{"id":"W4307793420","doi":"10.1002/cjce.24749","title":"A <scp>CNN</scp> approach based on correlation metrics to chemical process fault classifications with limited labelled data","year":2022,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Data mining; Classifier (UML); Convolutional neural network; Heuristic; Fault (geology); Artificial intelligence; Correlation; Pattern recognition (psychology); Entropy (arrow of time); Machine learning; 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":[0.000734303,0.0007070737,0.0004825709,0.001055332,0.0002796582,0.0007451735,0.0009138023,0.0006887282,0.001440312],"category_scores_gemma":[0.001893334,0.0002592435,0.0005094403,0.000829008,0.0004711676,0.0009037895,0.0007110108,0.0006298048,0.0002876258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001040729,"about_ca_system_score_gemma":0.000987242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01047078,"about_ca_topic_score_gemma":0.009663278,"domain_scores_codex":[0.9996758,0.00006503983,0.00002113517,0.00008734755,0.0001004263,0.000050315],"domain_scores_gemma":[0.9994032,0.0001743728,0.0001064646,0.00008454285,0.0002023754,0.00002886681],"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":[0.0001253543,0.00007977393,0.003995375,0.00007902001,0.00009214582,0.0001761068,0.00005136764,0.6836735,0.01359805,0.007164047,0.001750755,0.2892145],"study_design_scores_gemma":[8.951789e-7,0.00001110626,0.000285689,0.000002559911,0.000003995678,0.00000967604,0.00000311688,0.9972597,0.001485363,0.0007820118,0.000153582,0.000002168182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05432722,0.0002469447,0.9420335,0.0002735327,0.00004480399,0.00004861906,0.0001308522,0.000683383,0.002211176],"genre_scores_gemma":[0.8739411,0.0001726898,0.1231575,0.0001083366,0.00004785185,0.00006558187,0.00029198,0.00006384992,0.002151116],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01047078,"threshold_uncertainty_score":0.02081966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01798455031363288,"score_gpt":0.2013323768855991,"score_spread":0.1833478265719662,"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."}}