Classification of EEG signals for epileptic seizure evaluation

Abstract

Feature extraction and classification of biosignals is an important issue in development of disease diagnostic expert system (DDES). In this paper we propose a simple method for EEG classification based on Fourier features. Parameters like energy, entropy, power, and kurtosis were considered for discrimination of various categories of EEG signals. After calculating the above mentioned parameters of the discussed signals, we found that without going for rigorous time-frequency domain analysis, only frequency based analysis is well suitable to classify various EEG signals.