Incremental Clustering Approach for Evolving Trajectory Data Stream

Trajectory data stream contain an enormous amount of data about spatial and temporal information of moving objects. Clustering the trajectory may bring benefits to several applications such as traffic monitoring system, behavior analysis of animal movement pattern, weather forecasting. In many real applications, trajectory data keep coming into the database or server for immediate analysis. Most existing approaches analyze the whole object trajectory from the static database rather than the current movement dynamic data. These methods cannot get a concise result because the objects always move then their position has changed over time. In this paper, we address the problem of monitoring the evolution of moving objects over time and propose incremental Sub-Trajectory Clustering based on Micro-group (iSTCM) framework to reduce computational time complexity. As an experiment, the performance of our proposed algorithm will conduct on real taxicab datasets and compare the efficiency and cluster quality as effectiveness with another state of the art methods.