{"id":"W4403079654","doi":"10.3389/frai.2024.1437315","title":"Generative AI with WGAN-GP for boosting seizure detection accuracy","year":2024,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Université TÉLUQ","funders":"Canada Research Chairs","keywords":"Oversampling; Computer science; Artificial intelligence; Generative grammar; Pattern recognition (psychology); Machine learning; Boosting (machine learning); Generative adversarial network; Random forest; Deep learning","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":[],"consensus_categories":[],"category_scores_codex":[0.000258948,0.0002155899,0.0002018171,0.0002395674,0.0002093911,0.0004088946,0.0003148312,0.00009590549,0.00001708275],"category_scores_gemma":[0.0005647009,0.0001794144,0.00007141662,0.0006489167,0.0001687939,0.0004991714,0.00005099156,0.0003808994,0.00003326667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001058266,"about_ca_system_score_gemma":0.00007918593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002237431,"about_ca_topic_score_gemma":0.0001128705,"domain_scores_codex":[0.9982335,0.0000909275,0.0003695099,0.0006943304,0.0002103377,0.0004013765],"domain_scores_gemma":[0.9991879,0.0004288649,0.0000670625,0.0001911378,0.00006012888,0.00006491247],"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":[0.0002680405,0.00008215106,0.00009028185,0.0001048036,0.00002112651,0.00009144667,0.003982296,0.008388093,0.2109961,0.005358469,0.007483668,0.7631335],"study_design_scores_gemma":[0.00001732564,0.0001637848,0.000005136217,0.0001130758,0.000007003938,0.00001666431,0.0003507514,0.336563,0.6412923,0.01477144,0.006528678,0.000170903],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04857587,0.0002835541,0.9439812,0.001106678,0.004964273,0.0005125448,0.0000165181,0.0001973815,0.0003619474],"genre_scores_gemma":[0.9827082,0.00002657927,0.01535611,0.0007874513,0.0004449518,0.00008915259,0.000002349357,0.00003343889,0.0005517282],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9341324,"threshold_uncertainty_score":0.7316306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05249748134810538,"score_gpt":0.322638439425429,"score_spread":0.2701409580773236,"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."}}