{"id":"W3179017304","doi":"10.1109/access.2021.3096550","title":"Detection of Mulberry Ripeness Stages Using Deep Learning Models","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":141,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"European Commission","keywords":"Ripeness; Computer science; Artificial intelligence; Convolutional neural network; Residual neural network; Sorting; Deep learning; Transfer of learning; Pattern recognition (psychology); Ripening; Machine learning; Horticulture","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000824364,0.0000920438,0.0001450174,0.00000799099,0.0001629916,0.00008671649,0.0001798843,0.00007875921,0.0000958159],"category_scores_gemma":[0.00002005837,0.00003479871,0.00007532653,0.0004040794,0.00002051259,0.0004477971,0.0000640514,0.0001044126,0.000003257951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001329923,"about_ca_system_score_gemma":0.000005424259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004803,"about_ca_topic_score_gemma":0.00126851,"domain_scores_codex":[0.9992549,0.0000685557,0.0001547783,0.0002042598,0.0001552106,0.0001622652],"domain_scores_gemma":[0.9996027,0.00008158798,0.00009261483,0.00003619098,0.000144296,0.00004260279],"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":[0.000006918025,0.00003533717,0.007034651,0.000008658996,0.00001064351,0.000006285816,0.00005182535,0.005727032,0.9519613,0.00001638471,0.00001017471,0.03513075],"study_design_scores_gemma":[0.0001161549,0.00005075379,0.07534131,0.00003561746,0.00002754477,0.0000169451,0.000419317,0.005653013,0.9159766,0.0005767305,0.001573977,0.0002120169],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9981602,0.0002925054,0.000676608,0.00005849508,0.0002666996,0.00005474675,0.000003071388,0.00003748222,0.0004501989],"genre_scores_gemma":[0.9993775,0.00005275099,0.00004159283,0.0000593194,0.0002868216,0.000003734298,0.00001088597,7.687911e-7,0.0001666028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06830666,"threshold_uncertainty_score":0.141905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06621188665532554,"score_gpt":0.2680260978486114,"score_spread":0.2018142111932859,"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."}}