School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China

---

Abstract—This paper presents a new Algorithm to analyze the Electroencephalography (EEG) signal, which is regarded as an important way to analyze the alcoholism. In order to distinguish the nonlinear characteristics of EEG with alcoholic people and the control, an exponential power ratio index (EPRI) is proposed to quantify the slow wave and fast wave power features of the EEG signal, and the Independent Component Analysis (ICA) and Support Vector Machine (SVM) are combined for analysis. The proposed method is implemented on the real data sets acquired from UCI common databases, which have been studied by some research groups. The results suggest that the proposed method is valid for analysis of EEG signal in alcoholism.

Index Terms—Electroencephalography (EEG), Independent Component Analysis (ICA), Support Vector Machine (SVM), Time Series, Feature Analysis

[PDF]

Cite: Mingyue Yan, "An Exponential Power Ratio Index based Algorithm for Analysis of Alcoholic EEG Signal," Journal of Software vol. 8, no. 9, pp. 2385-2390, 2013.