{"id":"W4399365488","doi":"10.3390/ani14111690","title":"Augmenting Aquaculture Efficiency through Involutional Neural Networks and Self-Attention for Oplegnathus Punctatus Feeding Intensity Classification from Log Mel Spectrograms","year":2024,"lang":"en","type":"article","venue":"Animals","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Spectrogram; Artificial intelligence; Computer science; Filter (signal processing); Deep learning; Pattern recognition (psychology); Feature extraction; Feature (linguistics); Artificial neural network; Gabor filter; Computer vision","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":[0.000315789,0.000171111,0.0001558334,0.00002787285,0.0002539165,0.0002200221,0.0001873326,0.0001495085,0.00001711329],"category_scores_gemma":[0.00006204751,0.0001455808,0.00007467957,0.0002378479,0.0001541727,0.0003975156,0.0002404003,0.0002125948,0.00002128053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002345702,"about_ca_system_score_gemma":0.000004467297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003719311,"about_ca_topic_score_gemma":0.00003083008,"domain_scores_codex":[0.9986185,0.0000302403,0.0002439728,0.0005324077,0.0002253746,0.0003495403],"domain_scores_gemma":[0.9996112,0.0001016836,0.00007710385,0.0001526879,0.00001835499,0.00003899078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001428735,0.000472731,0.3203377,0.0001729185,0.000273331,0.00003445266,0.005406829,0.001375441,0.6094555,0.02153529,0.008467184,0.03232577],"study_design_scores_gemma":[0.0004345503,0.0003169675,0.5857272,0.0001304691,0.0001655482,0.0000259431,0.002085057,0.3793926,0.00744742,0.01997955,0.003714863,0.0005798542],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9810016,0.001046877,0.0151814,0.001142537,0.0004978025,0.0003321349,0.00001507589,0.0006650843,0.000117457],"genre_scores_gemma":[0.9889531,0.00007946586,0.01057811,0.00003782695,0.0002108433,0.00004201734,0.0000462276,0.00001571245,0.0000367112],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.602008,"threshold_uncertainty_score":0.5936611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03870492867221371,"score_gpt":0.2758913390658319,"score_spread":0.2371864103936182,"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."}}