{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006444209,0.00108966,0.001357098,0.001466129,0.000551729,0.0008127294,0.002895632,0.00135172,0.007796352],"category_scores_gemma":[0.001164867,0.0004949563,0.0007974367,0.0009474782,0.0002513959,0.001924383,0.001337159,0.001041015,0.00517073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008630398,"about_ca_system_score_gemma":0.001159578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01179126,"about_ca_topic_score_gemma":0.01577581,"domain_scores_codex":[0.9994655,0.00002903408,0.00002593681,0.0001494953,0.000237839,0.00009216871],"domain_scores_gemma":[0.9995648,0.00004661307,0.00003749762,0.00007769013,0.0002384914,0.00003487684],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005261239,0.0004887001,0.001957565,0.0001676258,0.0001860388,0.0002019563,0.00003037192,0.03815688,0.03108171,0.001982542,0.02132618,0.9038942],"study_design_scores_gemma":[0.00003391828,0.0001193253,0.001174727,0.00001364373,0.00005197587,0.0001639678,0.00001686436,0.9747077,0.01777894,0.001435549,0.004481733,0.00002165408],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04780287,0.0007991414,0.9172432,0.0003303777,0.0003753285,0.000385744,0.001641011,0.02592599,0.005496283],"genre_scores_gemma":[0.4689153,0.0006779133,0.4950449,0.0005787304,0.0002899148,0.0005589403,0.008141818,0.0006489919,0.0251435],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01179126,"threshold_uncertainty_score":0.02608138,"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."}}