Discrimination of focal and non-focal EEG signals using entropy-based features in EEMD and CEEMDAN domains

In this paper, a comprehensive analysis for the discrimination of the focal and non-focal electroencephalography (EEG) signals is carried out in the ensemble empirical mode decomposition (EEMD) and complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) domains. A number of spectral entropy-based features such as the Shannon entropy, log-energy entropy, Renyi entropy and Tsallis entropy are calculated in the EEMD and CEEMDAN domain of the EEG signals. In lieu of using the signals from the EEG channels, the differences between two adjacent EEG channels are used due to its robustness to noise and interference. The ability of the entropy-based features in separating the focal and non-focal EEG signals is explored utilizing the one-way ANOVA analysis and the box-whisker plots. The results reveal that among the entropy measures computed in the EEMD and CEEMDAN domains, the quadratic Renyi entropy and log-energy entropy measures are most promising in discriminating the focal and non-focal EEG signals. The analysis may encourage the researchers to develop improved algorithms to classify these signals and would be helpful in locating the epileptogenic zones.