Evaluating the Influence of Ambient State of a Car on the Cognitive Distracted State of the Driver

To evaluate a car driver's cognitive distraction while driving, the influence of the ambient state of the car is evaluated. In this paper, Support Vector Machines and Random Forests, which are representative machine learning models, are applied to evaluate the cognitive distracted state. As an input data to the machine learning model, in addition to driver biometric information and driving information, ambient information of the car is used. In this study, the ambient information of the car is that of the preceding car and the shape of the road. Experiments using a car driving simulator are then conducted to evaluate the effectiveness of using ambient information of that car.