A Learning Algorithm for Localizing People Based on Wireless Signal Strength that Uses Labeled and Unlabeled Data

@inproceedings{Thrun2003ALA,
  title={A Learning Algorithm for Localizing People Based on Wireless Signal Strength that Uses Labeled and Unlabeled Data},
  author={Sebastian Thrun and Geoffrey J. Gordon and Frank Pfenning and Mary Koes and Brennan Sellner and Brad Lisien},
  booktitle={IJCAI},
  year={2003}
}
This paper summarizes a probabilistic approach for localizing people through the signal strengths of a wireless IEEE 802.11b network. Our approach uses data labeled by ground truth position to learn a probabilistic mapping from locations to wireless signals, represented by piecewise linear Gaussians. It then uses sequences of wireless signal data (without position labels) to acquire motion models of individual people, which further improves the localization accuracy. The approach has been… CONTINUE READING
Highly Cited
This paper has 28 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 21 extracted citations

A survey of problems and approaches in wireless-based indoor positioning

2016 International Conference on Indoor Positioning and Indoor Navigation (IPIN) • 2016
View 1 Excerpt

Implementation of particle filter for personal dynamic positioning based on ZigBee network

2010 3rd International Conference on Computer Science and Information Technology • 2010
View 1 Excerpt

RSSI localisation with sensors placed on the user

2010 International Conference on Indoor Positioning and Indoor Navigation • 2010
View 1 Excerpt

RSSI variability characterization and calibration method in wireless sensor network

The 2010 IEEE International Conference on Information and Automation • 2010
View 1 Excerpt

Sub-meter indoor localization in unmodified environments with inexpensive sensors

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems • 2010
View 1 Excerpt

Similar Papers

Loading similar papers…