Automatic Classification of Sleep Stages Using EEG Records. | ||||
MEJ- Mansoura Engineering Journal | ||||
Article 8, Volume 38, Issue 3, September 2013, Page 1-8 PDF (299.54 K) | ||||
Document Type: Research Studies | ||||
DOI: 10.21608/bfemu.2020.106742 | ||||
View on SCiNiTO | ||||
Authors | ||||
Mohamed Mowafy 1; Marwa Obayya2; F. E. Z. Abou-Chadi3; Mohamed saad4 | ||||
1Prof. of Electronics and Communications Engineering Department, Faculty of Engineering, Mansoura University | ||||
2Electronics and Communications Engineering Department, Faculty of Engineering, Mansoura University. | ||||
3Electronics and Communications Engineering Department, Faculty of Engineering, Mansoura University | ||||
4Head of Dept. Neurology, Faculty of Medicine, Mansoura University | ||||
Abstract | ||||
Currently in the world there is an alarming number of people who suffer from sleep disorders. A number of biomedical signals, such as EEG, EMG, ECG, EOG are used in sleep labs among other for diagnosis and treatment of sleep relayed disorders. The usual method for sleep stages classification is visual inspection by a sleep specialist. This is a very time consuming and laborious exercise. Automatic sleep stages classification can facilitate this process. In this work an attempt was made to classify six sleep stages consisting of Awake, Stage 1, Stage 2, Stage3, Stage 4, and REMS. Spectral analysis, Wavelet transform and artificial neural networks were deployed for this purpose. Twenty-four recordings of a healthy six stages studied per 30s epochs. The results demonstrated that the performance for automatically discriminated for these six sleep stages from each other when using wavelet packet with Sym3 where the classification was with average 81.94%. Data fusion improves the accuracy of classification results using fusion at the feature extraction level to 87.7%. | ||||
Keywords | ||||
Artificial Neural Networks; Sleep Analysis; Electroencephalogram (EEG); Data fusion | ||||
Statistics Article View: 114 PDF Download: 199 |
||||