{"id":"W4386401253","doi":"10.1016/j.eswa.2023.121395","title":"A lightweight open-world pest image classifier using ResNet8-based matching network and NT-Xent loss function","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ministry of Agriculture","funders":"","keywords":"PEST analysis; Computer science; Artificial intelligence; Convolutional neural network; Python (programming language); Classifier (UML); Pattern recognition (psychology); Artificial neural network; Machine learning; Computer vision; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002171474,0.0001852341,0.0002157707,0.00002313199,0.0008070737,0.0003869595,0.0002526798,0.00007428811,0.00004439754],"category_scores_gemma":[0.000002602469,0.00006658475,0.00004031451,0.001140787,0.00005418576,0.0001994515,0.00009861337,0.0001088787,0.00008233694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003816013,"about_ca_system_score_gemma":0.00001493776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009495402,"about_ca_topic_score_gemma":0.001259944,"domain_scores_codex":[0.9987066,0.00007039933,0.0002488437,0.0004426831,0.0002047727,0.0003267028],"domain_scores_gemma":[0.9993796,0.0001412004,0.0001327824,0.0001272147,0.00008097626,0.0001382412],"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":[0.0004214248,0.0007057035,0.04738202,0.0001913398,0.0002980501,0.00006024417,0.001173158,0.004023561,0.5289531,0.03400079,0.36832,0.01447067],"study_design_scores_gemma":[0.0003501748,0.0001207595,0.04399594,0.0002100597,0.00003420748,0.00002713168,0.001100731,0.002237214,0.0003742117,0.0003253264,0.9507617,0.0004624896],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9484378,0.00311451,0.01057097,0.01532516,0.001074505,0.007790182,0.0001364982,0.001421337,0.01212902],"genre_scores_gemma":[0.992507,0.00003155173,0.0008460575,0.0004790056,0.002105181,0.001445942,0.000281556,0.000005331673,0.002298317],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5824417,"threshold_uncertainty_score":0.620744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03010625107620761,"score_gpt":0.2551320172045343,"score_spread":0.2250257661283266,"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."}}