{"id":"W4313413122","doi":"10.1109/bibm55620.2022.9995697","title":"Defensive Adversarial Training for Enhancing Robustness of ECG based User Identification","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Hanyang University","keywords":"Robustness (evolution); Computer science; Artificial intelligence; Identification (biology); Wearable computer; Machine learning; Wearable technology; Noise (video); Gaussian noise; Adversarial system; Noise measurement; Data mining; Pattern recognition (psychology); Noise reduction; Embedded 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":[0.001775315,0.0008985355,0.0006919206,0.0004845409,0.0003537273,0.0005033195,0.0009291919,0.0009581402,0.0009289117],"category_scores_gemma":[0.007425782,0.0002661633,0.0004368738,0.0002542439,0.0009977862,0.001144644,0.001572208,0.001381698,0.0002589342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004074082,"about_ca_system_score_gemma":0.0004455842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000770236,"about_ca_topic_score_gemma":0.0006198011,"domain_scores_codex":[0.9988722,0.0003926936,0.00005794927,0.0002184964,0.0002949495,0.0001636308],"domain_scores_gemma":[0.9965275,0.002468904,0.0002558778,0.0003782898,0.0002622587,0.000107091],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006452911,0.0001673663,0.002893385,0.0001147766,0.00009559389,0.0003966739,0.000192808,0.8331713,0.03290815,0.01104641,0.001279549,0.1170887],"study_design_scores_gemma":[0.000003900054,0.00006001055,0.0002195723,0.000006102022,0.000007915052,0.00007198759,0.000008553016,0.9929668,0.005212375,0.001257696,0.0001785096,0.000006691249],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08199593,0.0003851619,0.9142725,0.0002985083,0.00008184097,0.0000465153,0.00004055001,0.0006701982,0.002208709],"genre_scores_gemma":[0.9628949,0.0001332997,0.03575563,0.0001495765,0.00003004512,0.00002746575,0.00004246066,0.00002804327,0.000938633],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001775315,"threshold_uncertainty_score":0.009388864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08006396738555416,"score_gpt":0.3304434298012353,"score_spread":0.2503794624156811,"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."}}