{"id":"W4308645678","doi":"10.1002/cjce.24759","title":"Dynamic global feature extraction and importance‐correlation selection for the prediction of concentrate copper grade and recovery rate","year":2022,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Principal component analysis; Feature selection; Kernel principal component analysis; Redundancy (engineering); Computer science; Pattern recognition (psychology); Data mining; Support vector machine; Feature extraction; Artificial intelligence; Kernel (algebra); Scale (ratio); Mathematics; Kernel method","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002202868,0.00006723306,0.00008568745,0.00003522401,0.0001236079,0.00002873188,0.00004996702,0.00003809547,0.000003489358],"category_scores_gemma":[0.00004533673,0.00005107646,0.0000280829,0.0001181109,0.00002060592,0.000103709,0.00000394924,0.0002727318,2.094863e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002362172,"about_ca_system_score_gemma":0.00005369821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000743194,"about_ca_topic_score_gemma":0.00009502633,"domain_scores_codex":[0.9996121,0.000008147304,0.0001491063,0.00004761191,0.00006599349,0.0001170213],"domain_scores_gemma":[0.9997317,0.0000689569,0.00006671589,0.00003268878,0.00002944753,0.00007051109],"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":[0.00002233777,0.000001580727,0.001466685,0.00006115552,0.00005882752,0.000001174659,0.0001647689,0.9089966,0.08680394,0.00009459974,0.0006247024,0.001703606],"study_design_scores_gemma":[0.0002722428,0.0000363413,0.002522757,0.00003826972,0.00006046598,0.0003220748,0.00005428286,0.9927201,0.002988326,0.0002216561,0.000696751,0.000066687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9922085,0.00220778,0.004642636,0.0003563195,0.0004372714,0.00008709481,0.00003341755,0.00001334214,0.00001362136],"genre_scores_gemma":[0.9996176,0.00002775717,0.0002422597,0.00001226753,0.0000701431,0.000004775862,0.000004637826,0.000009570749,0.00001098697],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08381561,"threshold_uncertainty_score":0.2082838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00577929870633069,"score_gpt":0.1923284341834626,"score_spread":0.1865491354771319,"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."}}