{"id":"W4319978501","doi":"10.1109/ifeea57288.2022.10038226","title":"Underwater fish detection in sonar image based on an improved Faster RCNN","year":2022,"lang":"en","type":"article","venue":"2022 9th International Forum on Electrical Engineering and Automation (IFEEA)","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Chinese Arctic and Antarctic Administration; Ministry of Natural Resources","keywords":"Artificial intelligence; Convolutional neural network; Computer science; Feature extraction; Intersection (aeronautics); Underwater; Pattern recognition (psychology); Object detection; Feature (linguistics); Pyramid (geometry); Computer vision; Sonar; Engineering; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005513229,0.0008754285,0.0007007779,0.001056642,0.0003417346,0.0006010967,0.001319663,0.000711308,0.00184742],"category_scores_gemma":[0.001031019,0.0004030364,0.000654579,0.0009359154,0.0003269135,0.001237447,0.0007359662,0.0006118194,0.0007555287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008405037,"about_ca_system_score_gemma":0.001088765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02100583,"about_ca_topic_score_gemma":0.02307675,"domain_scores_codex":[0.9995232,0.00002638097,0.00002121651,0.0001639326,0.0001736209,0.00009174151],"domain_scores_gemma":[0.9995634,0.00006780413,0.00005029131,0.00006570655,0.0002283386,0.00002453238],"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":[0.0003381605,0.000125185,0.004758019,0.000144237,0.0001522659,0.0002458174,0.00009115566,0.1400254,0.1048286,0.002578535,0.004357458,0.7423552],"study_design_scores_gemma":[0.00001451508,0.00009374255,0.002603662,0.00001115392,0.00006121016,0.0001644544,0.00001756197,0.9704137,0.02382505,0.0006124248,0.002157235,0.00002524247],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09683283,0.001080645,0.8907427,0.0002460156,0.0001705542,0.00008628804,0.0002615712,0.005094395,0.005485053],"genre_scores_gemma":[0.6163063,0.0008162796,0.3701215,0.0003531749,0.00008792377,0.0001047213,0.000868761,0.0002523606,0.01108894],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02100583,"threshold_uncertainty_score":0.04176712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00729957020388391,"score_gpt":0.2211178585439608,"score_spread":0.2138182883400769,"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."}}