{"id":"W4402329819","doi":"10.1016/j.compeleceng.2024.109615","title":"Enhanced defect detection on wind turbine blades using binary segmentation masks and YOLO","year":2024,"lang":"en","type":"article","venue":"Computers & Electrical Engineering","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Binary number; Turbine; Segmentation; Turbine blade; Computer science; Artificial intelligence; Marine engineering; Computer vision; Aerospace engineering; Environmental science; Engineering; Mathematics","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":[0.0001363016,0.0002373379,0.0002203933,0.0004411174,0.00007449114,0.0001527792,0.00005280841,0.0001696626,0.000004591884],"category_scores_gemma":[0.00002103182,0.000236722,0.00009591139,0.0006793923,0.000008567566,0.0001754569,0.00001819748,0.0003947644,0.00001507378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002817301,"about_ca_system_score_gemma":0.00001039376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001011607,"about_ca_topic_score_gemma":4.179647e-7,"domain_scores_codex":[0.9989622,0.0000248593,0.0002527877,0.0002897478,0.0001703828,0.0003000812],"domain_scores_gemma":[0.999607,0.0001553742,0.00001801035,0.0001086446,0.00001769395,0.00009326314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001378275,0.000005385466,0.000001533256,0.00008320816,0.00006427153,0.00001447544,0.00007833496,0.4538671,0.4680668,0.0000345758,0.00003883131,0.07773168],"study_design_scores_gemma":[0.0002176427,0.0002218415,0.0001183443,0.0001613229,0.00003057867,0.00005237062,0.000004866303,0.8294366,0.1691269,0.000008405504,0.0004028761,0.000218274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5700052,0.0008352149,0.4268836,0.000004216328,0.00137686,0.0001682492,0.000001046212,0.000683943,0.00004167052],"genre_scores_gemma":[0.9986252,0.00003389859,0.0007269751,0.00001105349,0.0005217299,0.000009644257,0.000003416417,0.00005750785,0.00001054113],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4286201,"threshold_uncertainty_score":0.9653242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01185321229588755,"score_gpt":0.2234253770144981,"score_spread":0.2115721647186106,"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."}}