{"id":"W2015362166","doi":"10.1155/2008/743103","title":"Optimal Features Subset Selection and Classification for Iris Recognition","year":2008,"lang":"en","type":"article","venue":"EURASIP Journal on Image and Video Processing","topic":"Biometric Identification and Security","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Institute of Standards and Technology","keywords":"Biometrics; Iris recognition; Pattern recognition (psychology); Artificial intelligence; Selection (genetic algorithm); Computer science; IRIS (biosensor); Feature selection","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004461076,0.0001019763,0.0001070043,0.0003246259,0.0008467987,0.0007104143,0.0001212886,0.00006154674,0.00000367811],"category_scores_gemma":[0.0001687048,0.00008930227,0.00003375346,0.0004681972,0.00005043933,0.001262509,0.00001880061,0.0002142026,0.000004744586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003087895,"about_ca_system_score_gemma":0.00006175417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000166798,"about_ca_topic_score_gemma":7.914982e-7,"domain_scores_codex":[0.9991214,0.00005684421,0.0002197866,0.0002582895,0.0001863215,0.0001573664],"domain_scores_gemma":[0.9992298,0.00006994224,0.0002061302,0.00007097924,0.0003197787,0.0001033913],"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":[0.0001027717,0.0001320867,0.001087191,0.00009866273,0.00001753652,0.00001504027,0.001890482,0.000003056865,0.02638365,0.000288317,0.01259595,0.9573852],"study_design_scores_gemma":[0.005825953,0.001636601,0.6392503,0.0005399171,0.0001255298,0.01596478,0.0007996592,0.1940416,0.06562321,0.008466843,0.06602529,0.001700297],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2771567,0.0008719116,0.7191074,0.002360542,0.0001521118,0.0001334847,0.000003716268,0.00006394277,0.0001502172],"genre_scores_gemma":[0.8954116,0.0005985742,0.1031447,0.0004466288,0.0001963321,0.000009437603,0.000008898535,0.000009336678,0.0001745898],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.955685,"threshold_uncertainty_score":0.6850542,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05679887883331938,"score_gpt":0.3025141708221692,"score_spread":0.2457152919888499,"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."}}