Abstract
ObjectivesApproximately 20~30% of all traffic accidents are caused by fatigue driving. However, limited practicability remains a barrier for the real application of available techniques to detect driving fatigue. Use of pupillary light reflex (PLR) may be potentially effective for driving fatigue detection.MethodsA 90 min monotonous simulated driving task was utilized to induce driving fatigue. During the task, PLR measurements were performed at baseline and at an interval of 30 min. Subjective rating scales, heart rate variability (HRV) were monitored simultaneously.ResultsThirty-two healthy volunteers in China participated in our study. Based on the results of subjective evaluation and behavioral performances, driving fatigue was verified to be successfully induced by a simulated driving task. Significant variations of PLR and HRV parameters were observed, which also showed significant relevance with the change in Karolinska Sleepiness Scale at several timepoints (|r| = 0.55 ~ 0.72, P < 0.001). Furthermore, PLR variations had excellent ability to detect driving fatigue with high sensitivity and specificity, of which maximum constriction velocity variations achieved a sensitivity of 85.00% and specificity of 72.34% for driving fatigue detection, vs. 82.50 and 78.72% with a combination of HRV variations, a nonsignificant difference (AUC = 0.835, 0.872, P > 0.05).ConclusionsPupillary light reflex variation may be a potential indicator in the detection of driving fatigue, achieving a comparative performance compared with the combination with heart rate variability. Further work may be involved in developing a commercialized driving fatigue detection system based on pupillary parameters.
Highlights
Road traffic accidents has become the eighth leading cause of death worldwide [1]
Compared to the beginning of the experiment, we found significantly higher fatigue scores after the experiment [Karolinska Sleepiness Scale (KSS): T0: 3 [2,3,4], T1: 5 [4,5,6] a, T2: 6 (5.25–7) ab vs. T3: 7 [6,7,8] ab, P < 0.001; Fatigue Grade (FG) scale: T0: 0, T1: 0 (0–1) a, T2: 2 (1.25–3) a vs. T3: 3 (2.25–4) abc, P < 0.001]
The mean power of heart rate variability (HRV) in normalization of LF power by the formula (LFnu) and low frequency (LF)/high frequency (HF) significantly increased in a linear fashion [LFnu: T0: 51.96 ± 16.25 μV2, T1: 61.63 ± 17.51 μV2a, T2: 68.58 ± 19.24 μV2ab vs. T3: 72.12 ± 18.16 μV2abc; LF/HF: T0: 1.23 (0.68– 1.70), T1: 1.91 (0.97–3.19) a, T2: 2.63 (1.06–4.66) a vs. T3: 3.29 (1.49–7.57) ab; both P < 0.001, Figures 2B,C], while there was a mild decline in the mean power of HRV in normalization of HF power by the formula (HFnu), from T0: 44.99 (37.06–59.92) μV2, T1: 35.68 (23.81–51.24) μV2, T2: 29.05 (16.24–49.71) μV2a to T3: 22.94 (11.46–44.15) μV2a (P < 0.001, see Figure 2D)
Summary
Road traffic accidents has become the eighth leading cause of death worldwide [1]. They killed nearly 1.35 million people every year, and caused up to 50 million injuries [1], resulting in huge losses for societies with regard to population health and economic matters. Continuous efforts have been made to develop reliable indicators of driving fatigue to warn drivers of their fatigue status promptly and preventing possible accidents from occurring [4,5,6,7,8,9,10] Among these exploratory studies, the detection systems incorporating physiological signals of drivers, which mainly involves extracting and analyzing characteristics of electroencephalogram (EEG) [6, 11,12,13], heart rate variability (HRV) [5, 14, 15], electromyogram (EMG) [7, 16], etc., are considered as the most accurate and reliable ones to reflect the mental states. No study has been conducted to analyze the association between PLR variations with driving fatigue
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
