Classification of epileptic states using root-MUSIC and MLPNN

A new approach based on root-MUSIC frequency estimation method and a Multiple Layer Perceptron neural network is introduced. In this method, a feature vector is formed using power frequency, entropy, standard deviation, as well as the complexity of the time domain Electroencephalography (EEG) signal. The power frequency values are estimated using root-MUSIC algorithm. The resulted feature vector is then classified into three categories namely healthy, interictal (epileptic during seizure-free interval), and ictal (full epileptic condition during seizure interval) states using Multiple Layer Perceptron Neural Network (MLPNN). The experimental results show that EEG states classification maybe achieved with approximately 94.53% accuracy and variance of 0.063% applying the method on an available public database. This is a high speed with high accuracy as well as low misclassification rate method.