Classification of focal and non-focal EEG signals in VMD-DWT domain using ensemble stacking

摘要

Classification of focal and non-focal Electroencephalogram (EEG) signals is an important problem especially for the identification of epileptogenic sites in the brain. However, the number of research works reported in the literature is limited and most of them suffer from validation on a limited scale and moderate accuracy. In this paper, focal and non-focal EEG signals are analyzed in variational mode decomposition (VMD) and discrete wavelet transform (DWT) domain and features such as refined composite multiscale dispersion entropy, refined composite multiscale fuzzy entropy, and autoregressive model (AR) coefficients are extracted in VMD, DWT and VMD-DWT domain. Statistical analysis of the features is carried out by one way ANOVA to demonstrate their discriminating ability by means of p-values and visual inspection of the box plots of the features. A feature reduction algorithm based on neighborhood component analysis is used to reduce the model complexity and select the features with the highest discriminating abilities. An ensemble stacking classification approach is adopted to improve the accuracy of classification. The performance of the proposed method is studied using a publicly available benchmark database that contains 3750 pairs of focal and 3750 pairs of non-focal EEG signals. It is shown that the stacking configuration improves the accuracy significantly compared to a standalone classifier. It gives high values of sensitivity (96.1%), Specificity (94.4%), Accuracy (95.2%) and area under curve (0.989). Comparison with various existing methods reveals that the proposed method outperforms the others in accuracy. It may help researchers in developing a computer-aided system to identify epileptogenic sites in the brain. (C) 2019 Elsevier Ltd. All rights reserved.