TU Berlin

Service-centric NetworkingArbuzin, D. (2017). Real-time detection of moving crowds using spatio-temporal data streams. Master Thesis, Technische Universität Berlin


zur Navigation

Es gibt keine deutsche Übersetzung dieser Webseite.

Master Thesis: Real-time detection of moving crowds using spatio-temporal data streams

Title:  Real-time detection of moving crowds using spatio-temporal data streams


Over the last decade we have seen a tremendous change in Location Based Services. From  primitive reactive applications, explicitly invoked by users, they have evolved into modern  complex proactive systems, that are able to automatically provide information based on context and user location. This was caused by the rapid development of outdoor and indoor positioning technologies. GPS modules, which are now included almost into every device, together  with indoor technologies, based on WiFi fingerprinting or Bluetooth beacons, allow to determine the user location almost everywhere and at any time. This also led to an enormous growth  of spatio-temporal data.  Being very efficient using user-centric approach for a single target current Location Based  Services remain quite primitive in the area of a multitarget knowledge extraction. This is rather  surprising, taking into consideration the data availability and current processing technologies.  Discovering useful information from the location of multiple objects is from one side limited by  legal issues related to privacy and data ownership. From the other side, mining group location  data over time is not a trivial task and require special algorithms and technologies in order to  be effective.  Recent development in data processing area has led to a huge shift from batch processing  offline engines, like MapReduce, to real-time distributed streaming frameworks, like Apache  Flink or Apache Spark, which are able to process huge amounts of data, including spatiotemporal datastreams.  This thesis presents a system for detecting and analyzing crowds in a continuous spatiotemporal data stream. The aim of the system is to provide relevant knowledge in terms of  proactive LBS. The motivation comes from the fact of constant spatio-temporal data growth  and recent rapid technological development to process such data.

Supervisor: Bersant Deva

Type:  Master Thesis

Duration: 4 months



Schnellnavigation zur Seite über Nummerneingabe