{"id":"W2403069542","doi":"10.1016/j.biosystemseng.2016.04.001","title":"Performance evaluation of a model for the classification of contaminants from wheat using near-infrared hyperspectral imaging","year":2016,"lang":"en","type":"article","venue":"Biosystems Engineering","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Hyperspectral imaging; VNIR; Contamination; Canola; Environmental science; Identification (biology); Classifier (UML); Spectral signature; Artificial intelligence; Agronomy; Remote sensing; Computer science; Biology; Botany; Ecology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002530171,0.001273761,0.0009639803,0.0006440028,0.000559412,0.001388651,0.001054244,0.001802745,0.001156699],"category_scores_gemma":[0.002891473,0.0002914762,0.0007918993,0.0003995996,0.0003211413,0.0008383233,0.0006586396,0.00104027,0.0005555062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001442689,"about_ca_system_score_gemma":0.001638591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0343061,"about_ca_topic_score_gemma":0.01505975,"domain_scores_codex":[0.9995015,0.0001722909,0.00003825151,0.0001390651,0.00006912404,0.00007982181],"domain_scores_gemma":[0.9980521,0.001210692,0.00008404472,0.00007959046,0.0004858662,0.00008775966],"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":[0.001634293,0.0007321103,0.01009955,0.0001456058,0.0004348281,0.00009864613,0.00007461732,0.837009,0.0115577,0.000440186,0.001963571,0.1358099],"study_design_scores_gemma":[0.00000938196,0.00007878804,0.00057069,0.000003124954,0.00001806467,0.000007212281,0.00001050672,0.9976913,0.001462287,0.00007989548,0.00006440582,0.00000431386],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8074745,0.00149383,0.1835593,0.000891084,0.0002079266,0.0001470101,0.0008336949,0.002954162,0.002438437],"genre_scores_gemma":[0.9726132,0.0001840824,0.02448379,0.0001378741,0.00002613791,0.00007150285,0.0009546069,0.00005080524,0.001478032],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0343061,"threshold_uncertainty_score":0.06821287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05573403160731253,"score_gpt":0.2873335790014156,"score_spread":0.2315995473941031,"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."}}