{"id":"W3121652263","doi":"10.3390/s21030750","title":"Introduction of Deep Learning in Thermographic Monitoring of Cultural Heritage and Improvement by Automatic Thermogram Pre-Processing Algorithms","year":2021,"lang":"en","type":"article","venue":"Sensors","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Ministerio de Ciencia, Innovación y Universidades","keywords":"Artificial intelligence; Thermography; Computer science; Automation; Segmentation; Convolution (computer science); Data processing; Field (mathematics); Image processing; Convolutional neural network; Process (computing); Computer vision; Deep learning; Artificial neural network; Pattern recognition (psychology); Machine learning; Image (mathematics); Engineering; Infrared; Database; Mechanical engineering","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":[0.0001409587,0.0001395155,0.0002237017,0.0001052001,0.00003116774,0.00001775285,0.00005659979,0.00008269095,0.00001617517],"category_scores_gemma":[0.00001834467,0.0001332438,0.00005493344,0.0003870213,0.00006710314,0.00008336812,0.00001760676,0.0001943419,4.944148e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001692439,"about_ca_system_score_gemma":0.000004491172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004205946,"about_ca_topic_score_gemma":0.000004180743,"domain_scores_codex":[0.9992039,0.00004267476,0.0002936422,0.0001622426,0.0001255606,0.0001719486],"domain_scores_gemma":[0.9996963,0.00002710669,0.00007327505,0.0001211702,0.00005135609,0.0000308426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005755883,0.00003376768,0.003962062,0.0004226712,0.00004468615,0.000003092276,0.00344884,0.004311208,0.6712992,0.000005098992,0.000004554002,0.3164591],"study_design_scores_gemma":[0.0004134019,0.000152448,0.04183827,0.0002725653,0.00005645639,0.00001558095,0.008926271,0.1299554,0.8177952,0.0001267795,0.0001122059,0.0003354284],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961336,0.002723591,0.0006443106,0.00001289994,0.00008558568,0.0001224809,0.00001021133,0.0002033945,0.00006396297],"genre_scores_gemma":[0.9971392,0.0004617966,0.002277859,0.000001107798,0.00005745859,0.00001333335,0.000007543538,0.00002462263,0.00001705263],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3161237,"threshold_uncertainty_score":0.5433524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004473439342449172,"score_gpt":0.2146784648773587,"score_spread":0.2102050255349095,"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."}}