PROJECT TITLE :

MPiLoc: Self-Calibrating Multi-Floor Indoor Localization Exploiting Participatory Sensing - 2018

ABSTRACT:

Whereas location is one of the most important context info in mobile and pervasive computing, giant-scale deployment of indoor localization system remains elusive. During this work, we have a tendency to propose MPiLoc, a multi-floor indoor localization system that utilizes information contributed by smartphone users through participatory sensing for automatic floor set up and radio map construction. Our system does not require manual calibration, prior information, or infrastructure support. The key novelty of MPiLoc is that it clusters and merges walking trajectories annotated with sensor and signal strengths to derive a map of walking methods annotated with radio signal strengths in multi-floor indoor environments. We tend to evaluate MPiLoc over 5 different indoor areas. Evaluation shows that our system can derive indoor maps for various indoor environments in multi-floor settings and achieve a median localization error of one.82 m.