{"id":"W2996981924","doi":"10.1109/access.2019.2962513","title":"Improved Kiwifruit Detection Using Pre-Trained VGG16 With RGB and NIR Information Fusion","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":192,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Beijing Technology and Business University; Dalhousie University; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"RGB color model; Artificial intelligence; Computer science; Convolutional neural network; Computer vision; Feature (linguistics); Pattern recognition (psychology); Deep learning; Channel (broadcasting); Object detection; Image fusion; Image (mathematics); Telecommunications","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":[0.000357811,0.001449399,0.0005323589,0.001261418,0.0002530615,0.0006361727,0.001141567,0.0006717537,0.002146441],"category_scores_gemma":[0.000548,0.0003032821,0.0007662786,0.00076618,0.0002262395,0.0008403378,0.0006480035,0.000578353,0.001407295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006751122,"about_ca_system_score_gemma":0.0006306286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01669708,"about_ca_topic_score_gemma":0.0207103,"domain_scores_codex":[0.9998086,0.000009929587,0.000006988136,0.000070339,0.00005634686,0.0000477818],"domain_scores_gemma":[0.9998848,0.0000149451,0.00001377677,0.00002269043,0.00005478179,0.00000881735],"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":[0.000468863,0.0002366471,0.006635914,0.0001951595,0.0002736988,0.0003731659,0.0001634647,0.09394623,0.1488927,0.001484261,0.008884353,0.7384456],"study_design_scores_gemma":[0.00002659903,0.0001624558,0.01237105,0.00004047638,0.0001159634,0.0003050498,0.00006323156,0.8919412,0.08516687,0.00112253,0.008631408,0.00005320464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.366636,0.002511447,0.5902153,0.0003712795,0.0004235417,0.0002376384,0.001847822,0.0235105,0.01424651],"genre_scores_gemma":[0.7308092,0.0005529164,0.2488212,0.000269245,0.00003891063,0.0001068929,0.003877306,0.0005251644,0.01499927],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01669708,"threshold_uncertainty_score":0.03319979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01078365766942732,"score_gpt":0.2182792561671489,"score_spread":0.2074955984977215,"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."}}