Seizure detection using median based feature

Epilepsy is a common neurological disorder which is difficult to treat because of its unpredictable and recurrent nature. The electroencephalogram (EEG) is a valuable tool for detecting epileptic seizures. With the aim of reducing the input feature dimensionality, a single median based feature called interquartile range (IQR) was used in this paper for the classification of normal and seizure EEG signals. Classification was done using a linear classifier and a support vector machine (SVM) classifier. Normal and seizure signals were classified with an accuracy of 71.62% and 96.57% using linear and SVM classifier respectively.