{"id":"W2893408214","doi":"10.1016/j.ijpharm.2018.08.052","title":"An application of deep learning to detect process upset during pharmaceutical manufacturing using passive acoustic emissions","year":2018,"lang":"en","type":"article","venue":"International Journal of Pharmaceutics","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Distributor; Fluidized bed; Upset; Artificial intelligence; Deep learning; Computer science; Python (programming language); Process (computing); Artificial neural network; Automotive engineering; Process engineering; Environmental science; Engineering; Mechanical engineering; Waste management","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002428438,0.0005539643,0.0003201459,0.0004328097,0.0001566876,0.0003276159,0.0005180916,0.0006136564,0.0007993585],"category_scores_gemma":[0.0004614231,0.0002330219,0.0002851319,0.0002902975,0.000149185,0.0003738592,0.000425302,0.0004282333,0.0002090058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001828439,"about_ca_system_score_gemma":0.0002720262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001775494,"about_ca_topic_score_gemma":0.002901276,"domain_scores_codex":[0.9998734,0.00001422559,0.000006583706,0.00003686081,0.00004878052,0.00002020018],"domain_scores_gemma":[0.9997514,0.0001194714,0.00002739091,0.00001723357,0.00006811848,0.00001634815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008547193,0.0008403686,0.01779539,0.0002737621,0.0001593482,0.0007114165,0.0001189755,0.183535,0.2432175,0.0007412696,0.001960408,0.5497918],"study_design_scores_gemma":[0.000009981143,0.0001133288,0.003547298,0.000005453387,0.00001526553,0.00006412483,0.00001544297,0.9700836,0.02528594,0.0003841078,0.000466549,0.00000891418],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4957775,0.0006382273,0.4964662,0.0002740825,0.0001997235,0.00006198706,0.0002829212,0.002451686,0.00384775],"genre_scores_gemma":[0.9485832,0.0001289528,0.04883025,0.00006772587,0.00002895477,0.00001833763,0.0001223724,0.00003315492,0.002186921],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001775494,"threshold_uncertainty_score":0.003530324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0246653128910031,"score_gpt":0.3745356733545004,"score_spread":0.3498703604634973,"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."}}