A new approach to detecting distracted car drivers using eye-movement data

In our study, we generate new rules for determining whether or not a driver is distracted, using collected data about the driver´s eye movement and driving data by learning as a new approach to detecting distracted car drivers. We use a learning tool, namely a support vector machine (SVM), to generate the rules. In addition, we focused on a qualitative model of a driver´s cognitive mental load in a prior study and investigated the relationship between this model and the driver´s distraction. In the investigation, we verify driver´s eye movements and driving data that are inconsistent with the model.