Empirical Mode Decomposition In Epileptic Seizure Prediction

In this paper, we attempt to analyze the effectiveness of the Empirical Mode Decomposition (EMD) for discriminating preictal periods from the interictal periods. The Empirical Mode Decomposition (EMD) is a general signal processing method for analyzing nonlinear and nonstationary time series. The main idea of EMD is to decompose a time series into a finite and often small number of intrinsic mode functions (IMFs). EMD is an adaptive decomposition method since the extracted information is obtained directly from the original signal. By utilizing this method to obtain the features of interictal and preictal signals, we compare these features with traditional features such as AR model coefficients and also the combination of them through self-organizing map (SOM). Our results confirmed that our proposed features could potentially be used to distinguish interictal from preictal data with average success rate up to 89.68% over 19 patients.