Road Type Classification of Driving Data Using Neural Networks

Road classification, knowing whether we are driving in the city, in rural areas, or on the highway, can improve the performance of modern driver assistance systems and contribute to understanding driving habits. This study focuses on solving this problem universally using only vehicle speed data. A data logging method has been developed to assign labels to the On-board Diagnostics data. Preprocessing methods have been introduced to solve different time steps and driving lengths. A state-of-the-art conventional method was implemented as a benchmark, achieving 89.9% accuracy on our dataset. Our proposed method is a neural network-based model with an accuracy of 93% and 1.8% Type I error. As the misclassifications are not symmetric in this problem, loss function weighting has been introduced. However, this technique reduced the accuracy, so cross-validation was used to use as much data as possible during the training. Combining the two approaches resulted in a model with an accuracy of 96.21% and unwanted Type I misclassifications below 1%.