Extracting Coach Schedule Information from Massive Trajectory Data

Abstract

In view of the difficulties in obtaining nationwide coach schedules, we propose a method of automatically extracting schedule information from massive trajectory data of coaches. We used the Density-Based Spatial Clustering of Applications with Noise algorithm to identify locations of coach stations from the long time-series of historical trajectories, use the application programming interface of online maps to extract station names, and finally extract coach schedules based on multiple trajectories. Experimental results in the Jing-Jin-Ji area validate the effectiveness and accuracy of the proposed method. This method can be used to obtain nationwide coach schedule information in a fast and low cost way.