{"id":"W4310474075","doi":"10.1007/s12161-022-02425-w","title":"Fusion of Spectral and Textural Data of Hyperspectral Imaging for Glycine Content Prediction in Beef Using SFCN Algorithms","year":2022,"lang":"en","type":"article","venue":"Food Analytical Methods","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Hyperspectral imaging; Partial least squares regression; Variable elimination; Computer science; Pattern recognition (psychology); Residual; Support vector machine; Convolutional neural network; Algorithm; Matrix (chemical analysis); Artificial intelligence; Mathematics; Chemistry; Machine learning","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":[0.0008271817,0.000810063,0.0005571892,0.00155991,0.0003052753,0.0005245001,0.0004144544,0.000559163,0.0008465988],"category_scores_gemma":[0.0008269306,0.0002054405,0.0009429645,0.001183978,0.0002744267,0.0008653945,0.0005060146,0.0005695891,0.0003848633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002773342,"about_ca_system_score_gemma":0.0006035273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005894281,"about_ca_topic_score_gemma":0.007986106,"domain_scores_codex":[0.9997991,0.00002851933,0.00001194942,0.00006075994,0.00006575866,0.00003400409],"domain_scores_gemma":[0.9997267,0.00006808836,0.00004058745,0.0000250399,0.0001220415,0.00001746227],"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":[0.001174879,0.0005694031,0.0155439,0.0003108733,0.0003281251,0.0001710175,0.0001985894,0.2054259,0.1956559,0.001531499,0.002632583,0.5764573],"study_design_scores_gemma":[0.00001140266,0.00007245791,0.007178016,0.00001194169,0.00006631785,0.00004535408,0.00004483783,0.9710212,0.01981442,0.0008798597,0.0008302166,0.00002408879],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4570824,0.001012522,0.5369486,0.0002181439,0.00007971964,0.00007328704,0.0008684582,0.001383882,0.002332953],"genre_scores_gemma":[0.7977329,0.0005766244,0.1971186,0.00009016199,0.00004943061,0.00008481785,0.002060952,0.00009637445,0.002190228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005894281,"threshold_uncertainty_score":0.01171994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1841758129738462,"score_gpt":0.4188059021506189,"score_spread":0.2346300891767727,"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."}}