{"id":"W3200138571","doi":"10.1080/03610470.2021.1958602","title":"Barley Variety Identification by iPhone Images and Deep Learning","year":2021,"lang":"en","type":"article","venue":"Journal of the American Society of Brewing Chemists","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Malting (Canada)","funders":"","keywords":"Artificial intelligence; Convolutional neural network; Hordeum vulgare; Deep learning; Transfer of learning; Computer science; Machine learning; Artificial neural network; Identification (biology); Visual inspection; Pattern recognition (psychology); Agronomy; Poaceae; Botany; Biology","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":[0.0002285108,0.0005751709,0.0002319227,0.00115915,0.000168083,0.0004388836,0.0003734267,0.0004544675,0.002309775],"category_scores_gemma":[0.0005601558,0.0001580712,0.0003111713,0.0006653348,0.0001615221,0.0005814044,0.0003927658,0.0003626126,0.00148608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003812585,"about_ca_system_score_gemma":0.0002480089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0072507,"about_ca_topic_score_gemma":0.00954972,"domain_scores_codex":[0.9998369,0.0000154133,0.000006733253,0.00006306138,0.00004656733,0.00003132175],"domain_scores_gemma":[0.9998722,0.0000275323,0.00001769176,0.00002626967,0.00004472903,0.00001165994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008483547,0.000312723,0.0094747,0.0001384126,0.00008899822,0.0004488718,0.00008021003,0.02814659,0.1495625,0.001173746,0.01170105,0.7980238],"study_design_scores_gemma":[0.0000225642,0.0001418907,0.01888124,0.0000184346,0.00003466206,0.0002321058,0.00009367786,0.9089456,0.06406099,0.001321035,0.006211165,0.00003675208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.627466,0.0009328173,0.3460206,0.0002865978,0.0003372492,0.0001717119,0.003230791,0.009843593,0.01171068],"genre_scores_gemma":[0.850956,0.0003103826,0.1350519,0.0001456787,0.00004299884,0.00007390468,0.004507833,0.0001869256,0.008724414],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0072507,"threshold_uncertainty_score":0.01441699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005278805909224921,"score_gpt":0.2006122106765865,"score_spread":0.1953334047673616,"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."}}