Agata Brajdic (alumni)
User ID:ab818
Position:PhD Approved
E-mail:ab818@cam.ac.uk
College:Trinity
Overview and Interests

My main research interests deal with challenges associated with indoor pedestrian positioning using inertial smartphone sensors. 

In particular, I'm looking into algorithms and techniques to perform:

  • A step-and-heading dead-reckoning system for unconstrained smartphones (analysis of various pedometry solutions)
  • Cloud based solutions for scalable remote location computation based on a particle filter parallelised for GPU (CUDA) architectures
  • Power footprint and the energy consumption of the inertial localisation on smartphones, and energy optimisation
Publications

1. Agata Brajdic, Robert Harle, "Walk detection and step counting on unconstrained smartphones," Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing, UbiComp 2013, Sep 2013

2. Agata Brajdic, Robert Harle, "Scalable indoor pedestrian localisation using inertial sensing and parallel particle filters," International Conference on Indoor Positioning and Indoor Navigation (IPIN), 2012, Nov 2012

3. Agata Brajdic, Robert Harle, "Particle filtering on GPU for indoor pedestrian localisation," International Conference on Pervasive Computing 2011, Jun 2011