Flock Patterns and Context

The wide deployment of location detection devices (for example, smartphones) leads to collecting of large datasets in the form of trajectories. There are a whole set of papers devoted to trajectory-based queries. Mostly, they are concentrated on similarity queries. In the same time, there is a constantly groving interest in getting various forms for aggregating behavior of trajectories as groups. The typical task, for example, is find all groups of moving objects that move together. For example, we can find convoys of vehicles, groups of people, etc. In this paper we discuss the task of flocks discovery for context-aware applications, where location data could be replaced by proximity information. We propose a framework and several strategies to discover such patterns in streaming context-related data. Our experiments with real datasets show that the proposed algorithms are scalable and efficient.