7. Clustering Driving Destinations Using a Modified DBSCAN Algorithm with Locally-Defined Map-Based Thresholds

The aim of this paper is to propose a method to cluster GPS data corresponding to driving destinations. A new DBSCAN-based algorithm is proposed to group stationary GPS traces, collected prior to end of trips, into destination clusters. While the original DBSCAN clustering algorithm uses a global threshold as a closeness measure in data space, we develop a method to set local thresholds values for data points; this is important because the GPS data proximity strongly depends on the density of the street grid around each point. Specifically, the spread of GPS coordinates in parking lots can vary substantially between narrow (personal parking lot) and wide (parking lot of a shopping mall) depending on the destinations. To characterize the parking lot diversities at each destination, we introduce the concept of using a local threshold value for each data point. The local threshold values are inferred from road graph density using a map database. Moreover, we propose a mutual reachability constraint to preserve the insensitivity of DBSCAN with respect to the ordering of the points. The performance of the proposed clustering algorithm has been evaluated extensively using trips of actual cars in Sweden, and some of the results are presented here.