{"id":"W3171398265","doi":"10.1109/tnnls.2021.3085869","title":"A Deep Probabilistic Transfer Learning Framework for Soft Sensor Modeling With Missing Data","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":123,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China-Zhejiang Joint Fund for the Integration of Industrialization and Informatization; State Key Laboratory of Industrial Control Technology; National Natural Science Foundation of China","keywords":"Soft sensor; Computer science; Artificial intelligence; Probabilistic logic; Missing data; Transfer of learning; Deep learning; Deep belief network; Machine learning; Gaussian process; Kriging; Bayes' theorem; Process (computing); Generative model; Data mining; Feature (linguistics); Data-driven; Gaussian; Generative grammar; Bayesian probability","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003075576,0.0003060026,0.0004209194,0.00007754189,0.0006601358,0.0003326808,0.0001230715,0.0002172865,0.000008932684],"category_scores_gemma":[0.00002860235,0.0002781348,0.00008698067,0.0002663905,0.00002967888,0.0001911222,0.000001486434,0.001215079,0.000002056749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004246829,"about_ca_system_score_gemma":0.0000182339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003445072,"about_ca_topic_score_gemma":0.00005063468,"domain_scores_codex":[0.9982042,0.0002453635,0.0003968537,0.000517534,0.0001984465,0.0004376509],"domain_scores_gemma":[0.9988837,0.0005029007,0.00003646881,0.0003325247,0.00009047587,0.0001539538],"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":[0.00008704085,0.00001733673,0.000008633949,0.0002709061,0.0001209468,0.00001319442,0.0002387287,0.9797361,0.0002562755,0.00002913958,0.000003180396,0.01921846],"study_design_scores_gemma":[0.0006447577,0.0001573903,0.000001563807,0.0004290363,0.0001165254,0.0001943126,0.001070534,0.9960518,0.0000214433,0.000005553407,0.0009647221,0.0003423482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0260688,0.001529712,0.9701545,0.00006164254,0.001101021,0.0004651336,0.000006758631,0.0005755375,0.0000369348],"genre_scores_gemma":[0.9983045,0.00007225613,0.0007968929,0.00002566326,0.0003330873,0.0001170174,0.0000173932,0.0001056039,0.000227512],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9722358,"threshold_uncertainty_score":0.9999671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02196076926981322,"score_gpt":0.2333345430326874,"score_spread":0.2113737737628741,"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."}}