{"id":"W4360954520","doi":"10.1016/j.jobe.2023.106326","title":"3D vision-based bolt loosening assessment using photogrammetry, deep neural networks, and 3D point-cloud processing","year":2023,"lang":"en","type":"article","venue":"Journal of Building Engineering","topic":"Image and Object Detection Techniques","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Point cloud; Convolutional neural network; Photogrammetry; Engineering; Point (geometry); Artificial intelligence; Pipeline (software); Structural engineering; Computer science; Computer vision; Mechanical engineering","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":[0.0005930513,0.001379762,0.0009290848,0.00399824,0.0004485864,0.001606359,0.00104022,0.001247053,0.003558662],"category_scores_gemma":[0.00148704,0.0005017797,0.0007625264,0.001893899,0.0005590583,0.001406347,0.001449516,0.0006841335,0.001616906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005864894,"about_ca_system_score_gemma":0.0006139156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003353492,"about_ca_topic_score_gemma":0.006361295,"domain_scores_codex":[0.9991245,0.00005225228,0.00004463326,0.0001625129,0.0005165096,0.00009959943],"domain_scores_gemma":[0.9990782,0.0001346472,0.0001933406,0.0001307647,0.0003811097,0.00008202406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008900258,0.0003320352,0.05808268,0.0004291555,0.0002165615,0.0007517231,0.0003508034,0.2852198,0.08647382,0.001735402,0.004465783,0.5610521],"study_design_scores_gemma":[0.00001859409,0.0001334368,0.03624329,0.00005261509,0.000107637,0.0002399426,0.0002481324,0.9324787,0.02694581,0.001355606,0.002115799,0.00006047752],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3972437,0.0008607543,0.5885236,0.0001632896,0.0001651651,0.0001949453,0.00082429,0.005051673,0.006972563],"genre_scores_gemma":[0.9566312,0.0002230968,0.04029834,0.00003556083,0.00001720157,0.0000324762,0.0005750339,0.0001571084,0.002029901],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00399824,"threshold_uncertainty_score":0.0119049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008419506259872775,"score_gpt":0.2699930061416644,"score_spread":0.2615734998817916,"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."}}