{"id":"W2175772854","doi":"10.1109/tnsre.2015.2501752","title":"Enabling Low-Power, Multi-Modal Neural Interfaces Through a Common, Low-Bandwidth Feature Space","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Frederick A. Coller Surgical Society; Plastic Surgery Foundation; A. Alfred Taubman Medical Research Institute; Wallace H. Coulter Foundation","keywords":"Computer science; Bandwidth (computing); Brain–computer interface; Decoding methods; Modality (human–computer interaction); Feature (linguistics); Interface (matter); Neural decoding; Wireless; Signal processing; SIGNAL (programming language); Artificial intelligence; Computer hardware; Telecommunications; Electroencephalography; Digital signal processing","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001990427,0.0003395854,0.0003556757,0.0001906068,0.000196522,0.0002409154,0.0002035689,0.0001423792,0.000003454321],"category_scores_gemma":[0.00008173909,0.0002842481,0.0001149641,0.0003411702,0.0001131741,0.0006753439,0.000005803381,0.0004873133,0.000009273214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000855182,"about_ca_system_score_gemma":0.000017948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009410399,"about_ca_topic_score_gemma":0.00001427869,"domain_scores_codex":[0.9981974,0.0001586718,0.0003899196,0.0005620997,0.0003215273,0.0003704261],"domain_scores_gemma":[0.9986513,0.0007021789,0.00009871707,0.0002771655,0.00008147994,0.0001891392],"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":[0.00007787321,0.0001522902,0.00004873599,0.0002987365,0.00001656386,0.00001239827,0.005341345,0.8600461,0.1330521,0.00009733524,0.0001804906,0.0006760086],"study_design_scores_gemma":[0.001615927,0.0009478895,0.0002657968,0.0005769319,0.00002185156,0.0001688975,0.001827883,0.8977383,0.09513549,0.00001316822,0.001100378,0.0005875251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8833771,0.000309181,0.1111875,0.0008972154,0.003323204,0.0005151363,0.00002797834,0.0003371563,0.0000256232],"genre_scores_gemma":[0.9984875,0.00001439806,0.0009300346,0.00009413304,0.00007479041,0.00006098087,9.303811e-7,0.00004412017,0.0002930765],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1151105,"threshold_uncertainty_score":0.999961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02155508558872682,"score_gpt":0.2616960420091329,"score_spread":0.2401409564204061,"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."}}