{"id":"W2730013855","doi":"10.1016/j.clinph.2017.06.247","title":"Unsupervised detection and removal of muscle artifacts from scalp EEG recordings using canonical correlation analysis, wavelets and random forests","year":2017,"lang":"en","type":"article","venue":"Clinical Neurophysiology","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"European Regional Development Fund; Research Promotion Foundation","keywords":"Independent component analysis; Pattern recognition (psychology); Artificial intelligence; Computer science; Wavelet; Artifact (error); Autocorrelation; Random forest; Cluster analysis; Noise (video); Electroencephalography; Canonical correlation; Blind signal separation; Speech recognition; Mathematics; Statistics; Channel (broadcasting)","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":[0.0002234212,0.0001612234,0.0005979735,0.00008588939,0.0003018333,0.00007301351,0.000251762,0.0001811218,0.0000160412],"category_scores_gemma":[0.002644025,0.0001372602,0.0001597973,0.0001075739,0.0007462549,0.0001997231,0.0002860306,0.0003130635,0.000004649902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007572468,"about_ca_system_score_gemma":0.00002397376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002566011,"about_ca_topic_score_gemma":0.0001096505,"domain_scores_codex":[0.9977781,0.0005419343,0.0006169704,0.0007287594,0.0001147543,0.0002195324],"domain_scores_gemma":[0.9967659,0.002140611,0.000439407,0.0004726021,0.0000488602,0.0001325862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0005702672,0.00007285013,0.01239845,0.00001038941,0.00004043227,0.00005102146,0.00003983741,0.0003280483,0.943724,0.00001526826,0.000004426248,0.04274506],"study_design_scores_gemma":[0.001395716,0.0003449741,0.77547,0.00001822885,0.0001268958,0.00002133555,0.000003199266,0.2049601,0.01666145,0.0007582727,0.0001162978,0.0001235713],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966436,0.00002279037,0.002265989,0.0001259076,0.0007058649,0.0001523179,0.00001236351,0.00002443563,0.0000467424],"genre_scores_gemma":[0.9989936,0.0001103638,0.0004370946,0.0002876438,0.0001328909,0.000001605364,0.00000236188,0.00001320421,0.0000212249],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9270625,"threshold_uncertainty_score":0.5597308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06842096653408411,"score_gpt":0.34225346309979,"score_spread":0.273832496565706,"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."}}