{"id":"W2999321776","doi":"10.1002/ima.22398","title":"Enhancing multivariate pattern analysis for magnetoencephalography through relevant sensor selection","year":2020,"lang":"en","type":"article","venue":"International Journal of Imaging Systems and Technology","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Brain Institute; Western University","funders":"","keywords":"Computer science; Magnetoencephalography; Dimensionality reduction; Artificial intelligence; Pattern recognition (psychology); Feature selection; Principal component analysis; Cluster analysis; Unsupervised learning; Decoding methods; Pipeline (software); Selection (genetic algorithm); Feature (linguistics); Mutual information; Multivariate statistics; Machine learning; Psychology","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":[0.0007073096,0.0007533155,0.0004843599,0.0006060543,0.0001844476,0.0005021964,0.0004090544,0.0003221508,0.001517487],"category_scores_gemma":[0.003021505,0.0001896275,0.000641954,0.0007020774,0.0002975068,0.0005538329,0.0005130327,0.0005297829,0.0005445801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001607302,"about_ca_system_score_gemma":0.000451458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006461525,"about_ca_topic_score_gemma":0.001225681,"domain_scores_codex":[0.9997124,0.0001228133,0.00001578443,0.00005458701,0.000069924,0.00002452177],"domain_scores_gemma":[0.9990742,0.0004817257,0.00009971749,0.0001420385,0.0001683779,0.00003390818],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004195738,0.0002639026,0.004741715,0.0001992877,0.0001868637,0.0001780836,0.0001146626,0.08307441,0.2602135,0.004436368,0.003913785,0.6422579],"study_design_scores_gemma":[0.00001843529,0.0001007254,0.008795349,0.00001063767,0.0000399755,0.0001829769,0.0000227523,0.9237904,0.05866881,0.006425199,0.001915011,0.00002975893],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02871374,0.0001099146,0.9697528,0.0001140839,0.00002081381,0.00002582609,0.000111462,0.0008298183,0.0003215687],"genre_scores_gemma":[0.4463753,0.000231492,0.5513351,0.00007976943,0.00006435624,0.0001124232,0.0004245172,0.0002727571,0.001104239],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001517487,"threshold_uncertainty_score":0.005076468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01724979700023097,"score_gpt":0.2693448880303046,"score_spread":0.2520950910300737,"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."}}