Scalable Processing and Mining of Big Mobility Data

Spatial-temporal trajectory data contains rich information about moving objects and has been widely used for a large number of real-world applications. However, the complexity of spatial-temporal trajectory data, on the one hand, and the fast collection of datasets, on the other hand, has made it challenging to efficiently store, process, and query such data. In this thesis, we proposed two scalable methods to analyze big mobility data in the in-memory cluster computing environment. Particularly, we have extended Apache Spark with efficient trajectory indexing, partitioning and querying functionalities to support trajectory data analytics. We proposed distributed methods to the important problems of sub-trajectory similarity search and vessel trajectory annotation.