{"id":"W3197583449","doi":"10.1016/j.aca.2021.339001","title":"Advanced data fusion: Random forest proximities and pseudo-sample principle towards increased prediction accuracy and variable interpretation","year":2021,"lang":"en","type":"article","venue":"Analytica Chimica Acta","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Random forest; Principal component analysis; Sensor fusion; Data mining; Data set; Fusion; Sample (material); Pattern recognition (psychology); Artificial intelligence; Computer science; Chemistry","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":[0.006836605,0.001445306,0.001808008,0.002216028,0.0007369049,0.00231212,0.001909518,0.001463862,0.001787624],"category_scores_gemma":[0.0107237,0.0006008893,0.002238328,0.002296543,0.0009544157,0.003822876,0.002517591,0.002367857,0.001303595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004229627,"about_ca_system_score_gemma":0.001314317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001193058,"about_ca_topic_score_gemma":0.001330315,"domain_scores_codex":[0.9964276,0.001047024,0.0002343581,0.0008146238,0.0012921,0.0001842345],"domain_scores_gemma":[0.9961153,0.001245168,0.0002515056,0.0008865374,0.001385853,0.0001155286],"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":[0.0009542534,0.0005636794,0.004038131,0.0003667441,0.0004664345,0.0001399897,0.0002994082,0.09302867,0.04602152,0.01881791,0.003790214,0.831513],"study_design_scores_gemma":[0.00002758726,0.0001344004,0.001343195,0.00002300344,0.0001015078,0.0001119364,0.00003162169,0.9619551,0.01767967,0.01643231,0.002109737,0.00004991594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01220969,0.0002086562,0.9857842,0.0001258895,0.00006285655,0.000041882,0.000126443,0.001007878,0.0004324699],"genre_scores_gemma":[0.229836,0.0002872419,0.7673593,0.0001531575,0.0001395665,0.0001345599,0.0008284069,0.0003009679,0.0009608612],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006836605,"threshold_uncertainty_score":0.03615588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01880636204416096,"score_gpt":0.2853355387915155,"score_spread":0.2665291767473545,"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."}}