Fatigue-related crashes are a persistent road safety problem. Advances in technology have permitted the development and fitment of continuous driver fatigue monitoring systems in vehicles. Using driver monitoring system data, this paper presents an evaluation of the impact of real-time feedback on the incidence of fatigue events in three long-haul trucking companies in South Africa. Fatigue events were defined as micro sleeps or prolonged eyelid closure events and verified in real-time by a dedicated monitoring centre. Forty-nine trucks were observed over a five-month period. The observation period included a ‘baseline’ where data were logged but no alerts were provided to the driver, and an ‘intervention’ period where alarms were provided to both the driver and the employer in real-time. Poisson regression analysis was used to examine the difference in the incidence of fatigue events in the intervention period relative to the baseline period. Analysis demonstrates that the rate at which fatigue events occurred during the intervention period was significantly lower than in the baseline period, adjusted for number of operating days, time spent in vehicle moving and distance travelled. The implications and feedback mechanisms in the context of broader safety management are discussed. (Author/publisher)
Abstract