre_scores_gemma":[0.973461,0.0001308913,0.02540559,0.00001352374,0.000009853738,0.00002819074,0.00008125219,0.00001470429,0.0008550176],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01644909,"threshold_uncertainty_score":0.03270668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05880327707768501,"score_gpt":0.2859767980577272,"score_spread":0.2271735209800422,"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."}}