| Resumo: | This study explores retrospective data from a driver monitoring system (DMS) to analyze the driving time until the occurrence of drowsiness among commercial drivers. The database includes 1,121 driving records (trips) obtained from fleet vehicles belonging to six different companies. The time to the first drowsiness alert emitted by the DMS was modeled using a hazard-based duration model with a Weibull distribution and random parameters, considering the effects of trip duration and company-specific dummy variables. The results show that the probability of occurrence of the first drowsiness event increases with time, although it increases at different rates from one company to another. Then, company effects, such as the activity sector and fleet management policies, may play an important role in the development of driver drowsiness.
|
|---|