Driver Identification Based on Hidden Feature Extraction by Using Deep Learning

The rapid development of intelligent transportation and Internet of Vehicles technology provides a technical means for obtaining massive, real-time, and multi-dimensional driving behavior data. It can be used to evaluate the driving habits, we can even distinguish drivers by analyzing driving behavior, which can be used in vehicle anti-theft systems. Existing driver identification models use complicated artificial feature extraction, and it is difficult to achieve good performance. We propose a data-driven, end-to-end driver identification model based on improved convolutional neural network. The cross-validation results from the naturalistic driving dataset indicate the superiority of our model.