{"id":"W2125596974","doi":"10.1109/ccece.2008.4564817","title":"A SVM classifier combined with PCA for ultrasonic crack size classification","year":2008,"lang":"en","type":"article","venue":"Conference proceedings - Canadian Conference on Electrical and Computer Engineering","topic":"Ultrasonics and Acoustic Wave Propagation","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Pattern recognition (psychology); Support vector machine; Artificial intelligence; Principal component analysis; Classifier (UML); Feature selection; Computer science; Dimensionality reduction; Kernel Fisher discriminant analysis; Linear discriminant analysis; Kernel principal component analysis; Kernel (algebra); Feature extraction; Radial basis function kernel; Dimension (graph theory); Kernel method; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.000912495,0.00076739,0.001500759,0.001765751,0.0005419592,0.000864752,0.0005999223,0.001048624,0.002438422],"category_scores_gemma":[0.00245734,0.0004236292,0.0007416727,0.001864059,0.0002245977,0.001161135,0.0003553035,0.001020284,0.00212466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003518597,"about_ca_system_score_gemma":0.0005506927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001687034,"about_ca_topic_score_gemma":0.001824913,"domain_scores_codex":[0.9989976,0.0001468113,0.0000807117,0.0001549067,0.0005474214,0.00007252012],"domain_scores_gemma":[0.9988846,0.000279916,0.0000689794,0.00008891332,0.0006345679,0.00004308745],"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":[0.0002222297,0.0001884017,0.002204327,0.0001807344,0.00009335154,0.0001973839,0.00003458018,0.02620407,0.06448077,0.002604236,0.007263693,0.8963262],"study_design_scores_gemma":[0.00002520759,0.0002546138,0.00336961,0.00002763476,0.00006549996,0.000388267,0.00002095154,0.9566341,0.02856116,0.001792911,0.0088153,0.00004475605],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01789182,0.0007047633,0.9767177,0.0001803978,0.0003004175,0.0001038269,0.0001994437,0.002199916,0.00170172],"genre_scores_gemma":[0.2961723,0.001194884,0.6934419,0.0001362691,0.0002937641,0.0002917343,0.0009885196,0.0001482731,0.007332357],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002438422,"threshold_uncertainty_score":0.008157372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01863103409535043,"score_gpt":0.183739627017571,"score_spread":0.1651085929222206,"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."}}