{"id":"W4367680609","doi":"10.1177/14759217231168212","title":"Deep learning-based concrete defects classification and detection using semantic segmentation","year":2023,"lang":"en","type":"article","venue":"Structural Health Monitoring","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Convolutional neural network; Segmentation; Deep learning; Pattern recognition (psychology); Histogram of oriented gradients; Contextual image classification; Machine learning; Classifier (UML); Image segmentation; Histogram; Image (mathematics)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001737779,0.0001946188,0.0001851487,0.0002067019,0.0004477673,0.00006531025,0.00005628568,0.00008824977,0.000002026062],"category_scores_gemma":[0.0000279653,0.0002014007,0.00003512839,0.0003833389,0.00002942357,0.0002095627,0.00001800545,0.0002988797,0.000005681998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003649133,"about_ca_system_score_gemma":0.000024525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008165626,"about_ca_topic_score_gemma":0.00000899445,"domain_scores_codex":[0.9987811,0.00005347605,0.000275457,0.000229012,0.0001887048,0.0004722117],"domain_scores_gemma":[0.9995725,0.00005480381,0.00008994516,0.0001146792,0.00004791097,0.0001202251],"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":[0.00002899092,4.284119e-7,0.09719503,0.001035422,0.00003308378,0.000008233775,0.001597167,0.438095,0.321204,0.00002050367,0.000004610342,0.1407775],"study_design_scores_gemma":[0.000319535,0.00005242779,0.2267057,0.000121112,0.00001163326,0.00001100722,0.000831052,0.7327328,0.03890841,0.00006296204,0.00004038639,0.0002030806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894203,0.0003162747,0.006515086,0.00001742358,0.002738928,0.0002478641,0.000001211664,0.000728297,0.00001464405],"genre_scores_gemma":[0.9977795,0.0001088562,0.001364502,0.000008889699,0.0006497875,0.00001895058,0.00001487052,0.00004787524,0.000006742968],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2946377,"threshold_uncertainty_score":0.8212882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02244567678710882,"score_gpt":0.2947964006468159,"score_spread":0.2723507238597072,"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."}}