Classify and Compare Using S-SVM and LS-SVM for EMD Based Feature Extraction of EEG Signal

摘要

Disease identification is major task in the field of biomedical. This research paper presents a feature extraction from Electroencephalogram (EEG) signals using empirical mode decomposition (EMD). It discriminate the EEG signals corresponding to healthy persons and epileptic patients during seizure - free intervals and seizure attacks. It gives an effective time-frequency analysis of non-stationary signals. The intrinsic mode functions (IMF) obtained by the result of EMD give the decomposition of a signal according to its frequency components. This project presents the usage of temporal statistics, and spectral features including spectral centroid , coefficient of variation and the spectral skew of the IMFs for feature extraction from EEG signals. These features extraction is relevant to find out the normal and pathological EEG signal. The normal EEG signals have different temporal and spectral centroids , dispersions and symmetries when compared with the pathological EEG signals. The structured support vector machine (S-SVM) and least square support vector machine (LS- SVM) are used for the classification purposes. In this paper both this two classifier used to classify the EEG signals , Finally compare the performance and accuracy of both this two classifier, determine whether the S-SVM is more suitable for the EEG signals classification .