TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Gaussian mixture models for signal mapping and positioning

Tutkimustuotosvertaisarvioitu

Standard

Gaussian mixture models for signal mapping and positioning. / Raitoharju, M.; García-Fernández, F.; Hostettler, R.; Piché, R.; Särkkä, S.

julkaisussa: Signal Processing, Vuosikerta 168, 107330, 01.03.2020.

Tutkimustuotosvertaisarvioitu

Harvard

Raitoharju, M, García-Fernández, F, Hostettler, R, Piché, R & Särkkä, S 2020, 'Gaussian mixture models for signal mapping and positioning', Signal Processing, Vuosikerta. 168, 107330. https://doi.org/10.1016/j.sigpro.2019.107330

APA

Raitoharju, M., García-Fernández, F., Hostettler, R., Piché, R., & Särkkä, S. (2020). Gaussian mixture models for signal mapping and positioning. Signal Processing, 168, [107330]. https://doi.org/10.1016/j.sigpro.2019.107330

Vancouver

Raitoharju M, García-Fernández F, Hostettler R, Piché R, Särkkä S. Gaussian mixture models for signal mapping and positioning. Signal Processing. 2020 maalis 1;168. 107330. https://doi.org/10.1016/j.sigpro.2019.107330

Author

Raitoharju, M. ; García-Fernández, F. ; Hostettler, R. ; Piché, R. ; Särkkä, S. / Gaussian mixture models for signal mapping and positioning. Julkaisussa: Signal Processing. 2020 ; Vuosikerta 168.

Bibtex - Lataa

@article{15623d4355614a4cb1e44b0254f5f09f,
title = "Gaussian mixture models for signal mapping and positioning",
abstract = "Maps of RSS from a wireless transmitter can be used for positioning or for planning wireless infrastructure. The RSS values measured at a single point are not always the same, but follow some distribution, which vary from point to point. In existing approaches in the literature this variation is neglected or its mapping requires making many measurements at every point, which makes the measurement collection very laborious. We propose to use GMs for modeling joint distributions of the position and the RSS value. The proposed model is more versatile than methods found in the literature as it models the joint distribution of RSS measurements and the location space. This allows us to model the distributions of RSS values in every point of space without making many measurement in every point. In addition, GMs allow us to compute conditional probabilities and posteriors of position in closed form. The proposed models can model any RSS attenuation pattern, which is useful for positioning in multifloor buildings. Our tests with WLAN signals show that positioning with the proposed algorithm provides accurate position estimates. We conclude that the proposed algorithm can provide useful information about distributions of RSS values for different applications.",
keywords = "Gaussian mixtures, Indoor positioning, RSS, Signal mapping, Statistical modeling",
author = "M. Raitoharju and F. Garc{\'i}a-Fern{\'a}ndez and R. Hostettler and R. Pich{\'e} and S. S{\"a}rkk{\"a}",
year = "2020",
month = "3",
day = "1",
doi = "10.1016/j.sigpro.2019.107330",
language = "English",
volume = "168",
journal = "Signal Processing",
issn = "0165-1684",
publisher = "Elsevier",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Gaussian mixture models for signal mapping and positioning

AU - Raitoharju, M.

AU - García-Fernández, F.

AU - Hostettler, R.

AU - Piché, R.

AU - Särkkä, S.

PY - 2020/3/1

Y1 - 2020/3/1

N2 - Maps of RSS from a wireless transmitter can be used for positioning or for planning wireless infrastructure. The RSS values measured at a single point are not always the same, but follow some distribution, which vary from point to point. In existing approaches in the literature this variation is neglected or its mapping requires making many measurements at every point, which makes the measurement collection very laborious. We propose to use GMs for modeling joint distributions of the position and the RSS value. The proposed model is more versatile than methods found in the literature as it models the joint distribution of RSS measurements and the location space. This allows us to model the distributions of RSS values in every point of space without making many measurement in every point. In addition, GMs allow us to compute conditional probabilities and posteriors of position in closed form. The proposed models can model any RSS attenuation pattern, which is useful for positioning in multifloor buildings. Our tests with WLAN signals show that positioning with the proposed algorithm provides accurate position estimates. We conclude that the proposed algorithm can provide useful information about distributions of RSS values for different applications.

AB - Maps of RSS from a wireless transmitter can be used for positioning or for planning wireless infrastructure. The RSS values measured at a single point are not always the same, but follow some distribution, which vary from point to point. In existing approaches in the literature this variation is neglected or its mapping requires making many measurements at every point, which makes the measurement collection very laborious. We propose to use GMs for modeling joint distributions of the position and the RSS value. The proposed model is more versatile than methods found in the literature as it models the joint distribution of RSS measurements and the location space. This allows us to model the distributions of RSS values in every point of space without making many measurement in every point. In addition, GMs allow us to compute conditional probabilities and posteriors of position in closed form. The proposed models can model any RSS attenuation pattern, which is useful for positioning in multifloor buildings. Our tests with WLAN signals show that positioning with the proposed algorithm provides accurate position estimates. We conclude that the proposed algorithm can provide useful information about distributions of RSS values for different applications.

KW - Gaussian mixtures

KW - Indoor positioning

KW - RSS

KW - Signal mapping

KW - Statistical modeling

U2 - 10.1016/j.sigpro.2019.107330

DO - 10.1016/j.sigpro.2019.107330

M3 - Article

VL - 168

JO - Signal Processing

JF - Signal Processing

SN - 0165-1684

M1 - 107330

ER -