{"id":"W3205369454","doi":"10.1109/access.2021.3118971","title":"LiHEA: Migrating EEG Analytics to Ultra-Edge IoT Devices With Logic-in-Headbands","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thunder Bay Regional Research Institute; Lakehead University","funders":"","keywords":"Computer science; Deep learning; Edge computing; Artificial intelligence; Analytics; Edge device; Convolutional neural network; Enhanced Data Rates for GSM Evolution; Machine learning; Electroencephalography; Cloud computing; Data science","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":[0.0001395108,0.0002036888,0.0002692964,0.0001365733,0.0001241021,0.00049945,0.000716452,0.00006489826,0.00005258496],"category_scores_gemma":[0.0001830344,0.0001578241,0.00004944932,0.001066073,0.00005489859,0.000313808,0.00009081022,0.0002289601,0.00005003407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003557208,"about_ca_system_score_gemma":0.00008186013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007435506,"about_ca_topic_score_gemma":0.001699338,"domain_scores_codex":[0.9982582,0.0001020236,0.0002905739,0.0006326006,0.0003003549,0.0004162657],"domain_scores_gemma":[0.9989381,0.0004037934,0.0000895779,0.0003440952,0.00009514383,0.0001292596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001116451,0.0004803854,0.1440874,0.0002244965,0.00003154583,0.001464121,0.002560928,0.01735771,0.8201796,0.0005274767,0.006088454,0.006886151],"study_design_scores_gemma":[0.0003370151,0.0001378937,0.01350625,0.0002037982,0.00001177408,0.00007467586,0.0001424121,0.001791239,0.9805592,0.0001314081,0.002804538,0.0002998362],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.990039,0.00007609815,0.002337089,0.001636145,0.0004494651,0.0001438655,0.00001288062,0.00007975832,0.005225681],"genre_scores_gemma":[0.992869,0.000009941556,0.0007881523,0.005565254,0.0001368844,0.00001270971,0.000001526531,0.00001926977,0.0005972258],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1603795,"threshold_uncertainty_score":0.6435879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06822003191656277,"score_gpt":0.3398467743748696,"score_spread":0.2716267424583068,"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."}}