Detection of Epileptic Seizure Using EEG Sensor

Abstract

The epileptic seizure is a disease of central nervous system. Its detection by the physical analysis of the person?s body is very difficult. So, the appropriate detection of the seizure is very crucial in diagnosis of the person with seizure. The person with epileptic seizure which affects the brain signal can be detected by analyzing the brain signals using EEG sensor. The electroencephalogram (EEG) signal is very essential in the diagnosis of epilepsy. Long-term EEG recordings of an epileptic patient contain a huge amount of EEG data. The detection of epileptic activity is, therefore, a very demanding process that needs a detailed analysis of the entire length of the EEG data, usually performed by an expert. This paper describes an automated classification of EEG signals for detecting epileptic seizures using wavelet transform and statistical analysis. The decision making process is comprised of three different stages: (1) filtering of EEG signals given as input (2) feature extraction based on wavelet transform, and (3) classification by SVM classifier. The signal from brain given as an input to EEG sensor is analyzed using MATLAB by signal processing technique.