User trajectories contain a wealth of implicit information. The places that people visit, provide us with information about their preferences and needs. Furthermore, it provides us with information about the popularity of places, for example at which time of the year or day these places are frequently visited. The potential for behavioral analysis of trajectories is widely discussed in literature, but all of these methods need a pre-processing step: the geometric trajectory data needs to be transformed into a semantic collection or sequence of visited points-of-interest that is more suitable for data mining. Especially indoor activities in urban areas are challenging to detect from raw trajectory data. In this paper, we propose a new algorithm for the automated detection of visited points-of-interest. This algorithm extracts the actual visited points-of-interest well, both in terms of precision and recall, even for the challenging urban indoor activity detection. We demonstrate the strength of the algorithm by comparing it to three existing and widely used algorithms, using annotated trajectory data, collected through an experiment with students in the city of Hengelo, The Netherlands. Our algorithm, which combines multiple trajectory pre-processing techniques from existing work with several novel ones, shows significant improvements.

Trajectories of people contain a vast amount of information on users' interests and popularity of locations. To obtain this information, the places visited by the owner of the device on such a trajectory need to be recognized. However, the location information on a point of interest (POI) in a database is normally limited to an address and a coordinate pair, rather than a polygon describing its boundaries. A region of interest can be used to intersect trajectories to match trajectories with objects of interest. In the absence of expensive and often not publicly available detailed spatial data like cadastral data, we need to approximate this ROI. In this paper, we present several approaches to approximate the size and shape of ROIs, by integrating data from multiple public sources, a validation technique, and a validation of these approaches against the cadastral data of the city of Enschede, The Netherlands.

The usage of social networks sites (SNSs), such as Facebook, and geosocial networks (GSNs), such as Foursquare, has increased tremendously over the past years. The willingness of users to share their current locations and experiences facilitate the creation of geographical recommender systems based on user generated content (UGC). This idea has been used to create a substantial amount of geosocial recommender systems (GRSs), such as Gogobot, TripIt, and Trippy already, but can be applied to more complex scenarios, such as the recommendation of products with a strong binding to their region, such as real estate or vacation destinations.This extended form of GRS development requires advanced functionality for information collection (from the web, other social media and sensors), information enrichment (such as data quality assessment and advanced data analysis), and personalized recommendations. The creation of a toolset to cope with these challenges is the goal of this research project, for which the outline is presented in this paper.

Abstract. Trajectories have been providing us with a wealth of derived information such as traffic conditions and road network updates. This work focuses on deriving user profiles through spatiotemporal analysis of trajectory data to provide insight into the quality of information provided by users. The presented behavior profiling method assesses user participation characteristics in a treasurehunt type event. Consisting of an analysis and a profiling phase, analysis involves a timeline and a stay-point analysis, as well as a semantic trajectory inspection relating actual and expected paths. The analysis results are then grouped around profiles that can be used to estimate the user performance in the activity. The proposed profiling method is evaluated by means of a student orientation treasurehunt activity at the University of Twente, The Netherlands. The profiling method is used to predict the students' gaming behavior by means of a simple team type classification, and a feature-based answer type classification.