Empirical and Advanced Classification for Automatic Seizure EEG Detection in Brain Images

Abstract

Epilepsy may occur with result of abnormal transiting disturbance and electrical relative activities appear in human brain. Electroencephalogram (EEG) is a sufficient test measure to maintain records with respects to electrical activity of brain and it is widely used in analysis and detection of electro epileptic seizures. Based on emergency inception appear in human brain related set data sets, 1-dimensional pyramidal ensemble conventional neural network (1D-PECNN) is one the approach to classify different instances with respect attribute relations only. It is often complex to classify EEG signals from human EEG brain images. And also some of the human brain images consists high amount of EEG related content then it is very complex to interpretations to classify EEG signals. So in this paper, we propose Empirical De-composition based Classification Approach (EDCA) for the analysis of abnormal epileptic seizure signal from human brain images. EDCA evaluates intrinsic mode functions (IMF), it extract different features obtained from IMF for classification of abnormal epileptic seizure detection using least square support vector machine (L-SVM) classifier with different radius bias functions (RBF). RBF provides best accuracy of classification for proposed approach with respect to epileptic seizure EEG extraction from human brain images. An experimental result of proposed approach gives better and accurate results with respect to existing approaches in terms of different parameters.