Feature Extraction and Detection of Obstructive Sleep Apnea from Raw EEG Signal
- 25 Downloads
Electrocardiogram (EEG) signal detects the electrical activity of the brain. It records all the physiological changes occur in the brain. These signals are useful for detecting different types of sleep disorders. This paper aims in detecting obstructive sleep apnea (OSA) using SVM classifier and DWT technique. The EEG signal is extracted from the polysomnographic database removing the other artifacts, namely electrocardiogram (ECG), blood pressure (BP), respiratory signal at abdominal, respiratory signal at nasal, oxygen saturation are removed. Then, the EEG signal is segmented into four sub-bands as delta(\(\delta \)), theta(\(\theta \)), alpha(\(\alpha \)), and beta(\(\beta \)). The approximation coefficients and detailed coefficients are extracted from these sub-bands using wavelet decomposition technique with Daubechies order-2 (db2) transform. All these coefficients are given to SVM classifier for the detection of OSA. The accuracy of classifier is tested in three cases: in case 1, 90% of data is given for testing; in case 2, 70% is given; and in case 3, only 50% of data is given for testing. It is observed, case 1 has 98% of accuracy in detecting the obstructive sleep apnea. In this paper, 16 healthy subjects and 8 unhealthy subjects are considered. The detailed and approximation coefficients are extracted for all 2500 samples.
KeywordsElectrocardiogram (EEG) Obstructive sleep apnea (osa) Discrete wavelet transform (DWT) Support vector machine (SVM) classifier
The authors wish to thank the publicly available physio bank database https://physionet.org/physiobank/.
- 1.A.S. Al-Fahoum, A.A. Al-Fraihat, Methods of EEG signal features extraction using linear analysis in frequency and time-frequency domains. ISRN Neurosci. 13 (2014)Google Scholar
- 6.W.S. Almuhammadi, K.A. Aboalayon, M. Faezipour, Efficient obstructive sleep apnea classification based on EEG signals, in 2015 IEEE Systems, Applications and Technology Conference (LISAT) (IEEE, Long Island, 2015), pp. 1–6Google Scholar
- 8.P. Jahankhani, V. Kodogiannis, K. Revett, EEG signal classification using wavelet feature extraction and neural networks, in JVA ’06. IEEE John Vincent Atanasoff 2006 International Symposium on Modern Computing (IEEE, 2006), pp. 120–124Google Scholar
- 10.L. Almazaydeh, K. Elleithy, M. Faezipour, Detection of obstructive sleep apnea through ECG signal features, in 2012 IEEE International Conference on Electro/Information Technology (EIT) (IEEE, 2012), pp. 1–6Google Scholar
- 12.D. Alvarez, R. Hornero, J.V. Marcos, F. del Campo, M. Lopez, Spectral analysis of electroencephalogram and oximetric signals in obstructive sleep apnea diagnosis, in Engineering in Medicine and Biology Society. EMBC 2009. Annual International Conference of the IEEE (IEEE, 2009)Google Scholar