Predicting times of waiting on red signals using BERT
This work addresses traffic optimization problems, particularly for autonomous and connected vehicles, but is incremental as it applies an existing method (BERT) to a new domain-specific dataset.
The paper tackled predicting waiting times at red traffic signals using BERT-based models, achieving the best results compared to four other machine learning models across all metrics in experiments on a realistic road network dataset.
We present a method for approximating outcomes of road traffic simulations using BERT-based models, which may find applications in, e.g., optimizing traffic signal settings, especially with the presence of autonomous and connected vehicles. The experiments were conducted on a dataset generated using the Traffic Simulation Framework software runs on a realistic road network. The BERT-based models were compared with 4 other types of machine learning models (LightGBM, fully connected neural networks and 2 types of graph neural networks) and gave the best results in terms of all the considered metrics.