{"id":"W4407264112","doi":"10.1016/j.neucom.2025.129619","title":"Novel dynamic data-driven modeling based on feature enhancement with derivative memory LSTM for complex industrial process","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Key Laboratory of System Control and Information Processing; National Natural Science Foundation of China","keywords":"Computer science; Process (computing); Feature (linguistics); Dynamic data; Artificial intelligence; Long short term memory; Derivative (finance); Dynamic random-access memory; Data mining; Pattern recognition (psychology); Machine learning; Recurrent neural network; Artificial neural network; Semiconductor memory; Computer hardware; Database","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":[0.0001162424,0.0002133191,0.0002498573,0.0001237933,0.0001676734,0.000069886,0.0002966812,0.00008621444,0.000002304866],"category_scores_gemma":[0.00003629008,0.0001959149,0.00003602167,0.0002713888,0.00001188235,0.00007645791,0.00003897727,0.0003004214,0.000001486976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008349234,"about_ca_system_score_gemma":0.00005799825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006994598,"about_ca_topic_score_gemma":0.00001751773,"domain_scores_codex":[0.9989086,0.00002274852,0.0002321082,0.0003883725,0.0001791706,0.0002689391],"domain_scores_gemma":[0.9993939,0.0001184047,0.00005806353,0.0003193909,0.00006845032,0.00004181144],"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":[0.0001012181,0.00002864011,0.000009265236,0.0001284235,0.00004096132,0.000001031723,0.00006354663,0.9776548,0.01185146,0.00001164924,0.0001979434,0.009911126],"study_design_scores_gemma":[0.002397313,0.00009466399,0.00002340365,0.0002621103,0.0000241609,0.000001893778,0.0001243005,0.995063,0.0009072837,0.000003413726,0.000920763,0.0001776991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08346178,0.00001421283,0.9134597,0.0002303488,0.000521127,0.001011639,0.00003282118,0.000347954,0.0009204709],"genre_scores_gemma":[0.99584,2.896019e-7,0.003432408,0.0003467351,0.0001505819,0.00007815368,0.00006965167,0.00003589554,0.00004633118],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9123782,"threshold_uncertainty_score":0.7989176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04135916133846052,"score_gpt":0.2821693806037689,"score_spread":0.2408102192653084,"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."}}