Preprocessing effects of 22 linear univariate features on the performance of seizure prediction methods

Abstract

Combining multiple linear univariate features in one feature space and classifying the feature space using machine learning methods could predict epileptic seizures in patients suffering from refractory epilepsy. For each patient, a set of twenty-two linear univariate features were extracted from 6 electroencephalogram (EEG) signals to make a 132 dimensional feature space. Preprocessing and normalization methods of the features, which affect the output of the seizure prediction algorithm, were studied in terms of alarm sensitivity and false prediction rate (FPR). The problem of choosing an optimal preictal time was tackled using 4 distinct values of 10, 20, 30, and 40 min. The seizure prediction problem has traditionally been considered a two-class classification problem, which is also exercised here. These studies have been conducted on the features obtained from 10 patients. For each patient, 48 different combinations of methods are compared to find the best configuration. Normalization by dividing by the maximum and smoothing are found to be the best configuration in most of the patients. The results also indicate that applying machine learning methods on a multidimensional feature space of 22 univariate features predicted seizure onsets with high performance. On average, the seizures were predicted in 73.9% of the cases (34 out of 46 in 737.9h of test data), with a FPR of 0.15 h(-1).

Characterization of EEG patterns in brain-injured subjects and controls after a Snoezelen® intervention

“…It is important to note that the term MF is also known as 50% spectral edge frequency (SEF50) [23,24]. A parameter strongly related to MF is the mean frequency whose original definition is based on the computation of the spectral centroid.…”

An Enhanced Wavelet Neural Network Model with Metaheuristic Harmony Search Algorithm for Epileptic Seizure Prediction

“…Different classifiers have been proposed in the task of epileptic seizure prediction. They include neural mass model [4], support vector machines [5], and phase synchronization-based model [24].…”

“…In [5], 22 univariate features are generated from each of the 6 EEG signals. Therefore, each patient is characterized by a 132 dimensional feature space.…”

“…The results also suggested the existence of a pre-ictal period that precedes the onset of seizures. In [5], a feature space was derived from EEG signals by combining 22 linear univariate features. Different preprocessing and normalization methods were employed to study the biomedical signals.…”

Efficient feature selection using a hybrid algorithm for the task of epileptic seizure detection

“…For example, spectral power features, statistical moments, Hjorth parameter, spectral edge power, wavelet coefficients, Lyapunov exponent, and others [3,7].…”