{"id":"W2073296655","doi":"10.1016/j.jfca.2014.11.012","title":"Simplified tea classification based on a reduced chemical composition profile via successive projections algorithm linear discriminant analysis (SPA-LDA)","year":2015,"lang":"en","type":"article","venue":"Journal of Food Composition and Analysis","topic":"Tea Polyphenols and Effects","field":"Medicine","cited_by":66,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Comisión de Investigaciones Científicas; Composites Innovation Centre; Universidad Nacional del Sur; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Linear discriminant analysis; Mathematics; Chemical composition; Partial least squares regression; Fingerprint (computing); Black tea; Pattern recognition (psychology); Principal component analysis; Algorithm; Artificial intelligence; Statistics; Chemistry; Computer science; Food science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003881954,0.0005707067,0.0006384237,0.0007547803,0.0004183314,0.0006895172,0.0003822932,0.0003183967,0.001500526],"category_scores_gemma":[0.0005367548,0.0001999791,0.001094146,0.000726643,0.0002329257,0.0007286397,0.0006044616,0.0005626064,0.0009271159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001503941,"about_ca_system_score_gemma":0.0005436391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001778198,"about_ca_topic_score_gemma":0.002278549,"domain_scores_codex":[0.9997215,0.00004866281,0.00001730076,0.00007818785,0.00009508897,0.00003925979],"domain_scores_gemma":[0.9998463,0.00002744068,0.00001357529,0.00002412747,0.00007715078,0.0000113176],"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":[0.0007877403,0.0003121234,0.005355669,0.000273261,0.0002053693,0.0001942511,0.0001605807,0.04159627,0.2422639,0.002978565,0.00365505,0.7022172],"study_design_scores_gemma":[0.00002303224,0.0001234623,0.009010129,0.00001111979,0.0001082156,0.0001752292,0.00006655332,0.9564425,0.02921984,0.001649636,0.003119338,0.00005085686],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1697973,0.0004470691,0.8254933,0.0001717954,0.0001036156,0.00008173322,0.0003734447,0.001219396,0.00231229],"genre_scores_gemma":[0.6056551,0.0005825547,0.3860032,0.00007653758,0.00009369125,0.0001709672,0.001311917,0.0001971119,0.005908763],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001778198,"threshold_uncertainty_score":0.005019724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03528798284337333,"score_gpt":0.314153013572074,"score_spread":0.2788650307287007,"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."}}