Estimation of driver´s mental workload using visual information and heart rate variability

Most of the traffic accidents have been caused by driver´s inattention. Therefore, driver monitoring is one of the most important challenges in order to prevent traffic accidents. Some studies for evaluating mental workload during driving have been reported; however driver´s mental state should be estimated quantitatively for the future. This paper proposes an estimation method of driver´s mental workload using physiological information. We defined mental workload as NASA-TLX score, and used the multiple linear regression to quantify driver´s mental workload. As a result, higher accuracy was achieved by considering driver´s aggression.