HMIAN: A Hierarchical Mapping and Interactive Attention Data Fusion Network for Traffic Forecasting

With the development of intelligent transportation system (ITS), vital technology ITS, short-term traffic forecasting, gains increasing attention. However, existing prediction models ignore impact urban functional zones (FZs) on data, resulting in inaccurate extractions dynamic spatial relationships from network. Furthermore, how to calculate influence external factors, such as weather and holidays is an unsolved problem. This article proposes a spatio-temporal hierarchical mapping interactive attention network (HMIAN), which extracts features by constructing FZs, designs effective factors fusion method. HMIAN uses structure aggregate roads into interaction between FZs feed this information back features. And mechanism utilized fuse data with effectively, temporal In addition, some experiments were carried out three real sets. First, experiment results show better performance proposed model compared other methods complex Second, longitudinal comparison verifies that extracting road Finally, different are compared, provides consult for subsequent research factors.