Epileptic seizure detection using STFT based peak mean feature and support vector machine

Epilepsy is a neurological condition of intermittent brain dysfunction arising from irregular neuronal discharge through the brain. The electroencephalogram (EEG) offers valuable information about the brain’s physiological states and is also an effective method for detecting epilepsy. This study aims to develop a computer-aided automation system to identify epileptic seizures through EEG data from epileptic and healthy subjects. We employed discrete Short-time Fourier transform (STFT) to decompose EEG data into sub-bands, and sample entropy, mean, and peak mean features were extracted from each sub-band. Feature ’mean’ accounts for baseline differences, ’sample entropy’ for the chaotic nature of EEG data, and ’peak mean’ for the amplitude differences between healthy and epileptic EEG data. We achieved the highest classification accuracy of 100% in distinguishing epileptic ictal EEG signals and EEG signals from healthy subjects through 10-fold cross-validation using the Support vector machine with radial basis function (SVM-RBF) classifier. We also presented the comparison of peak mean feature with other well-known features in epilepsy detection using EEG. The high accuracy results obtained by the peak mean feature show its potential in seizure detection using EEG.