Home > Research > Publications & Outputs > Practical classification methods for indoor pos...

Electronic data

Links

Text available via DOI:

View graph of relations

Practical classification methods for indoor positioning

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Practical classification methods for indoor positioning. / Honary, Mahsa; Mihaylova, Lyudmila; Xydeas, Costas.
In: Open Transportation Journal, Vol. 6, 21.07.2012, p. 31-38.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Honary M, Mihaylova L, Xydeas C. Practical classification methods for indoor positioning. Open Transportation Journal. 2012 Jul 21;6:31-38. doi: 10.2174/1874447801206010031

Author

Bibtex

@article{839c1e6320464ff28d57a7fa7fb39de9,
title = "Practical classification methods for indoor positioning",
abstract = "Location awareness is of primary importance in a wealth of applications such as transportation, mobile health systems, augmented reality and navigation. For example, in busy transportation areas (such as airports) providing clear,personalised notifications and directions, can reduce delays and improve the passenger journeys. Currently some applications provide easy access to information. These travel related applications can become context aware via theavailability of accurate indoor/outdoor positioning. However, there are barriers that still have to overcome. One such barrier is the time required to set up and calibrate indoor positioning systems, another is the challenge of scalability withregard to the processing requirements of indoor positioning algorithms. This paper investigates the relationship between the calibration data and positioning system accuracy and analyses the performance of a k-Nearest Neighbour (k-NN) based positioning algorithm using real GSM data. Furthermore, the paper proposes a positioning scheme based on Gaussian Mixture Models (GMM). Experimental results show that the proposed GMM algorithm (without post-filtering) provides high levels of localization accuracy and successfully copes with the scalability problems that the conventional k-NN approach faces.",
keywords = "LOCALIZATION, Gaussian mixture, GSM data, Classification, Clustering, Received Signal Strengths, asset tracking, informed traveller",
author = "Mahsa Honary and Lyudmila Mihaylova and Costas Xydeas",
year = "2012",
month = jul,
day = "21",
doi = "10.2174/1874447801206010031",
language = "English",
volume = "6",
pages = "31--38",
journal = "Open Transportation Journal",
publisher = "Bentham Science Publishers",

}

RIS

TY - JOUR

T1 - Practical classification methods for indoor positioning

AU - Honary, Mahsa

AU - Mihaylova, Lyudmila

AU - Xydeas, Costas

PY - 2012/7/21

Y1 - 2012/7/21

N2 - Location awareness is of primary importance in a wealth of applications such as transportation, mobile health systems, augmented reality and navigation. For example, in busy transportation areas (such as airports) providing clear,personalised notifications and directions, can reduce delays and improve the passenger journeys. Currently some applications provide easy access to information. These travel related applications can become context aware via theavailability of accurate indoor/outdoor positioning. However, there are barriers that still have to overcome. One such barrier is the time required to set up and calibrate indoor positioning systems, another is the challenge of scalability withregard to the processing requirements of indoor positioning algorithms. This paper investigates the relationship between the calibration data and positioning system accuracy and analyses the performance of a k-Nearest Neighbour (k-NN) based positioning algorithm using real GSM data. Furthermore, the paper proposes a positioning scheme based on Gaussian Mixture Models (GMM). Experimental results show that the proposed GMM algorithm (without post-filtering) provides high levels of localization accuracy and successfully copes with the scalability problems that the conventional k-NN approach faces.

AB - Location awareness is of primary importance in a wealth of applications such as transportation, mobile health systems, augmented reality and navigation. For example, in busy transportation areas (such as airports) providing clear,personalised notifications and directions, can reduce delays and improve the passenger journeys. Currently some applications provide easy access to information. These travel related applications can become context aware via theavailability of accurate indoor/outdoor positioning. However, there are barriers that still have to overcome. One such barrier is the time required to set up and calibrate indoor positioning systems, another is the challenge of scalability withregard to the processing requirements of indoor positioning algorithms. This paper investigates the relationship between the calibration data and positioning system accuracy and analyses the performance of a k-Nearest Neighbour (k-NN) based positioning algorithm using real GSM data. Furthermore, the paper proposes a positioning scheme based on Gaussian Mixture Models (GMM). Experimental results show that the proposed GMM algorithm (without post-filtering) provides high levels of localization accuracy and successfully copes with the scalability problems that the conventional k-NN approach faces.

KW - LOCALIZATION

KW - Gaussian mixture

KW - GSM data

KW - Classification

KW - Clustering

KW - Received Signal Strengths

KW - asset tracking

KW - informed traveller

U2 - 10.2174/1874447801206010031

DO - 10.2174/1874447801206010031

M3 - Journal article

VL - 6

SP - 31

EP - 38

JO - Open Transportation Journal

JF - Open Transportation Journal

ER -