Recursive Gaussian Processes and Fingerprinting for Indoor Navigation

Tales Imbiriba; Peng Wu; Gerald Lamountain; Deniz Erdogmus; Pau Closas

doi:10.1109/PLANS46316.2020.9110187

Recursive Gaussian Processes and Fingerprinting for Indoor Navigation

Tales Imbiriba
, Peng Wu
, Gerald Lamountain
, Deniz Erdogmus
, Pau Closas

Computer Science

College of Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper investigates the use of Gaussian Processes (GP) for RSS fingerprinting-based navigation. In particular, a recursive GP scheme to adapt the fingerprints as they evolve over time is discussed which accounts for the uncertainty of position labels associated to new RSS measurements. The marginalization over the uncertainty of position labels is here implemented numerically through cubature rules, which is seen from computer simulations to enhance field estimation performance and, ultimately, positioning results.

Original language	English
Title of host publication	2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	933-940
Number of pages	8
ISBN (Electronic)	9781728102443
DOIs	https://doi.org/10.1109/PLANS46316.2020.9110187
State	Published - Apr 2020
Event	2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020 - Portland, United States Duration: Apr 20 2020 → Apr 23 2020

Publication series

Name	2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020

Conference

Conference	2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020
Country/Territory	United States
City	Portland
Period	4/20/20 → 4/23/20

ASJC Scopus Subject Areas

Signal Processing
Aerospace Engineering
Control and Optimization
Instrumentation

Keywords

fingerprinting
Gaussian Processes
geospatial sensing
Indoor navigation
uncertainty propagation

Access to Document

10.1109/PLANS46316.2020.9110187

Cite this

Imbiriba, T., Wu, P., Lamountain, G., Erdogmus, D., & Closas, P. (2020). Recursive Gaussian Processes and Fingerprinting for Indoor Navigation. In 2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020 (pp. 933-940). Article 9110187 (2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PLANS46316.2020.9110187

Recursive Gaussian Processes and Fingerprinting for Indoor Navigation. / Imbiriba, Tales; Wu, Peng; Lamountain, Gerald et al.
2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 933-940 9110187 (2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Imbiriba, T, Wu, P, Lamountain, G, Erdogmus, D & Closas, P 2020, Recursive Gaussian Processes and Fingerprinting for Indoor Navigation. in 2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020., 9110187, 2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020, Institute of Electrical and Electronics Engineers Inc., pp. 933-940, 2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020, Portland, United States, 4/20/20. https://doi.org/10.1109/PLANS46316.2020.9110187

Imbiriba T, Wu P, Lamountain G, Erdogmus D, Closas P. Recursive Gaussian Processes and Fingerprinting for Indoor Navigation. In 2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 933-940. 9110187. (2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020). doi: 10.1109/PLANS46316.2020.9110187

@inproceedings{8450e1812aec46c9bbf88e579cb95abc,

title = "Recursive Gaussian Processes and Fingerprinting for Indoor Navigation",

abstract = "This paper investigates the use of Gaussian Processes (GP) for RSS fingerprinting-based navigation. In particular, a recursive GP scheme to adapt the fingerprints as they evolve over time is discussed which accounts for the uncertainty of position labels associated to new RSS measurements. The marginalization over the uncertainty of position labels is here implemented numerically through cubature rules, which is seen from computer simulations to enhance field estimation performance and, ultimately, positioning results.",

keywords = "fingerprinting, Gaussian Processes, geospatial sensing, Indoor navigation, uncertainty propagation",

author = "Tales Imbiriba and Peng Wu and Gerald Lamountain and Deniz Erdogmus and Pau Closas",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020 ; Conference date: 20-04-2020 Through 23-04-2020",

year = "2020",

month = apr,

doi = "10.1109/PLANS46316.2020.9110187",

language = "English",

series = "2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "933--940",

booktitle = "2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020",

}

TY - GEN

T1 - Recursive Gaussian Processes and Fingerprinting for Indoor Navigation

AU - Imbiriba, Tales

AU - Wu, Peng

AU - Lamountain, Gerald

AU - Erdogmus, Deniz

AU - Closas, Pau

PY - 2020/4

Y1 - 2020/4

N2 - This paper investigates the use of Gaussian Processes (GP) for RSS fingerprinting-based navigation. In particular, a recursive GP scheme to adapt the fingerprints as they evolve over time is discussed which accounts for the uncertainty of position labels associated to new RSS measurements. The marginalization over the uncertainty of position labels is here implemented numerically through cubature rules, which is seen from computer simulations to enhance field estimation performance and, ultimately, positioning results.

AB - This paper investigates the use of Gaussian Processes (GP) for RSS fingerprinting-based navigation. In particular, a recursive GP scheme to adapt the fingerprints as they evolve over time is discussed which accounts for the uncertainty of position labels associated to new RSS measurements. The marginalization over the uncertainty of position labels is here implemented numerically through cubature rules, which is seen from computer simulations to enhance field estimation performance and, ultimately, positioning results.

KW - fingerprinting

KW - Gaussian Processes

KW - geospatial sensing

KW - Indoor navigation

KW - uncertainty propagation

UR - https://www.scopus.com/pages/publications/85087068522

UR - https://www.scopus.com/pages/publications/85087068522#tab=citedBy

U2 - 10.1109/PLANS46316.2020.9110187

DO - 10.1109/PLANS46316.2020.9110187

M3 - Conference contribution

AN - SCOPUS:85087068522

T3 - 2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020

SP - 933

EP - 940

BT - 2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE/ION Position, Location and Navigation Symposium, PLANS 2020

Y2 - 20 April 2020 through 23 April 2020

ER -

Recursive Gaussian Processes and Fingerprinting for Indoor Navigation

Abstract

Publication series

Conference

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this