{"id":"W2593116849","doi":"10.1016/j.microrel.2017.02.013","title":"Fault detection using thermal image based on soft computing methods: Comparative study","year":2017,"lang":"en","type":"article","venue":"Microelectronics Reliability","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Soft computing; Computer science; Principal component analysis; Fault detection and isolation; Histogram; Printed circuit board; Artificial intelligence; Adaptive neuro fuzzy inference system; Artificial neural network; Fuzzy logic; Finite element method; Support vector machine; Image processing; Engineering; Pattern recognition (psychology); Image (mathematics); Fuzzy control system","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":[0.001015345,0.0005460784,0.0007444109,0.002664718,0.0002342222,0.0006674544,0.0005638862,0.0006583742,0.001574357],"category_scores_gemma":[0.00354232,0.0001869158,0.0006179715,0.001219397,0.0002965452,0.0009567897,0.0003116202,0.0002665221,0.0002616454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003524777,"about_ca_system_score_gemma":0.0002788414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001732368,"about_ca_topic_score_gemma":0.001714725,"domain_scores_codex":[0.9991869,0.0002023424,0.00004908907,0.0001079853,0.0003852092,0.00006847037],"domain_scores_gemma":[0.996561,0.00182529,0.0002062916,0.0001765932,0.00115867,0.00007220236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002504708,0.0005758644,0.02160152,0.001089112,0.0005427473,0.0002192363,0.0003105688,0.05028081,0.04360231,0.001589062,0.001505555,0.8761784],"study_design_scores_gemma":[0.00005496619,0.001901305,0.04867425,0.0001132573,0.0006967132,0.0007710566,0.0004671444,0.8888993,0.05441666,0.001437731,0.002468397,0.00009922838],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.742628,0.01198785,0.2341666,0.0002395493,0.0002348577,0.0001041036,0.0002013692,0.0006153528,0.009822285],"genre_scores_gemma":[0.9688845,0.002114371,0.02693475,0.0000414358,0.0000749433,0.00002593822,0.0001260147,0.00004174136,0.001756244],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002664718,"threshold_uncertainty_score":0.005369723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04081144518267854,"score_gpt":0.3547048570552663,"score_spread":0.3138934118725878,"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."}}