Improving indoor localization with social interactions

Junghyun Jun, Long Cheng, Jun Sun, Yu Gu, Ting Zhu, Tian He

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

In this paper, we propose Social-Loc, which uniquely uti- lizes social interactions in addition to common on-board sen- sors such as accelerometer and gyroscope on modern smart- phones, to localize indoor mobile users. Specifically, Social- Loc takes the potential locations for individual users esti- mated by a novel particle filter tailored for indoor localiza- tion as input, and exploits both social encounter and non- encounter events to further improve the localization accu- racy. We have implemented Social-Loc on the Android plat- form and extensively evaluated its performance. The simula- tion results demonstrate that Social-Loc improves the accu- racy of the particle-filter-only scheme by as much as 560% on average and is able to achieve accuracy of few meters without any external ranging device or system training.

Original languageEnglish (US)
Title of host publicationSenSys 2012 - Proceedings of the 10th ACM Conference on Embedded Networked Sensor Systems
Pages323-324
Number of pages2
DOIs
StatePublished - 2012
Event10th ACM Conference on Embedded Networked Sensor Systems, SenSys 2012 - Toronto, ON, Canada
Duration: Nov 6 2012Nov 9 2012

Publication series

NameSenSys 2012 - Proceedings of the 10th ACM Conference on Embedded Networked Sensor Systems

Other

Other10th ACM Conference on Embedded Networked Sensor Systems, SenSys 2012
Country/TerritoryCanada
CityToronto, ON
Period11/6/1211/9/12

Keywords

  • Indoor localization
  • Mobile system
  • Pedestrian localization
  • Social in- teraction

Fingerprint

Dive into the research topics of 'Improving indoor localization with social interactions'. Together they form a unique fingerprint.

Cite this