{"id":"W4403667757","doi":"10.1016/j.eswa.2024.125614","title":"Multi-scale neural network for accurate determination of the ash content of coal flotation concentrate using froth images","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Minerals Flotation and Separation Techniques","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lakes Environmental (Canada); University of Waterloo; Ministry of Education and Child Care","funders":"Fundamental Research Funds for the Central Universities","keywords":"Computer science; Artificial neural network; Coal; Artificial intelligence; Scale (ratio); Content (measure theory); Process engineering; Froth flotation; Pulp and paper industry; Pattern recognition (psychology); Computer vision; Chemistry; Mathematics; Materials science; Metallurgy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002322898,0.000335082,0.0002164726,0.0005139023,0.0001577371,0.0002380895,0.0003168348,0.0004856803,0.0007630312],"category_scores_gemma":[0.0003472314,0.0001668689,0.0002757756,0.0003584372,0.0001063068,0.0003278086,0.0001876399,0.0002942432,0.0001822978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002921431,"about_ca_system_score_gemma":0.0002409696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00779189,"about_ca_topic_score_gemma":0.01054774,"domain_scores_codex":[0.999929,0.000007757659,0.000004287721,0.00002212944,0.00002433721,0.0000125807],"domain_scores_gemma":[0.9999017,0.0000315762,0.00001244178,0.00000698347,0.00004218256,0.000005161348],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005289655,0.0002672427,0.005962116,0.0001320212,0.0001033517,0.0001458734,0.00008385381,0.1599277,0.1677541,0.0007095842,0.001923704,0.6624615],"study_design_scores_gemma":[0.000003834509,0.00002661004,0.003510726,0.000003177268,0.00001233412,0.00001772966,0.000009041049,0.9858737,0.01026089,0.0001025336,0.0001735186,0.000005865918],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5448555,0.001005489,0.4491699,0.0001790664,0.0001091478,0.00007437574,0.0003078257,0.001070963,0.003227694],"genre_scores_gemma":[0.922559,0.0002627338,0.07387857,0.00004519902,0.00002091925,0.00004057828,0.0002043936,0.00001921303,0.002969371],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00779189,"threshold_uncertainty_score":0.01549304,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04883201929187114,"score_gpt":0.3170752791614687,"score_spread":0.2682432598695975,"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."}}