{"id":"W4391306315","doi":"10.1109/smc53992.2023.10394136","title":"Towards Privacy Preserving BCIs: Profiling the Feasibility of Federated Learning for Motor Imagery Brain-Computer Interfaces","year":2023,"lang":"en","type":"article","venue":"","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Holland Bloorview Kids Rehabilitation Hospital; University of Toronto","funders":"","keywords":"Computer science; Brain–computer interface; Machine learning; Profiling (computer programming); Artificial intelligence; Motor imagery; Transfer of learning; Wearable computer; Human–computer interaction; Electroencephalography; 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":[0.009692229,0.0008242045,0.0008722603,0.0009410626,0.0007198139,0.002214299,0.001234198,0.001385058,0.0008919665],"category_scores_gemma":[0.05069024,0.0002663262,0.0005897628,0.0009013901,0.001532386,0.003240257,0.001778607,0.001748803,0.0004227047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001416739,"about_ca_system_score_gemma":0.001590571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002191652,"about_ca_topic_score_gemma":0.001263033,"domain_scores_codex":[0.9943554,0.002575323,0.000373015,0.0009041615,0.001348217,0.0004438198],"domain_scores_gemma":[0.9749441,0.01401757,0.001201838,0.005690204,0.003775705,0.0003705663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002190801,0.0006520107,0.01671384,0.000292328,0.0002297553,0.0002579253,0.0004007721,0.6344799,0.01597186,0.01699726,0.002057498,0.3097561],"study_design_scores_gemma":[0.00003656425,0.0003976997,0.003339806,0.00003793971,0.00003125228,0.0001797348,0.0001255932,0.9597993,0.02085701,0.01426431,0.0009051501,0.00002552448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4132932,0.0008482832,0.5805213,0.0009990596,0.0000699442,0.0001849625,0.0002537018,0.001330314,0.002499146],"genre_scores_gemma":[0.9165209,0.0001919082,0.08223251,0.0001138667,0.00001902745,0.00007811863,0.0002247544,0.00006499997,0.0005537759],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009692229,"threshold_uncertainty_score":0.05125809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08459948094995262,"score_gpt":0.339502242149282,"score_spread":0.2549027611993294,"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."}}