Vigilance Analysis Based on Continuous Wavelet Transform of EEG Signals

Electroencephalography (EEG) is considered a reliable indicator of a person's vigilance level. In this paper, we use EEG recordings to discriminate three vigilance states of a person, namely alert, drowsy, and sleep, while driving a car in a simula-tion environment. The proposed framework explores the use of continuous wavelet transform in EEG signal processing. A large set of features is extracted from the wavelet coefficients, which are computed from EEG signals with multiple wavelet functions. We use random forest to rank the plenty of features and select the most important ones for later classification. Samples of EEG data are then trained and classified by SVM (Support Vector Machine). On datasets acquired from 5 subjects, our method reveals high classification accuracy (over 96%).