Mining Trajectory Data and Identifying Patterns for Taxi Movement Trips

In past years, trajectory data generated from Automatic Identification System (AIS) networks and taxi GPS devices increased significantly. There is a high demand for analyzing this data and extracting the knowledge from it. Large-scale taxi trajectory data is represented by a sequence of timestamped geographical locations, this sequence starts with the origin point and ends with the destination point. Applying data mining techniques such as clustering on trajectory data can provide useful information about the movement patterns and the behavior of people. Thus, can enhance the transportation management services in terms of urban planning and environment issues. In this paper, we propose a methodology which extracts movement patterns of taxi trips in Porto, Portugal. we cluster taxi trips using Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) algorithm, each point in the trip is a pair of coordinates which consists of longitude and latitude values.