Investigation of drowsiness while driving utilizing analysis of heart rate fluctuations

Sleepiness is a main causal factor for accidents and daytime malfunction. In this study we checked the feasibility of a new, ECG based method to detect the propensity to fall asleep while driving, using a passive Maintenance of Wakefulness Test (MWT) and an active Driving Simulation (DS) during increasing sleep deprivation conditions. Microsleeps (MS), and falling asleep (FA) events, were detected from electroencephalogram analysis. HRV was characterized using Time Domain analysis, Time Frequency Decomposition, Entropy, and Poincare plots. The first MS during MWT and DS represented a point for significant changes in all HRV measures. The first accident on DS occurred 2-7 minutes after the first MS. There are clear HRV markers that indicate sleepiness in sleep deprived subjects. Provided some of these variables show the same trends in sleepy non sleep deprived subjects, a threshold should be defined as to imminent danger of a driver falling asleep at the wheel.