{"id":"W4293298660","doi":"10.21203/rs.3.rs-1925394/v1","title":"Fusion of spectral and textural data of hyperspectral imaging for glycine content prediction in beef using SFCN algorithms","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Hyperspectral imaging; Partial least squares regression; Variable elimination; Computer science; Residual; Convolutional neural network; Support vector machine; Pattern recognition (psychology); Algorithm; Artificial intelligence; Matrix (chemical analysis); 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":[0.0008423091,0.001044659,0.0005155511,0.0009184889,0.0002625298,0.0004176397,0.0005928221,0.0006183199,0.000764591],"category_scores_gemma":[0.001146087,0.0003211238,0.0009213203,0.0006080739,0.0003305401,0.0007951531,0.0005146529,0.0005916215,0.000193534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005219173,"about_ca_system_score_gemma":0.0007838353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01162229,"about_ca_topic_score_gemma":0.008584637,"domain_scores_codex":[0.9997643,0.00003854662,0.00001499487,0.0000734191,0.0000688229,0.00004004855],"domain_scores_gemma":[0.9997354,0.00007407059,0.00004202651,0.00002392939,0.0001093242,0.00001522715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003153795,0.0001876367,0.007266559,0.00009785583,0.0001542548,0.0001187321,0.00009886138,0.6648733,0.04751372,0.001306883,0.001033346,0.2770335],"study_design_scores_gemma":[0.00000201046,0.00001208201,0.0007184843,0.000002235704,0.000008435608,0.000007475239,0.000005688304,0.9965599,0.002420894,0.0001903569,0.00006835981,0.000004056318],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2494483,0.0004050273,0.7473827,0.0001459897,0.00004489531,0.00005592013,0.0001455385,0.001073634,0.001297901],"genre_scores_gemma":[0.8639858,0.0002352277,0.1332226,0.00007042706,0.00002540149,0.00007182447,0.0004149795,0.0000605208,0.001913154],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01162229,"threshold_uncertainty_score":0.02310926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2324702868301527,"score_gpt":0.4477147808682758,"score_spread":0.2152444940381231,"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."}}