{"id":"W4399585680","doi":"10.1016/j.engstruct.2024.118343","title":"Pixel-level concrete bridge crack detection using Convolutional Neural Networks, gabor filters, and attention mechanisms","year":2024,"lang":"en","type":"article","venue":"Engineering Structures","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":49,"is_retracted":false,"has_abstract":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Convolutional neural network; Bridge (graph theory); Computer science; Structural engineering; Gabor filter; Pixel; Artificial intelligence; Pattern recognition (psychology); Engineering; Feature extraction","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007644639,0.0002839451,0.0001856002,0.0001636202,0.00009730504,0.0001657314,0.00008280972,0.0001429579,0.00001735388],"category_scores_gemma":[0.00001799109,0.0002853716,0.00007211993,0.0001788297,0.00002819371,0.0002645092,0.00003490629,0.0003704645,0.00000150292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001282972,"about_ca_system_score_gemma":0.000009129701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001861965,"about_ca_topic_score_gemma":0.000001106327,"domain_scores_codex":[0.9989659,0.00001026053,0.0002184756,0.0002615642,0.0001560661,0.0003877928],"domain_scores_gemma":[0.9996966,0.00004026292,0.00001946339,0.0001283256,0.00003152257,0.00008382052],"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":[0.000006068169,2.530763e-7,0.00003045959,0.0001791994,0.0000845262,0.00001892379,0.00006937824,0.8099082,0.1835866,0.002223517,0.000087842,0.003805045],"study_design_scores_gemma":[0.0001498058,0.00001923146,0.02018191,0.00009733059,0.00004192639,0.0002001679,0.00001412567,0.9730209,0.004913562,0.0003749557,0.0006671581,0.000318947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4531487,0.001322481,0.5406457,0.000008105866,0.004212215,0.00009913304,0.00002843506,0.0005264156,0.000008758729],"genre_scores_gemma":[0.9896662,0.00003788667,0.009119655,0.00001717467,0.001038609,0.00000956286,0.00001842465,0.00007562833,0.00001684462],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5365175,"threshold_uncertainty_score":0.9999598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01004749709603155,"score_gpt":0.2103510988253206,"score_spread":0.200303601729289,"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."}}