A convolutional neural network for sleep stage scoring from raw single-channel EEG
| العنوان: | A convolutional neural network for sleep stage scoring from raw single-channel EEG |
|---|---|
| المؤلفون: | Sébastien Mirek, Jean-François Payen, Stéphane Bonnet, Arnaud Sors, Laurent Vercueil |
| المساهمون: | Commissariat à l'énergie atomique et aux énergies alternatives - Laboratoire d'Electronique et de Technologie de l'Information (CEA-LETI), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Centre Hospitalier Universitaire de Dijon - Hôpital François Mitterrand (CHU Dijon), Centre Hospitalier Universitaire [Grenoble] (CHU) |
| المصدر: | Biomedical Signal Processing and Control Biomedical Signal Processing and Control, 2018, 42, pp.107-114. ⟨10.1016/j.bspc.2017.12.001⟩ Biomedical Signal Processing and Control, Elsevier, 2018, 42, pp.107-114. ⟨10.1016/j.bspc.2017.12.001⟩ |
| بيانات النشر: | Elsevier BV, 2018. |
| سنة النشر: | 2018 |
| مصطلحات موضوعية: | Channel (digital image), Computer science, Generalization, Feature extraction, Convolutional neural network, Health Informatics, 02 engineering and technology, Single-channel, Electroencephalography, [SPI]Engineering Sciences [physics], 03 medical and health sciences, 0302 clinical medicine, Cohen's kappa, 0202 electrical engineering, electronic engineering, information engineering, medicine, Preprocessor, EEG, medicine.diagnostic_test, business.industry, Supervised learning, Pattern recognition, Classification, Sleep staging, Sleep Heart Health Study, Signal Processing, 020201 artificial intelligence & image processing, Artificial intelligence, business, 030217 neurology & neurosurgery |
| الوصف: | International audience; We present a novel method for automatic sleep scoring based on single-channel EEG. We introduce the use of a deep convolutional neural network (CNN) on raw EEG samples for supervised learning of 5 class sleep stage prediction. The network has 14 layers, takes as input the 30-s epoch to be classified as well as two preceding epochs and one following epoch for temporal context, and requires no signal preprocessing or feature extraction phase. We train and evaluate our system using data from the Sleep Heart Health Study (SHHS), a large multi-center cohort study including expert-rated polysomnographic records. Performance metrics reach the state of the art, with accuracy of 0.87 and Cohen kappa of 0.81. The use of a large cohort with multiple expert raters guarantees good generalization. Finally, we present a method for visualizing class-wise patterns learned by the network. |
| تدمد: | 1746-8094 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2b8a1f5f4ffa1015996d965d4986adce https://doi.org/10.1016/j.bspc.2017.12.001 |
| حقوق: | CLOSED |
| رقم الأكسشن: | edsair.doi.dedup.....2b8a1f5f4ffa1015996d965d4986adce |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 17468094 |
|---|