{"id":"W4205761787","doi":"10.3389/fmars.2021.823173","title":"Automated Detection, Classification and Counting of Fish in Fish Passages With Deep Learning","year":2022,"lang":"en","type":"article","venue":"Frontiers in Marine Science","topic":"Fish Ecology and Management Studies","field":"Environmental Science","cited_by":122,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Research Chairs","keywords":"Convolutional neural network; Sonar; Computer science; Artificial intelligence; Adaptation (eye); Fish <Actinopterygii>; Citizen science; Fishery; Biology","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":[0.0008539387,0.00005826005,0.00009580638,0.0001497442,0.000358388,0.00001264851,0.0001794404,0.00001312596,0.00009062546],"category_scores_gemma":[0.0001012436,0.00005845743,0.000005391279,0.001015137,0.0006315821,0.0002469653,0.0006706062,0.0001450718,5.670349e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001861946,"about_ca_system_score_gemma":0.00000745873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001321835,"about_ca_topic_score_gemma":0.002596981,"domain_scores_codex":[0.9991388,0.00005261761,0.0001328488,0.0002636431,0.0002253882,0.0001867052],"domain_scores_gemma":[0.999783,0.00002177522,0.00009153349,0.00008061078,0.000006670194,0.00001637255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001317579,0.00002340146,0.9847847,0.000005673246,0.000001905521,0.000002602911,0.000331653,0.005576349,0.000231769,0.000007675937,0.001217608,0.007803468],"study_design_scores_gemma":[0.0002028547,0.0000669908,0.9428742,0.000002482857,0.000002831571,0.000001530011,0.002494816,0.0531804,0.00006876139,0.0001054277,0.0009343619,0.00006534888],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939798,0.000001367689,0.0004091433,0.000505078,0.0001141303,0.0001388055,4.52169e-7,0.00003828697,0.004812984],"genre_scores_gemma":[0.9962783,0.00001927209,0.003266394,0.0001905788,0.000001987794,0.00004176744,0.000001340409,0.000003092024,0.0001973036],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04760405,"threshold_uncertainty_score":0.2756467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004535035949910538,"score_gpt":0.1929162966942858,"score_spread":0.1883812607443753,"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."}}