Discrimination and classification of focal and non-focal EEG signals using entropy-based features in the EMD-DWT domain

In this paper, a comprehensive analysis of focal and non-focal electroencephalography is carried out in the empirical mode decomposition and discrete wavelet transform domains. A number of spectral entropy-based features such as the Shannon entropy, log-energy entropy and Renyi entropy are calculated in the empirical mode decomposition and discrete wavelet transform domains and their efficacy in discriminating the focal and non-focal EEG signals is investigated. The electroencephalogram signals are obtained from a publicly available electroencephalography database that consists of 7500 signal pairs which contain over 80 h of electroencephalogram data collected from five epilepsy patients. It is shown that in the log-energy entropy when calculated in the combined empirical mode decomposition-discrete wavelet transform domain gives a better discrimination of these signals as compared to that of the other entropy measures that is the Shannon and quadratic Renyi entropy as well as to that obtained in empirical mode decomposition or discrete wavelet transform domain. When the log-energy entropy values are utilized as features in a K-nearest neighbor classifier to classify the signals, it provides 89.4% accuracy (with 90.7% sensitivity), which is higher than that of the state-of-the-art methods. Overall, the proposed classification method reports a significant improvement in terms of sensitivity, specificity and accuracy in comparison to the existing techniques. Besides, for being computationally fast, the proposed method has the potential for identifying the epileptogenic zones, which is an important step prior to resective surgery usually performed on patients with low responsiveness to anti-epileptic medications.