{"id":"W3194315986","doi":"10.1002/cjce.24303","title":"Fermentation process quality prediction using teacher student stacked sparse recurrent autoencoder","year":2021,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Autoencoder; Computer science; Artificial intelligence; Process (computing); Pattern recognition (psychology); Recurrent neural network; Distillation; Encoder; Machine learning; Artificial neural network","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":[0.0005730781,0.000642661,0.0006579746,0.0004173814,0.0001814086,0.000476611,0.0006300314,0.0006670039,0.0005751887],"category_scores_gemma":[0.001420102,0.0003642124,0.0007624541,0.0003085019,0.0002268516,0.0005678773,0.0003676884,0.0007858902,0.0001996309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000491578,"about_ca_system_score_gemma":0.0006570359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009423533,"about_ca_topic_score_gemma":0.008139967,"domain_scores_codex":[0.9997494,0.00004565624,0.00001850878,0.00007780175,0.00007277208,0.00003589215],"domain_scores_gemma":[0.9993882,0.0002050916,0.00007859622,0.00004831176,0.0002587523,0.00002095362],"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":[0.0001788734,0.0001373654,0.005064687,0.00006757306,0.00012482,0.0001135764,0.00005301645,0.869278,0.01291496,0.0007573951,0.0007556566,0.110554],"study_design_scores_gemma":[0.000001266889,0.000009119227,0.0002805347,0.000001127629,0.000003955769,0.000003677154,0.000001437808,0.9985943,0.0009977845,0.00007407431,0.00003058413,0.000002074905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1907808,0.000343187,0.8060297,0.0001870714,0.00007035345,0.00003235325,0.0001275253,0.001029866,0.001399231],"genre_scores_gemma":[0.9565705,0.000120183,0.04178504,0.00004654803,0.00002060109,0.00002682846,0.0001900501,0.00002600102,0.00121423],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009423533,"threshold_uncertainty_score":0.01873738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02188636863020503,"score_gpt":0.2698506390176032,"score_spread":0.2479642703873982,"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."}}