{"id":"W4383503686","doi":"10.1109/joe.2023.3272393","title":"Classification of Herring, Salmon, and Bubbles in Multifrequency Echograms Using U-Net Neural Networks","year":2023,"lang":"en","type":"article","venue":"IEEE Journal of Oceanic Engineering","topic":"Underwater Acoustics Research","field":"Earth and Planetary Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Fisheries and Oceans Canada; ASL Environmental Sciences (Canada); University of Victoria","funders":"Western Canada Research Grid; Compute Canada","keywords":"Herring; Artificial neural network; Computer science; Context (archaeology); Convolutional neural network; Noise (video); Underwater; Artificial intelligence; Cartography; Geography; Geology; Oceanography; Fish <Actinopterygii>; Fishery; Biology; Archaeology; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005887904,0.00008674273,0.0001706823,0.0003425999,0.00002421415,0.00003641606,0.0001527306,0.00005698467,0.00001451047],"category_scores_gemma":[0.00005874367,0.00007662298,0.00003449283,0.0004254145,0.00002867194,0.000216629,0.000008085747,0.0002838481,0.000001045055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001430886,"about_ca_system_score_gemma":0.00002679457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001353261,"about_ca_topic_score_gemma":0.00005912129,"domain_scores_codex":[0.9990156,0.00003023869,0.0003759971,0.00009103473,0.0002395911,0.0002475759],"domain_scores_gemma":[0.9995196,0.000139027,0.0001170749,0.00007443944,0.00005841958,0.00009142581],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008432671,0.000004442609,0.1306015,0.00003730901,0.00001064718,0.00003740013,0.0000951356,0.8566635,0.01006955,9.297727e-7,0.000008855743,0.002462266],"study_design_scores_gemma":[0.0001573526,0.00004554485,0.229649,0.00006714848,0.000005941925,0.00005596304,0.00006332607,0.7696671,0.0002108303,0.00001681114,0.000006023433,0.00005492314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9761323,0.0004032441,0.02306858,0.00001853965,0.0002890259,0.00005423919,0.000003182459,0.00001402093,0.00001680443],"genre_scores_gemma":[0.997375,0.0002179508,0.002273102,0.000002650167,0.0001175542,7.373389e-8,0.000002635861,0.000006567614,0.000004508387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09904744,"threshold_uncertainty_score":0.3124594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03920318880741237,"score_gpt":0.2650535003897765,"score_spread":0.2258503115823641,"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."}}