{"id":"W4388808912","doi":"10.1016/j.jfca.2023.105840","title":"Portable hyperspectral imaging coupled with multivariate analysis for real-time prediction of plant-based meat analogues quality","year":2023,"lang":"en","type":"article","venue":"Journal of Food Composition and Analysis","topic":"Meat and Animal Product Quality","field":"Agricultural and Biological Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"VNIR; Hyperspectral imaging; Partial least squares regression; Chemometrics; Principal component analysis; Multivariate statistics; Environmental science; Mathematics; Chemistry; Food science; Artificial intelligence; Statistics; Computer science; Chromatography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009443366,0.0001143024,0.0005658475,0.0002088631,0.0001587369,0.00004859434,0.00009276407,0.0000373583,0.00005371066],"category_scores_gemma":[0.0000235634,0.00004833584,0.0004416571,0.001887413,0.00004725493,0.0001402656,0.0000102704,0.00006728923,4.48083e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001526534,"about_ca_system_score_gemma":0.00001161106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002770049,"about_ca_topic_score_gemma":0.000164265,"domain_scores_codex":[0.998666,0.0001431322,0.0005393934,0.0001967004,0.0002983775,0.0001563243],"domain_scores_gemma":[0.998758,0.0002118971,0.0005614098,0.00005282578,0.0003195564,0.00009635885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000644636,0.0001677428,0.1183465,0.00002340195,0.003064016,0.000003816948,0.00008664084,0.002392542,0.8747051,0.000137849,0.00004807065,0.0003796792],"study_design_scores_gemma":[0.000640596,0.0008637823,0.8972312,0.0000275553,0.00485631,0.000004284128,0.0004810628,0.08292664,0.01266197,0.0001398446,0.00001758488,0.000149186],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974335,0.00005114716,0.001092507,0.0007141862,0.00001407911,0.00007882728,0.0005640402,0.00002657721,0.00002517307],"genre_scores_gemma":[0.9984289,0.00003823661,0.0006428004,0.00002677456,0.00008510557,0.000001893374,0.0007565367,9.317105e-7,0.00001880003],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8620431,"threshold_uncertainty_score":0.1971079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03918008626548713,"score_gpt":0.2689600659983292,"score_spread":0.229779979732842,"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."}}