Multivariate Multiscale Entropy: An Approach to Estimating Vigilance of Driver

Various driver’s vigilance estimation techniques currently exist in the literature. But none of them estimates complexity domain. In this research, we propose recently introduced multivariate multiscale entropy method to fill above mentioned research gap. We apply technique differential features electroencephalogram and electrooculogram signals detect vigilance. Also, employ it percentage eye closure values analyse cognitive states (awake, tired drowsy) The contribution is efficiently classify using a new feature based on entropy. experimental profile curves show statistically significant differences (p < 0.01) among brain electroencephalogram, forehead signals. Moreover, difference sample across all scales awake (1.0828 ± 0.4664), (0.7841 0.3183) drowsy (0.2938 0.1664) are <0.01). support vector machine, machine learning technique, discriminates with promising classification accuracy 76.2%. Therefore, could be an indicator for estimation.