{"id":"W7037157578","doi":"","title":"Deep learning-based surface and subsurface damage identification using computer vision and thermography","year":2023,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Ichthyology and Marine Biology","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Research Manitoba","keywords":"Deep learning; Segmentation; Identification (biology); Process (computing); Ground truth; Residual; Structural health monitoring; Thermography; Image segmentation","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000297227,0.0006566416,0.0004295861,0.000775521,0.0001956919,0.0005308912,0.0006452316,0.0005904931,0.0008473202],"category_scores_gemma":[0.0005827133,0.0003669695,0.0007721382,0.0004674875,0.0005139479,0.0008614599,0.0007464567,0.0009208061,0.000323014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008462194,"about_ca_system_score_gemma":0.0007245264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005338167,"about_ca_topic_score_gemma":0.007103199,"domain_scores_codex":[0.9998077,0.00002080306,0.000008195273,0.00006422047,0.00006470534,0.00003435711],"domain_scores_gemma":[0.9998074,0.00004878865,0.00004572521,0.00002726619,0.00005357378,0.00001732084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001175217,0.0001258834,0.003479999,0.00009343856,0.00007337295,0.0001492533,0.00007759697,0.7119545,0.03537873,0.004624764,0.001802619,0.2421223],"study_design_scores_gemma":[0.000001184177,0.00001626313,0.0005519069,0.000003667608,0.000005460026,0.00001605172,0.000005207425,0.9940206,0.003991166,0.001091046,0.0002931052,0.000004219788],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09366534,0.0005209983,0.9011309,0.0002220203,0.00006212642,0.00006014767,0.0001318675,0.001398632,0.002808064],"genre_scores_gemma":[0.8931453,0.0005243934,0.1006017,0.0001502029,0.0000431639,0.00006621662,0.0003701239,0.0000704891,0.005028522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005338167,"threshold_uncertainty_score":0.01061416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008968622165295044,"score_gpt":0.2100166368862252,"score_spread":0.2010480147209302,"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."}}