Predicting drowsy driving in real-time situations: Using an advanced driving simulator, accelerated failure time model, and virtual location-based services

摘要: This paper aims to both identify the factors affecting driver drowsiness and develop a real-time drowsy driving probability model based on virtual Location-Based Services (LBS) data obtained using simulator. A simulation experiment was designed conducted 32 participant drivers. Collected included continuous time before detection of LBS related temperature, day, lane width, average travel speed, in heavy traffic, different roadway types. Demographic information, such as nap habit, age, gender, experience also collected through questionnaires distributed participants. An Accelerated Failure Time (AFT) developed estimate drowsiness. The results AFT showed longer during day than at night, lower temperatures. Additionally, drivers who identified having habit were more vulnerable Generally, higher speeds correlated risk driving, periods low-speed traffic jam conditions. Considering road types, felt quickly freeways compared other facilities. proposed provides better understanding how is influenced by environmental demographic factors. can be used provide for LBS-based warning system, improving past methods only fixed driving.