The article presents a study on improving speed predictions in Intelligent Transportation Systems (ITS) using sparse GPS data and topographical features. The researchers aimed to extract accurate traffic insights from areas with limited or no data coverage. They created a Temporally Orientated Speed Dictionary Centered on Topographically Clustered Roads and used it to train a machine learning model. The model predicts speed in regions where transportation data is lacking. The results showed improvement over new and standard regression methods, offering new strategies for missing data traffic analysis.
Publication date: 13 Feb 2024
Project Page: Not Provided
Paper: https://arxiv.org/pdf/2402.07507
