Detection of dynamic activity patterns at a collective level from large-volume trajectory data

Abstract

Recent developments in pervasive location acquisition technologies provide the technical support for massive collection of trajectory data. Activity locations identified from trajectory data can be used to evaluate space–time activity patterns. However, the studies that explore activity patterns at collective levels often fail to address the temporal aspect. The traditional spatial statistics, which are commonly used for spatial pattern analysis, are limited in describing space–time interactions. This paper proposes a method to detect the dynamics of space–time development of urban activity patterns that are embedded in large volume trajectory data. Taxi cabs’ trajectory data in the city of San Francisco were analyzed to identify activity instances, activity hot spots, and space–time dynamics of activity hot spots. The urban activity hot spots, evolving through different stages and across the city, provide a comprehensive depiction of the space–time activity patterns in the urban landscape. The dynamic patterns of the activity hot spots can be used to retrieve historical events and to predict future activity hot spots, which may be valuable for transportation and public safety management.