{"id":"W4309570861","doi":"10.3390/s22239031","title":"Automated Impact Damage Detection Technique for Composites Based on Thermographic Image Processing and Machine Learning Classification","year":2022,"lang":"en","type":"article","venue":"Sensors","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Université Laval","funders":"","keywords":"Support vector machine; Aerospace; Composite number; Computer science; Thermography; Confusion matrix; Structural health monitoring; Artificial intelligence; Pattern recognition (psychology); Machine learning; Structural engineering; Engineering; Algorithm; Aerospace 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003834795,0.0005684638,0.0004880467,0.002079883,0.0002379624,0.0004187603,0.0005048636,0.0005389513,0.0009765024],"category_scores_gemma":[0.0006305971,0.0002332041,0.0005013797,0.0009716373,0.0002917158,0.0005589083,0.0002505594,0.0004529367,0.0004041059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00028298,"about_ca_system_score_gemma":0.0003073455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001056364,"about_ca_topic_score_gemma":0.001624275,"domain_scores_codex":[0.9996446,0.00003823864,0.00002312422,0.00007878961,0.0001805719,0.00003471105],"domain_scores_gemma":[0.9994892,0.0001124811,0.0001033825,0.00006591983,0.0002120839,0.00001686014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002812683,0.0002625236,0.005823058,0.0002227353,0.00005604278,0.0001866412,0.0001559944,0.0199392,0.3607988,0.0009836026,0.001329363,0.6099607],"study_design_scores_gemma":[0.00001636146,0.0003528348,0.02798917,0.00002330165,0.00005042405,0.0004648549,0.0001052257,0.7337763,0.2336314,0.0009038383,0.002624189,0.00006211664],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2101434,0.0005236256,0.7839565,0.000112453,0.00006910173,0.0001597554,0.0001533066,0.002816999,0.00206492],"genre_scores_gemma":[0.6164774,0.0003426339,0.3807546,0.00005447962,0.0000417306,0.0001223657,0.0002905277,0.0000628948,0.001853253],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002079883,"threshold_uncertainty_score":0.003266752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0101831854583401,"score_gpt":0.2385255503812305,"score_spread":0.2283423649228905,"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."}}