{"id":"W4393156220","doi":"10.1177/14759217241235637","title":"Advanced deep learning framework for underwater object detection with multibeam forward-looking sonar","year":2024,"lang":"en","type":"article","venue":"Structural Health Monitoring","topic":"Underwater Acoustics Research","field":"Earth and Planetary Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Colleges and Universities","keywords":"Sonar; Computer science; Underwater; Object detection; Artificial intelligence; Preprocessor; Convolutional neural network; Deep learning; Computer vision; Key (lock); Feature (linguistics); Pattern recognition (psychology); Computer security","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003402981,0.0002304617,0.0002293387,0.0001899183,0.0008614732,0.0003009278,0.0001672127,0.000109192,0.0000723435],"category_scores_gemma":[0.00003949481,0.0001706267,0.00006496719,0.0003209613,0.00005570368,0.0004073187,0.00001837517,0.0007214135,0.00002579558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001162241,"about_ca_system_score_gemma":0.0001236512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009823871,"about_ca_topic_score_gemma":0.000853623,"domain_scores_codex":[0.997775,0.0000848288,0.0002767745,0.0004978061,0.0004467413,0.0009188672],"domain_scores_gemma":[0.9989862,0.0004915346,0.00006546387,0.0001390635,0.00007144344,0.000246294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000148097,0.000001218527,0.02777661,0.0005534902,0.00003688669,0.00001239806,0.001229135,0.1280526,0.0004214283,0.000008451629,8.968727e-7,0.8417587],"study_design_scores_gemma":[0.0007348047,0.001925868,0.0832146,0.001007144,0.00002854381,0.0001118806,0.002700937,0.8849548,0.01249788,0.009690469,0.002413746,0.000719326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5895395,0.002090705,0.4050921,0.0001645569,0.001930505,0.0007401237,0.00002096432,0.0003572688,0.00006432199],"genre_scores_gemma":[0.9090852,0.0001032227,0.08974636,0.00001945551,0.0008711976,0.00001302131,0.00003146108,0.00002504001,0.0001050786],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8410394,"threshold_uncertainty_score":0.6957955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02159336322916778,"score_gpt":0.3204191138567183,"score_spread":0.2988257506275505,"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."}}