{"id":"W2598457882","doi":"10.1111/mice.12263","title":"Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks","year":2017,"lang":"en","type":"article","venue":"Computer-Aided Civil and Infrastructure Engineering","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":3134,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Convolutional neural network; Sobel operator; Computer science; Artificial intelligence; Robustness (evolution); Pixel; Computer vision; Canny edge detector; Shadow (psychology); Deep learning; Pattern recognition (psychology); Adaptability; Image (mathematics); Edge detection; Image processing","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002712619,0.0006700404,0.0005152483,0.0008985008,0.000193493,0.0004863293,0.0009013828,0.0007459099,0.001781245],"category_scores_gemma":[0.0008168447,0.00041194,0.0005236177,0.0005593259,0.0002539043,0.0007171787,0.0006428923,0.0008680761,0.0006372592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006241478,"about_ca_system_score_gemma":0.0005493022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01147855,"about_ca_topic_score_gemma":0.01804269,"domain_scores_codex":[0.9998517,0.00001223164,0.000007450932,0.00004582292,0.00004667668,0.00003594916],"domain_scores_gemma":[0.9996449,0.0001162662,0.00005397365,0.00004847242,0.0001112058,0.00002517154],"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":[0.0002968882,0.0002305383,0.007351551,0.0001169717,0.0001315677,0.0001473508,0.00003870206,0.4411699,0.02861086,0.002560169,0.005220114,0.5141253],"study_design_scores_gemma":[0.000001695618,0.000008579174,0.000817059,0.000004437336,0.000005969111,0.0000110821,0.000002148827,0.9962925,0.00213681,0.0004812279,0.0002351952,0.000003337147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2157869,0.001527351,0.7726768,0.0004190632,0.000180963,0.00006260382,0.0008242748,0.003212027,0.00531003],"genre_scores_gemma":[0.9220856,0.0004682652,0.06893399,0.0001295618,0.00005794736,0.00003313495,0.001131153,0.00006385595,0.007096395],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01147855,"threshold_uncertainty_score":0.02282345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004973053066563081,"score_gpt":0.1899400987236036,"score_spread":0.1849670456570405,"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."}}