Tampere University of Technology

TUTCRIS Research Portal

Clustering benefits in mobile-centric WiFi positioning in multi-floor buildings

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Standard

Clustering benefits in mobile-centric WiFi positioning in multi-floor buildings. / Cramariuc, Andrei; Huttunen, Heikki; Lohan, Elena-Simona.

2016 International Conference on Localization and GNSS (ICL-GNSS). IEEE, 2016.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Cramariuc, A, Huttunen, H & Lohan, E-S 2016, Clustering benefits in mobile-centric WiFi positioning in multi-floor buildings. in 2016 International Conference on Localization and GNSS (ICL-GNSS). IEEE, International Conference on Localization and GNSS, 1/01/00. https://doi.org/10.1109/ICL-GNSS.2016.7533846

APA

Vancouver

Author

Cramariuc, Andrei ; Huttunen, Heikki ; Lohan, Elena-Simona. / Clustering benefits in mobile-centric WiFi positioning in multi-floor buildings. 2016 International Conference on Localization and GNSS (ICL-GNSS). IEEE, 2016.

Bibtex - Download

@inproceedings{c380532137b44e019cb677b2ba7c5280,
title = "Clustering benefits in mobile-centric WiFi positioning in multi-floor buildings",
abstract = "In mobile-centric indoor positioning, having a small databases to transfer from the network side to the mobile is of utmost importance. For scalable and low-complexity solutions, various clustering algorithms have been suggested in the literature, either in coordinates or 3D dimension or in the Access Points or Received Signal Strength (RSS) dimension. Typically, the two dimensions were investigated separately. This paper offers a comparative analysis between different clustering methods, together with a novel metric, called the Penalized Logarithmic Gaussian Distance metric which can boost the performance of the clustering. The results are compared based on real-field measurement data in two different multi-floor buildings and they are given in terms of estimation errors, floor detection probabilities and complexity. It is shown that the proposed metric enhances the performance of both 3D and RSS clustering and that the RSS clustering has lower complexity but worse performance than the 3D clustering. We are also providing in open-access the measurement data together with the Python-based implementation of the algorithms to serve as future benchmarks for indoor positioning studies.",
author = "Andrei Cramariuc and Heikki Huttunen and Elena-Simona Lohan",
year = "2016",
doi = "10.1109/ICL-GNSS.2016.7533846",
language = "English",
isbn = "978-1-5090-1757-7",
publisher = "IEEE",
booktitle = "2016 International Conference on Localization and GNSS (ICL-GNSS)",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - Clustering benefits in mobile-centric WiFi positioning in multi-floor buildings

AU - Cramariuc, Andrei

AU - Huttunen, Heikki

AU - Lohan, Elena-Simona

PY - 2016

Y1 - 2016

N2 - In mobile-centric indoor positioning, having a small databases to transfer from the network side to the mobile is of utmost importance. For scalable and low-complexity solutions, various clustering algorithms have been suggested in the literature, either in coordinates or 3D dimension or in the Access Points or Received Signal Strength (RSS) dimension. Typically, the two dimensions were investigated separately. This paper offers a comparative analysis between different clustering methods, together with a novel metric, called the Penalized Logarithmic Gaussian Distance metric which can boost the performance of the clustering. The results are compared based on real-field measurement data in two different multi-floor buildings and they are given in terms of estimation errors, floor detection probabilities and complexity. It is shown that the proposed metric enhances the performance of both 3D and RSS clustering and that the RSS clustering has lower complexity but worse performance than the 3D clustering. We are also providing in open-access the measurement data together with the Python-based implementation of the algorithms to serve as future benchmarks for indoor positioning studies.

AB - In mobile-centric indoor positioning, having a small databases to transfer from the network side to the mobile is of utmost importance. For scalable and low-complexity solutions, various clustering algorithms have been suggested in the literature, either in coordinates or 3D dimension or in the Access Points or Received Signal Strength (RSS) dimension. Typically, the two dimensions were investigated separately. This paper offers a comparative analysis between different clustering methods, together with a novel metric, called the Penalized Logarithmic Gaussian Distance metric which can boost the performance of the clustering. The results are compared based on real-field measurement data in two different multi-floor buildings and they are given in terms of estimation errors, floor detection probabilities and complexity. It is shown that the proposed metric enhances the performance of both 3D and RSS clustering and that the RSS clustering has lower complexity but worse performance than the 3D clustering. We are also providing in open-access the measurement data together with the Python-based implementation of the algorithms to serve as future benchmarks for indoor positioning studies.

U2 - 10.1109/ICL-GNSS.2016.7533846

DO - 10.1109/ICL-GNSS.2016.7533846

M3 - Conference contribution

SN - 978-1-5090-1757-7

BT - 2016 International Conference on Localization and GNSS (ICL-GNSS)

PB - IEEE

ER -