Identification and Correlation Analysis of Critical Intersections in Urban Road Networks Based on Vehicle Trajectory Data

To achieve the coordinated control of multiple intersections in a large-scale urban road network, we needed a method to study critical intersections' global correlation characteristics. First, the Real-coded Accelerating Genetic Algorithm Projection Pursuit Classification (RAGA-PPC) was used to solve and evaluate the critical degree of intersections. Second, the k-means clustering algorithm was applied to intersections critical degree to divide the critical intersections and non-critical intersections. Third, a new approach of calculating the critical intersections' correlation degree based on the improved FP-Growth algorithm, which can mine frequent itemsets of intersections from vehicle trajectories, was applied to analyze the global correlation characteristics of the selected critical intersection. Finally, Didi GAIA Dataset was selected for critical intersections identification and correlation analysis. The experimental results show that the correlation between critical intersections tends to decrease with global distance and varies with time.