{"id":"W4280506572","doi":"10.1177/09544097221093486","title":"Use of deep convolutional neural networks and change detection technology for railway track inspections","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Institution of Mechanical Engineers Part F Journal of Rail and Rapid Transit","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Pavemetrics Systems (Canada)","funders":"Federal Railroad Administration","keywords":"Change detection; Computer science; Fastener; Convolutional neural network; Field (mathematics); Software deployment; Process (computing); Track (disk drive); Artificial intelligence; Artificial neural network; Machine vision; Machine learning; Engineering; Software engineering","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":[0.000225951,0.0001043321,0.0002528656,0.000194299,0.0001213233,0.000006121369,0.0001036239,0.00008450187,0.000003653095],"category_scores_gemma":[0.0000540236,0.00008339722,0.0001139849,0.0002764336,0.000125376,0.0002322418,0.00002308078,0.0003149163,6.5703e-9],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003646671,"about_ca_system_score_gemma":0.00001006649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002300763,"about_ca_topic_score_gemma":0.000001530974,"domain_scores_codex":[0.9992357,0.000004339649,0.0003939889,0.00007701599,0.000158743,0.0001301885],"domain_scores_gemma":[0.9995002,0.00003302434,0.0001815482,0.00003512917,0.0002090429,0.00004111232],"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":[0.0007630853,0.0001174437,0.0003874221,0.000787236,0.0005163348,0.000001746422,0.00121199,0.5911261,0.3220409,0.03138308,0.0001160998,0.05154852],"study_design_scores_gemma":[0.003628883,0.001687061,0.00251412,0.0003563945,0.0005005447,0.0009771567,0.001423403,0.7277778,0.2516234,0.001939542,0.007157553,0.0004141188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9087198,0.00160292,0.08717138,0.0003932137,0.00173029,0.000312325,0.00002455378,0.0000340293,0.00001146888],"genre_scores_gemma":[0.9985262,0.0003231521,0.0009692733,0.000009921836,0.0001433225,0.00001651915,5.256367e-7,0.000009467234,0.00000167094],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1366517,"threshold_uncertainty_score":0.340084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01464035208344411,"score_gpt":0.1936580649380174,"score_spread":0.1790177128545733,"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."}}