Trajectory Analytics: Indexing, Mining, and Applications to Network Optimization

1. MOTIVATION The last decade has witnessed an unprecedented growth in the availability of devices equipped with location-tracking sensors. Examples of such devices include cellphones, in-car navigation systems and weather monitoring gadgets. The widespread usage of these devices has resulted in an abundance of data that are in the form of trajectories. Querying and mining these trajectories is critical to extract the knowledge hidden in the raw datasets and to design intelligent spatio-temporal data management systems. For example, in cellular network analytics, cellphone service providers are interested in identifying “bottleneck” regions that affect a high volume of trajectories due to poor coverage [15]. In zoology, tracking movements of animals is critical to understand their flocking behaviors [8] and migratory patterns [1]. Meteorologists are interested in analyzing trajectories of wildfires and tornadoes to identify “alleys” that are conducive to these environmental disasters [13]. For efficient traffic management, governmental agencies are interested in understanding how congestions spread across a road network so that infrastructure developments can be prioritized in an appropriate manner. In this tutorial, we will survey the rich area of trajectory analytics, which offers solutions to the above problems. Additionally, we will analyze the pros and cons of existing techniques and outline challenges that remain to be solved. Broadly, in this tutorial, we will focus on three different aspects of trajectory analytics: matching and indexing trajectories, mining patterns from trajectories, and their applications on cellular network optimization.