{"id":"W3213652225","doi":"10.15587/1729-4061.2021.243094","title":"Improvement of the model of object recognition in aero photographs using deep convolutional neural networks","year":2021,"lang":"en","type":"article","venue":"Eastern-European Journal of Enterprise Technologies","topic":"Advanced Computational Techniques in Science and Engineering","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Convolutional neural network; Object (grammar); Set (abstract data type); Cognitive neuroscience of visual object recognition; Test set; Pattern recognition (psychology); Computer vision; Aerial image; Object detection; Sensitivity (control systems); Image (mathematics); Class (philosophy); Artificial neural network; Deep learning; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003978329,0.0001081931,0.0001884394,0.0002303883,0.00003323597,0.00002314123,0.0009592375,0.00002934052,7.818228e-7],"category_scores_gemma":[0.0001055505,0.00008397012,0.0001331125,0.0005869971,0.0001364406,0.000361371,0.0005213084,0.0002622732,1.342301e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000444066,"about_ca_system_score_gemma":0.0000432764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001073529,"about_ca_topic_score_gemma":8.815799e-7,"domain_scores_codex":[0.9987371,0.00006031449,0.0005860518,0.0001535129,0.0002997982,0.0001632243],"domain_scores_gemma":[0.9989179,0.00004590801,0.0004929722,0.0002765043,0.000248478,0.00001828651],"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":[0.00001290697,0.00005605215,0.001390411,0.0000138793,0.00001494753,0.00003251837,0.0001689922,0.8928885,0.0353433,0.000277001,0.000002084104,0.06979942],"study_design_scores_gemma":[0.0002316285,0.0001098097,0.000463972,0.0002495413,0.000005958869,0.0000797282,0.0002190148,0.9621773,0.03146484,0.004914975,0.000001907053,0.00008127491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3483176,0.0002618514,0.6510802,0.00004460204,0.0001582787,0.00004415858,0.000001008024,0.000034527,0.00005778608],"genre_scores_gemma":[0.8875504,0.00006172054,0.1123397,0.00002865956,0.00001021146,9.46956e-7,2.563737e-7,0.000006104953,0.000001958399],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5392328,"threshold_uncertainty_score":0.3424202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0262486175809996,"score_gpt":0.2431298466269491,"score_spread":0.2168812290459495,"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."}}