An Analysis of EEG Changes during Prolonged Simulated Driving for the Assessment of Driver Fatigue

Abstract

Fatigue during driving is the main contributing factor to road accidents. It is influenced by time on task (TOT) and time of day (TOD). Recent electroencephalogram (EEG) research on fatigue assessment has shown a promising result in explaining the fatigue phenomenon. However, different findings exist regarding the best EEG parameters related to fatigue. This study examined EEG changes according to the effect of TOT and TOD and determined the best parameters to distinguish fatigue status. To generate driver fatigue, prolonged driving in the morning and at night in a simulator was conducted. The EEG signal was collected from 28 male participants at frontal and occipital areas. The EEG power (brainwave) was determined from the first and last 5 minutes of the driving task and after a break of 30 minutes. The results of this study showed a general tendency of EEG power changing throughout the driving sessions. However, changes related to fatigue were only found for the night sessions, as confirmed by θ power and the subjective fatigue measurement result. This study showed that TOT (as a factor that induces fatigue) was explained by θ from the frontal area, whereas TOD was differentiated by α, θ, θ/β, (θ+α)/β and (θ+α)/(β+α).

Prediction of drowsiness using EEG signals in young Indonesian drivers

“…When exhausted, a driver's θ and α power are significantly higher than those when non-fatigued. As Zuraida et al [ 28 ] noted, the increase in the θ wave is more dominant than those of the others. Meanwhile, other studies demonstrated that deteriorating performance and diminished alertness are accompanied by an increase in θ and a decrease in β activity [ 14 , 60 ].…”

“…The mean value of the 15-min PSDs was used to represent each brain wave as an EEG metric. The EEG parameters of power- α , power- β , power- θ and four ratios of brainwaves ( θ / β , θ /[ α + β ], [ θ + α ]/ β , and [ θ + α ]/[ α + β ]) were analyzed [ 26 , 28 ]. The EEG parameters were selected based on the significant difference found for the four ratios of brainwaves between alert and fatigue in driving conditions; these four ratios of brainwaves were considered to be good indicators of driver drowsiness [ 26 , 45 , 46 ].…”

“…They found that the parameter ( θ + α )/ β at the frontal and temporal points resulted in the most significant difference between alert and sleepy conditions. According to the research of Zuraida et al [ 28 ], the increase in power θ , which is dominant in the frontal area, can be used as a strong indicator of fatigue.…”

Fatigue Among Indonesian Commercial Vehicle Drivers: A Study Examining Changes in Subjective Responses and Ocular Indicators

“…This study found that driving for about 2.5 hours resulted in moderate level of fatigue, and that a 15-minute rest period did not return fatigue measures to their baseline values. Previous studies have shown that 2 to 3 hours of driving (following a restful night sleep) generally do not yield excessive fatigue and sleepiness (Zuraida et al, 2019;Puspasari et al, 2018;Wang et al, 2018;Di-Stasi et al, 2012;Craig et al, 2011). However, discrepancies do exist due to differences in experimental settings (field vs. simulator) and also due to inter-individual differences (Ingre et al, 2006).…”

“…sleep durations prior to the experiment). The work of Zuraida et al (2019), for instance, shows the progression of sleepiness that tended to be linear. In contrast, Puspasari et al (2019) found exponential patterns, particularly for drivers who did not receive enough sleep the night before.…”