Bispectrum Features and Multilayer Perceptron Classifier to Enhance Seizure Prediction

Abstract

The ability to accurately forecast seizures could significantly improve the quality of life of patients with drug-refractory epilepsy. Prediction capabilities rely on the adequate identification of seizure activity precursors from electroencephalography recordings. Although a long list of features has been proposed, none of these is able to independently characterize the brain states during transition to a seizure. This work assessed the feasibility of using the bispectrum, an advanced signal processing technique based on higher order statistics, as a precursor of seizure activity. Quantitative features were extracted from the bispectrum and passed through two statistical tests to check for significant differences between preictal and interictal recordings. Results showed statistically significant differences (p < 0.05) between preictal and interictal states using all bispectrum-extracted features. We used normalized bispectral entropy, normalized bispectral squared entropy, and mean of magnitude as inputs to a 5-layer multilayer perceptron classifier and achieved respective held-out test accuracies of 78.11%, 72.64%, and 73.26%.

Preictal and Interictal Recognition for Epileptic Seizure Prediction Using Pre-trained 2D-CNN Models

“…The preictal part consisted of a 5-minute section one hour before the seizure onset, and the interictal state consisted of a 5-minute section four hours away from the seizure. The authors used 30-sec non-overlapping segments for feature extraction and reported that the best testing accuracy obtained for preictal and interictal classification was 78.11% [40].…”

Detecting Epileptic Seizures in EEG Signals with Complementary Ensemble Empirical Mode Decomposition and Extreme Gradient Boosting

“…Previous research showed that extracting features from different domains, including time domain, frequency domain, and/or time-frequency domain, is effective for developing epileptic seizure detection models [ 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 , 23 , 24 , 25 , 26 ]. Although these three types of features were proposed, none are able to comprehensively characterize EEG signals.…”

“…In frequency domain analysis, the main methods include fast Fourier transform [ 15 ], higher-order spectra [ 16 ], bispectrum [ 17 , 18 ], power spectral analysis [ 19 ], eigenvectors [ 20 ], etc. Polat and Günes extracted the relevant features from raw EEG signals using fast Fourier transform, and built a hybrid system to detect epileptic seizures [ 15 ].…”

“…Ieracitano et al extracted continuous wavelet transform (CWT) and bispectrum features, and built a number of classifiers to perform both two-way and three-way classifications [ 17 ]. Bou Assi et al extracted quantitative features from a bispectrum, and experimental results demonstrated statistically significant differences between interictal and preictal states with bispectrum-extracted features [ 18 ]. Goldfine et al evaluated an EEG spectrum from 4 to 24 Hz with univariate comparisons and multivariate comparisons, and the experimental results demonstrated that EEG spectral analysis could be used to demonstrate awareness in patients with severe brain injury [ 19 ].…”

Detection of the interictal epileptic discharges based on wavelet bispectrum interaction and recurrent neural network

“…This prompts us to study the interaction between frequencies of the EEG signal to track the changes in EEG arising from linear and nonlinear changes under a variety of physiologic conditions. Recently, the higher-order statistic (HOS) methods [16][17][18][19][20][21] such as bispectrum (BS) and wavelet bispectrum (WBS) have been used for extracting features of the bio-signals. HOS methods explore the existence of quadratic (and cubic) nonlinear coupling between the different frequency components of a signal.…”