The Feature Extraction Method of EEG Signals Based on Degree Distribution of Complex Networks from Nonlinear Time Series
The nonlinear time series analysis method based on complex networks theory gives a novel perspective to understand the dynamics of the nonlinear time series. Considering the electroencephalogram (EEG) signals showing different nonlinear dynamics under different brain states, this study proposes an epileptic EEG analysis approach based on statistical properties of complex networks and applies the approach to epileptic EEGs automatic detection. Firstly, the complex network is constructed from the epileptic EEG signals and the degree distribution (DDF) of the resulting networks is calculated. Then the entropy of the degree distribution (NDDE) is used as a feature to classify the ictal EEGs and the interictal EEGs. The experiment results show that the NDDE of the ictal EEG is lower than interictal EEG’s and the classification accuracy, taking the NDDE as a classification feature, is up to 96.25%.
KeywordsEEG Epilepsy Seizure detection Complex networks Degree distribution Shannon entropy
Unable to display preview. Download preview PDF.
- 7.Xie, Y., Xu, J.-X., Yang, H.-J., Hu, S.-J.: Phase-Space Reconstruction of ECoG Time Sequences and Extraction of Nonlinear Characteristic Quantities. Acta Phys. Sin. 51(2), 205–214 (2002)Google Scholar
- 8.Xie, Y., Xu, J.-X., Kang, Y.-M., Yang, H.-J., Hu, S.-J.: Nonlinear Noise Reduction for Electrocorticograms. Acta Phys. Sin. 52(5), 1121–1126 (2003)Google Scholar
- 12.Norbert, M., Jonathan, F.D., Zou, Y., Reik, V.D., Jurgen, K.: Complex Network Approach for Recurrence Analysis of Time Series. Physics Letters A 373, 4246–4254 (2009)Google Scholar