A review of feature extraction and performance evaluation in epileptic seizure detection using EEG

Abstract

Since the manual detection of electrographic seizures in continuous electroencephalogram (EEG) monitoring is very time-consuming and requires a trained expert, attempts to develop automatic seizure detection are diverse and ongoing. Machine learning approaches are intensely being applied to this problem due to their ability to classify seizure conditions from a large amount of data, and provide pre-screened results for neurologists. Several features, data transformations, and classifiers have been explored to analyze and classify seizures via EEG signals. In the literature, some jointly-applied features used in the classification may have shared similar contributions, making them redundant in the learning process. Therefore, this paper aims to comprehensively summarize feature descriptions and their interpretations in characterizing epileptic seizures using EEG signals, as well as to review classification performance metrics. To provide meaningful information of feature selection, we conducted an experiment to examine the quality of each feature independently. The Bayesian error and non-parametric probability distribution estimation were employed to determine the significance of the individual features. Moreover, a redundancy analysis using a correlation-based feature selection was applied. The results showed that the following features -variance, energy, nonlinear energy, and Shannon entropy computed on a raw EEG signal, as well as variance, energy, kurtosis, and line length calculated on wavelet coefficients-were able to significantly capture the seizures. An improvement of 4.77-13.51% in the Bayesian error from the baseline was obtained.

ScoreNet: A Neural network-based post-processing model for identifying epileptic seizure onset and offset in EEGs

“…Training and test data were taken from the same patient but different records. Detection methods were validated with all patient cases; they were assessed using event-based, epoch-based, and time-based metrics (Temko et al, 2011;Boonyakitanont et al, 2020a). The event-based metrics included good detection rate (GDR) and false positive rate per hour (FPR/h).…”

“…Several studies have developed methods to automatically detect epileptic seizures in EEG epochs (Acharya et al, 2015;Alotaiby et al, 2015;Boonyakitanont et al, 2020a;Hassan et al, 2020). Some studies focused on extracting single features relevant to EEG characteristics, e.g., amplitude (Satirasethawong et al, 2015;Shoeb and Guttag, 2010;Altunay et al, 2010), statistics (Samiee et al, 2015;Li et al, 2017), entropy (Tawfik et al, 2016;Li et al, 2018;Gupta and Pachori, 2019) and predictability (Kumar et al, 2015;Jaiswal and Banka, 2017;Li et al, 2019).…”

Automated seizure diagnosis system based on feature extraction and channel selection using EEG signals

“…These features can be classified on the basis of their description or the field where the attributes are determined. Many other researchers have found a basic group of attributes appropriate to their suggested classification system, while some have introduced different groups of variables obtained from time, frequency and time-frequency domains [25][26][27][28][29][30] Classification is the process of identifying groups or classes based on similarities between them. This step is essential to distinguish between seizure itself-the ictal period-and the normal non-ictal period.…”

Sonlu Dürtü Yanıtı Filtresi ve Yapay Sinir Ağları Eğitim Algoritmaları tabanlı Epileptik EEG Sinyalinin Sınıflandırılması

“…Therefore, an objective EEG signal for evaluation of different methods were analyzed. In the literature, studies have been carried out on the EEG data (wavelet coefficient, entropy, fractal sizing, and statistical features) of epileptic patients and control group (healthy) individuals (Boonyakitanont, et. al.…”