{"id":"W3172401710","doi":"10.1002/cpe.6297","title":"Ship‐iceberg discrimination from Sentinel‐1 synthetic aperture radar data using parallel convolutional neural network","year":2021,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"Synthetic Aperture Radar (SAR) Applications and Techniques","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Government of Newfoundland and Labrador; Memorial University of Newfoundland","funders":"Jiangxi Provincial Department of Science and Technology; Education Department of Jiangxi Province; National Natural Science Foundation of China","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Iceberg; Synthetic aperture radar; Constant false alarm rate; Pattern recognition (psychology); Support vector machine; Artificial neural network; Deep learning; Computer vision; Geology","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":[0.0001128798,0.000158465,0.000154765,0.00002326043,0.0002384279,0.0001255842,0.0001258594,0.00007718332,0.00003574071],"category_scores_gemma":[0.0001885767,0.0001593188,0.00001885489,0.0001571284,0.0001087993,0.0007681749,0.000110514,0.000159457,0.000002562492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001722554,"about_ca_system_score_gemma":0.00003550355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002961014,"about_ca_topic_score_gemma":0.000003730398,"domain_scores_codex":[0.9989758,0.00007499249,0.0002419731,0.0003807185,0.0001591726,0.0001673999],"domain_scores_gemma":[0.9988129,0.0006867096,0.0000795385,0.0002536488,0.00009463164,0.00007260063],"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":[0.00006712718,0.0002624569,0.001693057,0.000184186,0.0002055665,0.00007013942,0.009154454,0.002277468,0.003985218,0.03095845,0.004528838,0.9466131],"study_design_scores_gemma":[0.0002283576,0.000009640324,0.001083283,0.00007240644,0.00007979223,0.0001624968,0.001984162,0.885354,0.000149672,0.001593354,0.1090097,0.0002732103],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07714655,0.01237173,0.9079746,0.001062997,0.0003513803,0.0001522947,0.00004416643,0.0001741062,0.0007222099],"genre_scores_gemma":[0.8603049,0.001025102,0.1378192,0.0003447714,0.0001465364,0.00001515787,0.0003221133,0.00001425523,0.000008029232],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9463398,"threshold_uncertainty_score":0.6496834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04111409104507462,"score_gpt":0.3108569003007611,"score_spread":0.2697428092556864,"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."}}