{"id":"W2508774639","doi":"10.1109/tifs.2016.2599270","title":"Continuous Authentication Using One-Dimensional Multi-Resolution Local Binary Patterns (1DMRLBP) in ECG Biometrics","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Information Forensics and Security","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":99,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Computer science; Biometrics; Feature extraction; Word error rate; Pattern recognition (psychology); Authentication (law); Local binary patterns; Artificial intelligence; Feature (linguistics); Feature vector; Quantization (signal processing); Binary number; Computer vision; Histogram; Mathematics; Computer security","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002239138,0.0001336096,0.0002116392,0.0007544465,0.000145593,0.00002899349,0.00003462254,0.000139473,0.00002708028],"category_scores_gemma":[0.00001689402,0.0001063364,0.00008712061,0.0005012784,0.00009051729,0.0004837943,0.000002307582,0.0001689408,0.00002262025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001774451,"about_ca_system_score_gemma":0.00004506309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002361864,"about_ca_topic_score_gemma":0.000035057,"domain_scores_codex":[0.9989284,0.00002979513,0.0004204781,0.0001447437,0.0002863245,0.0001902839],"domain_scores_gemma":[0.9993459,0.00006567291,0.0001186891,0.0001650687,0.0001920309,0.000112624],"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":[0.0009129146,0.001860052,0.02789185,0.0005539887,0.0004335612,0.000019681,0.004141958,0.01017272,0.01218647,0.0005381238,0.0001021953,0.9411865],"study_design_scores_gemma":[0.00388276,0.0003323316,0.0226157,0.0005345429,0.0002238319,0.00003785819,0.0005149571,0.9615152,0.009567591,0.0002477998,0.0002122158,0.0003152371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4431768,0.00001322783,0.556271,0.0001703389,0.0001635884,0.0001103933,0.00005159176,0.00003051719,0.00001248175],"genre_scores_gemma":[0.9940572,0.00008863516,0.005663509,0.00008512459,0.00002612386,0.000009260117,0.00002838792,0.000008124,0.0000336581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9513425,"threshold_uncertainty_score":0.4336272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02587855206873061,"score_gpt":0.2699524053016732,"score_spread":0.2440738532329426,"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."}}