{"id":"W2971407654","doi":"10.1109/tii.2019.2938890","title":"Hierarchical Quality-Relevant Feature Representation for Soft Sensor Modeling: A Novel Deep Learning Strategy","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":281,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Higher Education Discipline Innovation Project; National Key Research and Development Program of China Stem Cell and Translational Research; Natural Science Foundation of Hunan Province; Central South University; National Natural Science Foundation of China","keywords":"Autoencoder; Computer science; Artificial intelligence; Deep learning; Feature extraction; Soft sensor; Feature (linguistics); Feature learning; Quality (philosophy); Pattern recognition (psychology); Constraint (computer-aided design); Representation (politics); Data mining; Flexibility (engineering); Machine learning; Process (computing); Engineering","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":[0.0003031597,0.0002228519,0.0003271913,0.0001972182,0.0001650851,0.0001332542,0.0001143433,0.0004311583,0.00003412645],"category_scores_gemma":[0.00003256579,0.0002190587,0.0001937183,0.0002539658,0.00001649356,0.0003428179,7.931576e-7,0.001007603,0.00008401146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001207962,"about_ca_system_score_gemma":0.0000423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003431792,"about_ca_topic_score_gemma":0.0000194474,"domain_scores_codex":[0.9985045,0.000045813,0.0007100199,0.0001295467,0.0003009041,0.0003091824],"domain_scores_gemma":[0.9992095,0.0002509828,0.0001021226,0.0002320157,0.00008888201,0.00011646],"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":[0.0001800242,0.00002819785,0.000002678347,0.00007226458,0.00009304352,1.456578e-7,0.0006881845,0.9718043,0.002271201,0.00006202372,0.00006604366,0.02473195],"study_design_scores_gemma":[0.002965528,0.000192776,0.000001205521,0.00004716003,0.00003649601,0.0000106418,0.002670323,0.9887562,0.002107046,0.00001894405,0.002937922,0.0002557679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1095342,0.000007340247,0.8865278,0.00006939789,0.001765319,0.0008547005,0.00005216699,0.0003956158,0.0007934095],"genre_scores_gemma":[0.9976875,0.000009948755,0.001027625,0.00004110142,0.0002188504,0.00011135,0.00002096973,0.00003918941,0.0008434688],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8881533,"threshold_uncertainty_score":0.8932956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05716108803394792,"score_gpt":0.2893104638036404,"score_spread":0.2321493757696925,"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."}}