{"id":"W4289169399","doi":"10.1016/j.heliyon.2022.e10063","title":"Damage characterization of embedded defects in composites using a hybrid thermography, computational, and artificial neural networks approach","year":2022,"lang":"en","type":"article","venue":"Heliyon","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"King Fahd University of Petroleum and Minerals","keywords":"Thermography; Artificial neural network; Nondestructive testing; Computational model; Characterization (materials science); Materials science; Thermal; Computer science; Composite number; Structural engineering; Artificial intelligence; Biological system; Engineering; Algorithm; Infrared; Optics; Nanotechnology","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":[0.0001059578,0.00009861799,0.0001413056,0.0002052432,0.0000702497,0.00001643867,0.00006478836,0.00002558622,0.00001286726],"category_scores_gemma":[0.000001401043,0.0001137115,0.00003981443,0.0003299951,0.00003453744,0.00006020587,0.00003396018,0.0001526859,1.876421e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001343839,"about_ca_system_score_gemma":0.000003693939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006125972,"about_ca_topic_score_gemma":9.85987e-7,"domain_scores_codex":[0.9994092,0.00006766418,0.0001848692,0.0001153341,0.00009840599,0.0001245007],"domain_scores_gemma":[0.9998051,0.00003533728,0.00004351403,0.00008056167,0.0000128322,0.00002266148],"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":[0.00003218657,0.00005548324,0.003479932,0.0001441476,0.00001454736,0.00000419898,0.000384826,0.6235173,0.3713256,0.0001232456,0.000002123431,0.0009163219],"study_design_scores_gemma":[0.0001182543,0.00003764094,0.03012263,0.00002758024,0.00001273075,0.00001257414,0.00005536982,0.9640334,0.005317912,0.0001405525,0.000004690914,0.0001166339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9330639,0.0003067332,0.06606313,0.00000187887,0.00006405228,0.0002062672,0.0001318481,0.0001226196,0.0000395268],"genre_scores_gemma":[0.9989655,0.00002875682,0.0007584677,0.00002281634,0.00002194988,0.00002604041,0.0001556322,0.00002053138,3.045475e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3660077,"threshold_uncertainty_score":0.463702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01208083932436693,"score_gpt":0.2104047744597433,"score_spread":0.1983239351353764,"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."}}