{"id":"W4382982296","doi":"10.3390/s23136077","title":"k-Fold Cross-Validation Can Significantly Over-Estimate True Classification Accuracy in Common EEG-Based Passive BCI Experimental Designs: An Empirical Investigation","year":2023,"lang":"en","type":"article","venue":"Sensors","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autocorrelation; Classifier (UML); Cross-validation; Brain–computer interface; Statistics; Artificial intelligence; Mathematics; Pattern recognition (psychology); Seriousness; Correlation; Computer science; Block design; Electroencephalography; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003114471,0.0002588092,0.0002387867,0.0003279014,0.0002358482,0.0003164505,0.0003347789,0.0001450062,0.00003230323],"category_scores_gemma":[0.0004696048,0.0002550709,0.00006333572,0.0008436471,0.0002422069,0.0004949658,0.00005099928,0.0002425469,0.00008934725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002105873,"about_ca_system_score_gemma":0.0001147842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001783409,"about_ca_topic_score_gemma":0.00007893977,"domain_scores_codex":[0.9972619,0.0006283727,0.0005047657,0.0007373224,0.0004518484,0.0004158239],"domain_scores_gemma":[0.9983196,0.000826575,0.0002527829,0.0003846613,0.00004745838,0.0001689244],"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":[0.00007696985,0.0001331949,0.03682419,0.00001796999,0.00000262935,0.00004482946,0.002492537,0.0210669,0.9379518,0.0002193735,0.0004261669,0.0007434166],"study_design_scores_gemma":[0.0004746072,0.0001477832,0.1276939,0.00003668214,0.00000352679,0.000003112919,0.0003435174,0.2361745,0.6346128,0.0002663939,0.00004019956,0.0002029301],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975281,0.000003893999,0.0001534496,0.0009941327,0.0003129708,0.0004937869,0.00005326434,0.0003815431,0.00007885909],"genre_scores_gemma":[0.9985958,0.000002727038,0.000256307,0.0007618805,0.00006244498,0.00006538564,0.0001453745,0.00003827218,0.00007176319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.303339,"threshold_uncertainty_score":0.9999902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1320162087649119,"score_gpt":0.4027358302915617,"score_spread":0.2707196215266499,"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."}}