{"id":"W3047507127","doi":"10.1007/s11042-020-09447-8","title":"Statistical edge-based feature selection for counterfeit coin detection","year":2020,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Currency Recognition and Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Feature vector; Pattern recognition (psychology); Artificial intelligence; Counterfeit; Feature (linguistics); Feature selection; Robustness (evolution); Edge detection; Enhanced Data Rates for GSM Evolution; Precision and recall; Pixel; Test set; Computer vision; Mathematics; Image processing; Image (mathematics)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000661654,0.00009691688,0.00009727431,0.00003938061,0.0002218638,0.0001686421,0.0001048414,0.00007027725,0.00001691803],"category_scores_gemma":[0.00007210176,0.00009668942,0.00003438402,0.0002729491,0.00003184467,0.0001931295,0.00001926198,0.0001148957,0.00004230771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002181176,"about_ca_system_score_gemma":0.00003709855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005111069,"about_ca_topic_score_gemma":0.00001800473,"domain_scores_codex":[0.9992892,0.0000196806,0.0001297721,0.0003280129,0.0001008559,0.0001325184],"domain_scores_gemma":[0.9993876,0.0002045052,0.00005477247,0.00009825373,0.0001180179,0.000136847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002996576,0.00005921349,0.0001412925,0.00004576969,0.000007829771,1.244055e-7,0.00009065032,0.00005580135,0.01132991,0.001747785,0.002282631,0.984209],"study_design_scores_gemma":[0.0006883171,0.0001467282,0.001811521,0.000004877377,0.00001507078,0.000004545853,0.0000135733,0.8530622,0.01389201,0.0005336565,0.1296772,0.0001503228],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007289827,0.00003659807,0.9961526,0.001786253,0.000091316,0.0007085045,0.0001399781,0.0002225416,0.00013319],"genre_scores_gemma":[0.8710251,0.00001713005,0.1251435,0.001295646,0.000526027,0.001737203,0.000188233,0.00001527891,0.00005189756],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9840587,"threshold_uncertainty_score":0.394288,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0363787805505537,"score_gpt":0.2740267961423607,"score_spread":0.237648015591807,"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."}}