{"id":"W3199842479","doi":"10.1109/tcyb.2021.3109618","title":"Toward Robust Fault Identification of Complex Industrial Processes Using Stacked Sparse-Denoising Autoencoder With Softmax Classifier","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"National Science Fund for Distinguished Young Scholars; National Natural Science Foundation of China; Education Department of Hunan Province","keywords":"Softmax function; Pattern recognition (psychology); Artificial intelligence; Autoencoder; Computer science; Noise reduction; Classifier (UML); Robustness (evolution); Sparse approximation; Machine learning; Feature learning; Fault detection and isolation; Deep learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009669054,0.0002119988,0.0002927207,0.0001393477,0.0001116107,0.0001010175,0.0001079447,0.0001823099,0.00008760055],"category_scores_gemma":[0.00001311909,0.0002151895,0.00007321207,0.0006079783,0.00006832363,0.0001465417,9.032702e-7,0.0003046919,0.00001439299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001375126,"about_ca_system_score_gemma":0.0001587439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005523485,"about_ca_topic_score_gemma":0.0002236762,"domain_scores_codex":[0.9985689,0.00005683823,0.0005227801,0.0002544326,0.0003620007,0.0002350402],"domain_scores_gemma":[0.9991685,0.00006778438,0.0001124623,0.0002740803,0.0002942679,0.00008296862],"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":[0.00004335205,0.00008736918,0.00001566603,0.0001427624,0.0001253864,0.000007197926,0.0004560144,0.9261901,0.06937613,0.000009105465,0.00006478513,0.003482174],"study_design_scores_gemma":[0.001355236,0.00007939807,0.00008462343,0.0001802471,0.0001749366,0.00006866598,0.001027858,0.7408086,0.2544566,0.00001473295,0.001415266,0.0003338045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1658615,0.00006919278,0.8323447,0.00004685835,0.0007980633,0.0002366234,0.00005722438,0.0002395526,0.000346332],"genre_scores_gemma":[0.9979068,0.00003387546,0.001443757,0.00001686375,0.00009058054,0.0000214333,0.000007160809,0.00005873778,0.0004208123],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8320453,"threshold_uncertainty_score":0.8775172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08324951348829113,"score_gpt":0.251822423041248,"score_spread":0.1685729095529569,"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."}}