{"id":"W4412908762","doi":"10.2166/hydro.2025.288","title":"Enhancing object detection in underwater aquatic system with YOLO-transformer hybrid model and IoT sensor integration","year":2025,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Underwater; Computer science; Transformer; Real-time computing; Environmental science; Artificial intelligence; Engineering; Geology; Electrical engineering; Oceanography","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":[0.0005522142,0.000113391,0.0001985644,0.0001979147,0.00006206039,0.00005166995,0.000118989,0.00005261401,0.00000141551],"category_scores_gemma":[0.00004012591,0.00007736974,0.00002950254,0.0001717225,0.00007154037,0.0004705632,0.00003179723,0.0002540316,0.000006570351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004397644,"about_ca_system_score_gemma":0.00002047146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008417541,"about_ca_topic_score_gemma":0.0002819815,"domain_scores_codex":[0.9989113,0.00002667076,0.0005898006,0.00006377454,0.0002486123,0.0001598961],"domain_scores_gemma":[0.9995821,0.00004245435,0.0002221189,0.0001152522,0.000009566076,0.00002853886],"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":[0.0004460204,0.0001616907,0.01260001,0.001119546,0.0001563743,0.00005618445,0.01788589,0.6935322,0.2425589,0.0003677035,0.00009149778,0.03102406],"study_design_scores_gemma":[0.0004599566,0.0001815237,0.001006538,0.0004711091,0.00003220161,0.0001931631,0.003705141,0.661119,0.3318578,0.0008478319,0.00001094926,0.0001147423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.873739,0.000009157913,0.1254452,0.000118517,0.00006459456,0.0001172308,5.702201e-7,0.00002793599,0.0004778045],"genre_scores_gemma":[0.9855908,0.00001160186,0.01431122,0.00002237575,0.000007503094,0.000002304836,3.116293e-7,0.000005329621,0.00004852129],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1118518,"threshold_uncertainty_score":0.3155046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01068792576573151,"score_gpt":0.2267084273229783,"score_spread":0.2160205015572468,"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."}}