{"id":"W4323338364","doi":"10.1109/access.2023.3252897","title":"MICAL: Mutual Information-Based CNN-Aided Learned Factor Graphs for Seizure Detection From EEG Signals","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Computer science; Convolutional neural network; Estimator; Generalizability theory; Pattern recognition (psychology); Artificial intelligence; Correlation; Mutual information; Electroencephalography; Graph; Inference; Machine learning; Data mining; Mathematics; Statistics; Theoretical computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005549587,0.001295833,0.0008565521,0.001086897,0.0002124368,0.0005588016,0.001242938,0.0006613098,0.001915286],"category_scores_gemma":[0.002816352,0.0003829313,0.000774693,0.0006861342,0.0003059609,0.0009275997,0.0009639825,0.0007726552,0.0008113419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006655615,"about_ca_system_score_gemma":0.0008989153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00724519,"about_ca_topic_score_gemma":0.0104906,"domain_scores_codex":[0.9996271,0.00006266755,0.00002055729,0.0001031421,0.0001210899,0.00006532547],"domain_scores_gemma":[0.9995327,0.0001722596,0.0000853856,0.00007226445,0.0001100723,0.00002724072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003357833,0.0001214545,0.003492125,0.0001552751,0.0001887752,0.0002115198,0.00006468578,0.3457756,0.01928941,0.00494973,0.009125217,0.6162904],"study_design_scores_gemma":[0.000008918275,0.00003167275,0.0005757495,0.000006616473,0.000013419,0.0000578728,0.000006638417,0.9911862,0.004411119,0.002642018,0.001050427,0.000009288408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02171437,0.0004416744,0.9706438,0.0001941169,0.00004077505,0.00007443531,0.0005497255,0.005005397,0.0013358],"genre_scores_gemma":[0.5813506,0.0004323406,0.4083196,0.0003561144,0.00009184604,0.0002227282,0.0037708,0.0005089073,0.004947123],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00724519,"threshold_uncertainty_score":0.01440603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0805775991345329,"score_gpt":0.3386890959475823,"score_spread":0.2581114968130494,"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."}}