The availability of sensor data from car black boxes as well as from the driver’s smartphone makes worth investigating how deep learning approaches can help in assessing the people skills when driving.
In this regard, the candidate will be in charge of reviewing the state of the art of deep learning algorithms applied to the driving style assessment, with a specific focus on time series. Moreover, the candidate is expected to design and develop experiments for the evaluation and comparison of different techniques, both on real and synthetic data.
The thesis will be developed at the Information Engineering Department of the “Università Politecnica delle Marche”.
Involed tools and technologies: Keras, TensorFlow, Google Colab, Python, and similar.