{"id":"W2517732947","doi":"10.1002/jsfa.8014","title":"Non‐destructive detection of dicyandiamide in infant formula powder using multi‐spectral imaging coupled with chemometrics","year":2016,"lang":"en","type":"article","venue":"Journal of the Science of Food and Agriculture","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China; Canadian Food Inspection Agency","keywords":"Chemometrics; Partial least squares regression; Infant formula; Support vector machine; Least squares support vector machine; Residual; Pattern recognition (psychology); Mathematics; Artificial intelligence; Artificial neural network; Chemistry; Biological system; Analytical Chemistry (journal); Chromatography; Computer science; Statistics; Food science; Algorithm; Biology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006377937,0.0004404215,0.0002830963,0.0005718005,0.0001600956,0.0003314897,0.0003949601,0.0005371281,0.0003901065],"category_scores_gemma":[0.0008489269,0.0002050241,0.00027955,0.0004355579,0.0002765542,0.0004078893,0.0003030997,0.0004098229,0.0001402082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003955733,"about_ca_system_score_gemma":0.0002576522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001168347,"about_ca_topic_score_gemma":0.00182553,"domain_scores_codex":[0.9995421,0.00006738028,0.00001668348,0.0001038951,0.0002474449,0.00002248076],"domain_scores_gemma":[0.9997036,0.00009708799,0.00007001787,0.00001979399,0.00009606135,0.00001335879],"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":[0.0001130996,0.00007017212,0.005288764,0.0001605466,0.00003105331,0.00005877971,0.00003857324,0.001571574,0.9568226,0.0001606271,0.0001552593,0.03552898],"study_design_scores_gemma":[0.000007074837,0.0001655092,0.01045811,0.000009714377,0.00003587831,0.0002273352,0.00003589748,0.07014455,0.9179062,0.0001197605,0.0008684764,0.00002143843],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8773311,0.002352713,0.116956,0.0002541582,0.00007907376,0.00005805067,0.000194691,0.000361558,0.00241254],"genre_scores_gemma":[0.8998137,0.0009315593,0.09793556,0.00008718181,0.0000162147,0.00003763228,0.00009095394,0.00001742097,0.001069686],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001168347,"threshold_uncertainty_score":0.003373027,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007602056305830203,"score_gpt":0.2330366494613982,"score_spread":0.225434593155568,"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."}}