{"id":"W3135700689","doi":"10.3390/bdcc5010009","title":"Automatic Defects Segmentation and Identification by Deep Learning Algorithm with Pulsed Thermography: Synthetic and Experimental Data","year":2021,"lang":"en","type":"article","venue":"Big Data and Cognitive Computing","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Thermography; Artificial neural network; Convolutional neural network; Nondestructive testing; Computer science; Artificial intelligence; Synthetic data; Segmentation; Deep learning; Identification (biology); Machine learning; Experimental data; Pattern recognition (psychology); Algorithm; Infrared","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":[0.0001822749,0.0001424426,0.0001304449,0.0000579286,0.0001783027,0.0001582372,0.000108038,0.00003969647,0.000005106957],"category_scores_gemma":[0.00002574682,0.0001396685,0.000007575542,0.0001486911,0.00008575473,0.0002174585,0.0002240023,0.0001131125,1.884968e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004291918,"about_ca_system_score_gemma":0.000005907012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009641974,"about_ca_topic_score_gemma":0.000004246834,"domain_scores_codex":[0.9991615,0.00007349676,0.000141235,0.0003893217,0.00009589697,0.000138553],"domain_scores_gemma":[0.9994654,0.000171622,0.00004827215,0.0002314688,0.00003044658,0.00005277378],"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":[0.000004576962,0.00002126979,0.0009726137,0.00007954137,0.00008462911,0.000009123907,0.000616412,0.000003761478,0.04268748,0.000001679921,0.00001333908,0.9555055],"study_design_scores_gemma":[0.0007288625,0.00007827263,0.01189083,0.0004249989,0.0002407832,0.0001228547,0.005112493,0.9140692,0.06687175,0.00003820195,0.00004867921,0.0003730473],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6396824,0.005977609,0.3534911,0.000002550179,0.00003394262,0.0001370996,0.0004923303,0.0001570084,0.00002593345],"genre_scores_gemma":[0.995517,0.0002304477,0.002471132,0.00001802433,0.00002845396,0.000007286439,0.001704493,0.00002180692,0.000001367071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9551325,"threshold_uncertainty_score":0.5695515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02192510317903041,"score_gpt":0.2521473211379021,"score_spread":0.2302222179588717,"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."}}