作者: J. Gade , A. Rosenfalck , I. Bendtson
关键词: Detection theory 、 Unsupervised learning 、 Electroencephalography 、 Eeg patterns 、 Artificial intelligence 、 Classifier (UML) 、 Internal medicine 、 Probabilistic classification 、 Pattern recognition 、 Hypoglycemia 、 Endocrinology 、 Nocturnal hypoglycemia 、 Medicine
摘要: The aim of the project was to detect specific EEG patterns related hypoglycemia. analysis performed using a probabilistic classifier and unsupervised learning for construction sets classifier. Unsupervised additional tools were used in search occurring when blood-glucose level below hypoglycemic threshold. rate these 5% normal nights. In patients who known have no or reduced glucagon response hypoglycemia, increased 20-80%.