{"id":"W4367624326","doi":"10.3390/s23094444","title":"Automatic Detection and Identification of Defects by Deep Learning Algorithms from Pulsed Thermography Data","year":2023,"lang":"en","type":"article","venue":"Sensors","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Artificial intelligence; Convolutional neural network; Deep learning; Segmentation; Computer science; Thermography; Identification (biology); Artificial neural network; Pattern recognition (psychology); Image segmentation; Algorithm; Field (mathematics); Machine learning; Infrared; Mathematics; Optics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063501,0.0009749129,0.0005234066,0.00119581,0.0001774606,0.0006284203,0.0009427682,0.0007582303,0.001035552],"category_scores_gemma":[0.001484488,0.0003380513,0.0006037528,0.0006647637,0.0003876803,0.0009708854,0.0006388844,0.0008597309,0.0005762346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005395192,"about_ca_system_score_gemma":0.0005091857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002283031,"about_ca_topic_score_gemma":0.003170004,"domain_scores_codex":[0.9997118,0.00003107589,0.00001993768,0.00009480165,0.00009256849,0.00004980987],"domain_scores_gemma":[0.9994453,0.0001539276,0.0001091439,0.00006718384,0.0002010317,0.00002344214],"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":[0.000398362,0.0003555535,0.006784613,0.0003086448,0.0000952343,0.0002520584,0.0001296748,0.1932026,0.1423448,0.001842975,0.002988128,0.6512975],"study_design_scores_gemma":[0.000005045201,0.00006909114,0.001725974,0.00001283328,0.00001446247,0.00003772659,0.00002216833,0.9690317,0.02778449,0.0007466787,0.0005402294,0.000009706709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1726445,0.0005931678,0.821457,0.0001686015,0.00006069892,0.0001021061,0.0004218947,0.002872677,0.001679384],"genre_scores_gemma":[0.6949225,0.0005143377,0.3000616,0.0001412582,0.00002723881,0.0001635136,0.001190967,0.0001327736,0.002845821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002283031,"threshold_uncertainty_score":0.00453949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009987959816891797,"score_gpt":0.2198290319901243,"score_spread":0.2098410721732325,"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."}}