Classification of epileptic seizures using wavelet packet log energy and norm entropies with recurrent Elman neural network classifier

Abstract

Electroencephalogram shortly termed as EEG is considered as the fundamental segment for the assessment of the neural activities in the brain. In cognitive neuroscience domain, EEG-based assessment method is found to be superior due to its non-invasive ability to detect deep brain structure while exhibiting superior spatial resolutions. Especially for studying the neurodynamic behavior of epileptic seizures, EEG recordings reflect the neuronal activity of the brain and thus provide required clinical diagnostic information for the neurologist. This specific proposed study makes use of wavelet packet based log and norm entropies with a recurrent Elman neural network (REN) for the automated detection of epileptic seizures. Three conditions, normal, pre-ictal and epileptic EEG recordings were considered for the proposed study. An adaptive Weiner filter was initially applied to remove the power line noise of 50 Hz from raw EEG recordings. Raw EEGs were segmented into 1 s patterns to ensure stationarity of the signal. Then wavelet packet using Haar wavelet with a five level decomposition was introduced and two entropies, log and norm were estimated and were applied to REN classifier to perform binary classification. The nonlinear Wilcoxon statistical test was applied to observe the variation in the features under these conditions. The effect of log energy entropy (without wavelets) was also studied. It was found from the simulation results that the wavelet packet log entropy with REN classifier yielded a classification accuracy of 99.70 % for normal-pre-ictal, 99.70 % for normal-epileptic and 99.85 % for pre-ictalepileptic.

Frontal EEG Changes with the Recovery of Carotid Blood Flow in a Cardiac Arrest Swine Model

“…Table 2 shows the Pearson correlation coefficients between EEG parameters and the recovery rates of CBF. Among them, time-domain magnitude and two entropy indices, log energy entropy [25] and Rényi entropy [26], showed a correlation coefficient of approximately 0.78. Figure 4 demonstrates the scatter plots for these three parameters.…”

Redundancy Removed Dual-Tree Discrete Wavelet Transform to Construct Compact Representations for Automated Seizure Detection

“…The model of Kumar et al [4] can discriminate normal data from ictal data with a 100% accuracy and also discriminate interictal data from ictal data with a very low error rate. Methods proposed by Raghu et al [42] yielded excellent performance for both classification tasks on Bonn database. Moreover, previous studies also proposed wavelet-based methods [43,44] and achieved a 100% or almost 100% classification accuracy.…”

Real-Time Localization of Epileptogenic Foci EEG Signals: An FPGA-Based Implementation

“…Table 1 lists the 39 features considered in this work for each segment of the signal dataset. All these have been used succesfully as features in previous EEG seizure detection works [14,[30][31][32][33][34][35][36][37].…”

“…Log energy entropy (LogEn) [30] Non-normalized energy based entropy Median frequency (MDF) [31] Division of the EEG power spectrum into two regions Mean frequency (MNF) [31] Mean normalized frequency of the power spectrum Katz fractal dimension (KFD) [31] Index characterizing the fractal pattern complexity Lower quartile 1 (Q1) [31] 25% of the EEG signal Upper quartile 3 (Q3) [31] 75% of the EEG signal Inter quartile range (IQR) [31] Difference between Q3 and Q1 Semi inter quartile deviation (SID) [31] Measure of spread Skewness (Sk) [32] Measure of the degree of symmetry Kurtosis (Kr) [32] Measure of tailedness of the probability distribution Root mean square (RMS) [33] Root mean square of the EEG signal Band power (PB) [33] Average power of the EEG signal (0 to f s /2) Zero crossing (ZC) [33] Number of times that the signal changes of sign Complexity (Comp) [33] Hjorth parameter Mobility (Mob) [33] Hjorth parameter Activity (Act) [33] Hjorth parameter Spurious free dynamic range (SFDR) [34] Length along a EEG signal Curve length (CL) [34] Length along a EEG signal Teager energy (TE) [34] Non linear energy Variance (Var) [34] Variance of the EEG signal Standard deviation (Std) [34] Standard deviation of the signal Mean (Mean) [34] Mean of the EEG signal 1st derivative variance (Var1) [34] Variance of the first derivative 1st derivative standard deviation (Std1) [34] Standard deviation of the first derivative 1st derivative mean (Mean1) [34] Mean of the first derivative 2nd derivative variance (Var2) [34] Variance of the second derivative 2nd derivative standard deviation (Std2) [34] Standard deviation of the second derivative 2nd derivative mean (Mean2) [34] Mean of the second derivative Derivative variance ratio (RatioVar) [36] Ratio of derivative respect absolute of derivative variances Power (P) [35] Power of the signal window 1st difference (1d)…”