Prediction of Epileptic Seizures using digital signal processing and support vector machine

Abstract

Epilepsy is a neurological disorder that causes abnormal behavior and recurrent seizures due to unusual brain activity. Our study has attempted to predict seizures in epileptic patients through the process of feature extraction from EEG signals during preictal and ictal periods, classification and regularization. EEG signals from various parts of the brain from 10 epileptic patients were collected. The signals were converted into its frequency components using a method called fast Fourier transform or FFT. It was then used to determine the three features- the phase angle, the amplitude and the power spectral density of the signals. In order to classify the signals, these features were then used. Regularization was then used to make better predictions i.e. increase the prediction accuracy and decrease the rate of false alarm rate. Through this study, we hope to contribute to the development of better and advanced seizure predicting devices in the medical field.