{"id":"W4396691627","doi":"10.3390/computers13050116","title":"A Hybrid Deep Learning Architecture for Apple Foliar Disease Detection","year":2024,"lang":"en","type":"article","venue":"Computers","topic":"Plant Pathogens and Fungal Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Deep learning; Plant disease; Computer science; Context (archaeology); Convolutional neural network; Plant identification; Machine learning; Identification (biology); Biology; Biotechnology; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003755765,0.00009558013,0.00006089477,0.0000351622,0.00007482425,0.00004861135,0.00007361448,0.00002766605,0.000002693315],"category_scores_gemma":[0.00003586915,0.00008911984,0.0001265313,0.00003235859,0.00001733537,0.000001907061,0.00004142326,0.00005427572,0.000008247843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006591378,"about_ca_system_score_gemma":0.00002162245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001027002,"about_ca_topic_score_gemma":0.000002192852,"domain_scores_codex":[0.9994533,0.00001917219,0.00006738719,0.0002621438,0.00004815182,0.000149829],"domain_scores_gemma":[0.9997397,0.00002600186,0.00001256924,0.000100662,0.00001562848,0.0001054283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003298401,0.00005040833,0.000269263,0.0003348764,0.000146793,0.00008484229,0.00005555044,0.01109952,0.6926402,0.0002272636,0.006370707,0.2883907],"study_design_scores_gemma":[0.0004650976,0.0003893862,0.001692134,0.00009057667,0.0001229997,0.0000648058,0.00001797373,0.1467898,0.02502196,0.0008969491,0.8239755,0.0004727551],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1432719,0.003277386,0.8523724,0.00005495331,0.0004203592,0.0001868449,0.0002988821,0.00006721199,0.00005005486],"genre_scores_gemma":[0.9975598,0.00006798896,0.001016664,0.0001413723,0.000470817,0.00004310938,0.0005206179,0.00001987506,0.0001597039],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.854288,"threshold_uncertainty_score":0.3634202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005420688139665262,"score_gpt":0.2136885310144599,"score_spread":0.2082678428747946,"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."}}