Drivers overloaded with information significantly increase the chance of vehicle collisions. However, few existing computational models are able to simulate human performance and mental workload at the same time. We propose a new computational modeling approach—a queuing network approach based on queuing network theory of human performance (Liu, 1996, 1997) and neuroscience discoveries. This modeling approach is composed of a simulation model of a queuing network architecture and a set of mathematical equations implemented in the simulation model to quantify mental workload. It not only successfully models the mental workload measured by the six workload scales in NASA-TLX in terms of subnetwork utilization, but also simulates driving performance, reflecting mental workload from both subjective and performance-based measurements. In addition, this modeling approach allows us to visualize mental workload in driving in real-time. Further usage and implementation of the model in designing intelligent and adaptive in-vehicle systems are discussed.
Mendeley saves you time finding and organizing research
Choose a citation style from the tabs below