{"id":"W4387418550","doi":"10.1016/j.jprocont.2023.103091","title":"Image restoration and analysis with application to quality variable prediction in flotation process","year":2023,"lang":"en","type":"article","venue":"Journal of Process Control","topic":"Minerals Flotation and Separation Techniques","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Institute for Oil Sands Innovation, University of Alberta; Natural Sciences and Engineering Research Council of Canada; China Scholarship Council; University of Alberta","keywords":"Outlier; Artificial intelligence; Computer science; Froth flotation; Kalman filter; Noise (video); Process (computing); Computer vision; Pattern recognition (psychology); Image (mathematics); Chemistry","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":[0.0006428607,0.0004981931,0.0006165754,0.0009198929,0.0004557603,0.0006830645,0.0005061658,0.0008605914,0.001828608],"category_scores_gemma":[0.001539532,0.0003768902,0.0005978252,0.0006239646,0.0005315527,0.0005132505,0.0003855781,0.0008050405,0.0004181159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003349019,"about_ca_system_score_gemma":0.0005766139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004264969,"about_ca_topic_score_gemma":0.00350734,"domain_scores_codex":[0.9998415,0.00003208501,0.000009529598,0.00003405668,0.00005855798,0.00002434425],"domain_scores_gemma":[0.9993468,0.0002802061,0.00005686801,0.0000544029,0.000236467,0.00002532577],"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":[0.0008504518,0.000413066,0.002839627,0.0002651197,0.0000796253,0.0001809085,0.00019428,0.09459719,0.1942134,0.002716011,0.001429097,0.7022213],"study_design_scores_gemma":[0.00001702264,0.0001041423,0.002826787,0.00000796211,0.00003209777,0.00008983414,0.00002900536,0.9307289,0.06440309,0.000653333,0.001088619,0.00001927515],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08727402,0.0003533821,0.9090434,0.0002217535,0.00006278302,0.00008376831,0.00006589614,0.001571987,0.001322933],"genre_scores_gemma":[0.5105321,0.0004755771,0.4860664,0.00007486501,0.0000566532,0.00009076436,0.0001049892,0.0001910802,0.002407575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004264969,"threshold_uncertainty_score":0.00848031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008147572609760755,"score_gpt":0.3067596165184351,"score_spread":0.2986120439086744,"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."}}