期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2017
卷号：95
期号：16
页码：4024
出版社：Journal of Theoretical and Applied
摘要：A comprehensive research of Electroencephalography (EEG) is carried out on Empirical Mode Decomposition (EMD) and Discrete Wavelet Transform (DWT) domains. In this scenario, the hybrid feature extraction is performed by utilizing entropy features like Shannon entropy, log-energy entropy and Renyi entropy. Generally, the entropy measures are effective in evaluation of non-linear interrelation and complexity of signals. After that, a superior classifier named as Support Vector Machine (SVM) is implemented for classifying the signals. Experimental outcome proves that the advanced method distinguishes the focal and non-focal signals with a superior accuracy.
关键词：Empirical Mode Decomposition (EMD); Intrinsic Mode Function (IMF); Support Vector Machine (SVM)
