{"id":"W4412980735","doi":"10.1016/j.aquaeng.2025.102604","title":"LightHybridNet-Transformer-FFIA: A hybrid Transformer based deep learning model for enhanced fish feeding intensity classification","year":2025,"lang":"en","type":"article","venue":"Aquacultural Engineering","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"China Agricultural University","keywords":"Transformer; Fishery; Environmental science; Engineering; Artificial intelligence; Computer science; Biology; Electrical engineering; Voltage","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":[0.0002100809,0.0002661414,0.0002552415,0.00008447755,0.0002134912,0.00007071959,0.0003184698,0.0001124302,0.00001318908],"category_scores_gemma":[0.0001691016,0.0002385729,0.0001399137,0.0002735912,0.00006652992,0.0004097939,0.0000322598,0.0003326412,0.00001678431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000372373,"about_ca_system_score_gemma":0.000008996751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005066546,"about_ca_topic_score_gemma":0.0000190777,"domain_scores_codex":[0.9985706,0.00000982504,0.0003209076,0.0004255844,0.000202343,0.0004707795],"domain_scores_gemma":[0.9995925,0.00006930269,0.0000528274,0.0001897152,0.00003145616,0.00006415269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003457831,0.00002073078,0.0002997189,0.00007550469,0.00002479681,7.371708e-7,0.000417345,0.2841069,0.7081912,0.0001410309,0.0002839436,0.006403538],"study_design_scores_gemma":[0.0002858719,0.00002729853,0.001185252,0.00005530096,0.0000242402,9.729251e-7,0.0001213313,0.5803741,0.4161225,0.00009810714,0.001490121,0.0002149331],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4690368,0.00001264071,0.5284413,0.001150257,0.0001707241,0.0003341751,0.000006942818,0.0005617935,0.0002853935],"genre_scores_gemma":[0.980424,0.00001601296,0.01875866,0.0000892939,0.00003393927,0.0001550584,0.00004821643,0.00002318389,0.0004515981],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5113872,"threshold_uncertainty_score":0.972872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01838088248289994,"score_gpt":0.2396101079760177,"score_spread":0.2212292254931178,"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."}}