Epileptic EEG signal classification using optimum allocation based power spectral density estimation

Abstract

This study proposes a novel approach blending optimum allocation (OA) technique and spectral density estimation to analyse and classify epileptic electroencephalogram (EEG) signals. This study employs the OA to determine representative sample points from the original EEG data and then applies periodogram (PD), autoregressive (AR), and the mixture of PD and AR to extract the discriminative features from each OA sample group. The obtained feature sets are evaluated by three popular machine learning methods: support vector machine (SVM), quadratic discriminant analysis (QDA), and k-nearest neighbour (k-NN). Several output coding approaches of the SVM classifier are tested for selecting the best feature sets. This scheme was implemented on a benchmark epileptic EEG database for evaluation and also compared with existing methods. The experimental results show that the OA_AR feature set yields better performances by the SVM with an overall accuracy of 100%, and outperforms the state-of-the-art works with a 14.1% improvement. Thus, the findings of this study prove that the proposed OA-based AR scheme has significant potential to extract features from EEG signals. The proposed method will assist experts to automatically analyse a large volume of EEG data and benefit epilepsy research.

Exploring Hermite transformation in brain signal analysis for the detection of epileptic seizure

“…Cross correlation, Complex network; Auto correlation; Cross-variances; Correlation dimension) [7][8][9][10][11], frequency domain feature (e.g. Fast Fourier Transform (FFT); Eigenvector; Autoregressive) [12][13][14], timefrequency domain features (e.g. Short Time Fourier Transform (STFT); Wavelet transform (WT); empirical mode decomposition (EMD)) [5,[15][16][17][18][19][20][21][22][23].…”

Altered Functional Connectivity after Epileptic Seizure Revealed by Scalp EEG

“…PSD, which estimates the distribution of power spectrum over frequency bins, is a well-established technique for quantitative analysis of EEG signals, as well as for epilepsy [ 8 , 39 ]. In this study, we first computed the PSD of pre- and postseizure via Welch's method and then statistically compared the PSD per electrode between the two conditions to uncover any potential differences using paired t -test.…”

“…Previous studies focusing on epileptic seizures found increased synchronization [ 4 – 6 ] and increased energy of brain waves [ 7 ] occur before the onset of epileptic seizure. The power spectral density (PSD) has been widely used to measure the fluctuating power of related epileptic activity [ 8 , 9 ]; for example, Bettus et al estimated the PSD difference between drug-resistant and drug-sensitive mesial temporal lobe epilepsy patients and found significantly decreased subtheta PSD in the drug-resistant group [ 10 ]. Additionally, nonlinear analyses have been widely used to uncover the dynamic information of the brain activity in epileptic patients (EPs) [ 11 ].…”

A Novel Permutation Entropy-Based EEG Channel Selection for Improving Epileptic Seizure Prediction

“…The classifier in this research is the SVM, as the SVM classification complexity does not depend on the feature dimension, and it provides a global solution [ 28 , 29 , 30 ], which might be appropriate for epileptic EEG classification. Shiao et al [ 31 ] showed that the SVM-based seizure prediction system could achieve a robust prediction for preictal period and normal period iEEG signals from dogs with epilepsy.…”