Performance analysis of classifiers in the detection of seizer and normal stages from EEG signals

The Electroencephalogram (EEG) signal is popularly used technique to analyse the brain activities and measured using Scalp electrodes which quite useful in detecting status of epilepsy a subject also supplement CT scan measurement. EEG signals are indirectly indicate condition Brain. sampled at 256 samples/second for sixteen epochs considered this work. In paper features normal seizure extracted statistical classified Detrend Fluctuation Analysis, Analysis EM, log regression, Non Linear regression. classifier performance compared standard parameters like sensitivity, specificity, Accuracy, Performance Index False Alarm. highest accuracy 98.96% obtained hybrid regression Normal an 98.96 % achieved with Expectation Maximization signal.