Efficient Discovery of Traveling Companion from Evolving Trajectory Data Stream

Abstract

Trajectory data stream contain an enormous amount of data about spatial and temporal information of moving objects. Discovering useful pattern from moving objects can convey valuable knowledge to a variety applications such as transportation management, military surveillance, and weather forecasting by analyzing animal movement behaviors. In many real applications, trajectory data keep coming into the database or server for immediate analysis. Most moving objects' pattern discovery approaches analyze the data by re-computing from scratch. Now, existing some group pattern approaches incrementally illuminate this problem. However, there was still high computational time complexity to the efficient and accurate discovery of traveling together moving objects(i.e., traveling companion) from evolving data streams. In this paper, we propose micro-group based clustering algorithm over evolving data stream to reduce computational time complexity. Experiments of this proposed system will conduct on real taxi trajectory data and synthetic data.