Predicting drowsy driving in real-time situations: Using an advanced driving simulator, accelerated failure time model, and virtual location-based services
Traditional drowsy driving warning systems use a fixed driving duration to alert drivers. Past studies have failed to fully explore the factors influencing drowsy driving time. This study investigates the impact of demographic and environmental factors on drowsy driving. The real-time prediction model included data collected using Location-based Services (LBS). The Accelerated Failure Time outperformed the General Log-Linear Model in goodness-of-fit.