Diagnosis of Sleep Apnea Syndrome from EEG Signals using Different Entropy measures

Sleep apnea is the most popular sleep disorders which may lead to physical and mental problems. A quick and accurate diagnosis helps physicians to make a suitable remedy for it. Electroencephalogram (EEG) is the electrical activity recorded from the surface of the skull. The identity of EEG is non-linear and complex, thus the study of complexity of EEG signal can be helpful to access valuable information from it. In this paper, 12 entropies (Shannon, Renyi, Tsallis, threshold, permutation, spectral, wavelet, SURE, norm, log energy, fuzzy, and sample), complexity features, are extracted from six frequency bands (delta, theta, alpha, sigma, beta, and gamma) in three different EEG channels. Finally, 72 features were applied to detect apneic subjects from normal ones by using support vector machine classifier (SVM), 90% accuracy was obtained in O1-A2 channel with whole features which is an acceptable accuracy in comparison with other works. Also to select the most effective features, the minimum-redundancy maximum-relevance (mRMR) algorithm was used and 89.07% accuracy with 28 selected features was acquired.