Epileptic Seizure Detection in EEGs Using Time–Frequency Analysis

TLDR

Detection of recorded epileptic seizure activity in EEG segments is crucial for localization and classification, yet seizure evolution is dynamic, nonstationary, and multi‑frequency, limiting visual and conventional frequency‑based methods. This study demonstrates the suitability of time‑frequency analysis for classifying EEG segments for epileptic seizures and compares several t‑f analysis methods. Short‑time Fourier transform and other t‑f distributions compute the power spectrum density of each segment, from which fractional‑energy features are extracted and used to classify segments with artificial neural networks. The methods were evaluated on three classification problems from a benchmark EEG dataset, producing qualitative and quantitative results.

Abstract

The detection of recorded epileptic seizure activity in EEG segments is crucial for the localization and classification of epileptic seizures. However, since seizure evolution is typically a dynamic and nonstationary process and the signals are composed of multiple frequencies, visual and conventional frequency-based methods have limited application. In this paper, we demonstrate the suitability of the time-frequency (t-f) analysis to classify EEG segments for epileptic seizures, and we compare several methods for t-f analysis of EEGs. Short-time Fourier transform and several t-f distributions are used to calculate the power spectrum density (PSD) of each segment. The analysis is performed in three stages: 1) t-f analysis and calculation of the PSD of each EEG segment; 2) feature extraction, measuring the signal segment fractional energy on specific t-f windows; and 3) classification of the EEG segment (existence of epileptic seizure or not), using artificial neural networks. The methods are evaluated using three classification problems obtained from a benchmark EEG dataset, and qualitative and quantitative results are presented.