{"id":"W4361028307","doi":"10.1016/j.postharvbio.2023.112334","title":"Near-infrared hyperspectral imaging combined with machine learning for physicochemical-based quality evaluation of durian pulp","year":2023,"lang":"en","type":"article","venue":"Postharvest Biology and Technology","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":51,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Hyperspectral imaging; Partial least squares regression; Mean squared error; Pulp (tooth); Mathematics; Near-infrared spectroscopy; Artificial intelligence; Correlation coefficient; Multispectral image; Support vector machine; Coefficient of determination; Pattern recognition (psychology); Computer science; Statistics; Optics; Physics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003930629,0.0001700662,0.0003755074,0.0002516196,0.0001603407,0.00001291788,0.0001646731,0.0002328582,0.00009907004],"category_scores_gemma":[0.0006080546,0.0001470124,0.00005673888,0.0008546344,0.0005550307,0.00004384089,0.00004737652,0.0002590317,0.000003317969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004117648,"about_ca_system_score_gemma":0.00008948662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005378188,"about_ca_topic_score_gemma":0.00002876676,"domain_scores_codex":[0.9989003,0.00004103125,0.0002452569,0.0003706046,0.00009942536,0.0003433973],"domain_scores_gemma":[0.999078,0.0002291762,0.0002006131,0.0002404689,0.0002106419,0.00004114349],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002387537,0.00008336811,0.4173011,0.00008534436,0.0001190383,0.000001288104,0.0000309009,0.00002583331,0.5778143,0.002973299,0.00001472602,0.001311962],"study_design_scores_gemma":[0.003231794,0.0002859882,0.01499689,0.00001995679,0.0003249924,0.000009676004,0.0003919876,0.01782391,0.9528697,0.009615121,0.0001653855,0.0002646554],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99689,0.0005264515,0.0001905885,0.001362557,0.00001554643,0.0001290027,0.00004919119,0.0003095928,0.0005270355],"genre_scores_gemma":[0.9987116,0.00001912451,0.0005228957,0.00002794428,0.00002081614,0.00008338023,0.0004596605,0.00001782347,0.0001367776],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4023042,"threshold_uncertainty_score":0.5994992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02306622392825224,"score_gpt":0.3240267257818474,"score_spread":0.3009605018535952,"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."}}