Loading and Unloading Points Identification Based on Freight Trajectory Big Data and Clustering Method

Abstract

Based on the GPS trajectory data of a freight enterprise in Dalian, China, this paper studies the identification of loading and unloading points by a clustering algorithm. Firstly, by analysing the characteristics of freight loading and unloading behaviour, combined with the spatial and temporal distribution characteristics of truck GPS trajectory data, three characteristic variables of the number of trucks passing through a certain place, the average speed of trucks and the average stay time of trucks in the place are extracted. Then, the clustering algorithm and visual analysis are used to obtain the target cluster, and the POI language of the geographic information is obtained according to the points in the target cluster. The meaning information is crawled to accurately identify the result of the freight loading point. Finally, two classical clustering algorithms, K-means and GMM, are evaluated and compared. The results show that the identification method designed in this paper finally identifies 2,320 freight loading and unloading points from 11,406,000 trajectory data, which can realise the accurate extraction of freight loading and unloading points.