Analyse semantisch annotierter Trajektorien

The analysis of movement data has attracted much interest over at least the last two decades. This is mainly due to the prevalence of GPS trackers and mobile devices, which resulted in a high amount of collected data. In order to study movement behavior, it is important to consider all factors that may have influenced the behavior of the object or person under consideration. Movement data is usually stored as so-called trajectories. If we enrich the trajectories by considering the context in which it was produced, we call them semantic trajectories. Typically, the analysis of trajectories is based on spatial characteristics only, which excludes existing information. Instead, this work focuses on the analysis of semantic trajectories. Hence, we propose a new model based on an extended finite state machine, which allows the representation of all properties of the given trajectories. With this new model, we consider two main steps in trajectory analysis: First, we aim to infer a semantically enriched representative trajectory for a given cluster of trajectories. Second, we introduce a variation of the well-known k-means algorithm to calculate a clustering based on the given context of the trajectories. To show semantic feasability of our approach, we conclude this work by evaluating two different contexts for trajectories in collaboration with domain experts.