Multivariate analysis for probabilistic WLAN location determination systems

Moustafa Youssef, Mohamed Abdallah, Ashok Agrawala

Research output: Chapter in Book/Report/Conference proceedingConference contribution

33 Citations (Scopus)

Abstract

WLAN location determination systems are gaining increasing attention due to the value they add to wireless networks. In this paper, we present a multivariate analysis technique for enhancing the performance of WLAN location determination systems by taking the correlation between samples from the same access point into account. We show that the autocorrelation between consecutive samples from the same access point can be as high as 0.9. Giving a sequence of correlated signal strength samples from an access point, the technique estimates the user location based on the calculated probability of this sequence from the multivariate distribution. We use a linear autoregressive model to derive the multivariate distribution function for the correlated samples. Using analytical analysis, we show that the proposed technique provides better location accuracy over previous techniques especially for the highly correlated samples in a typical WLAN environment. Implementation of the technique in the Horus WLAN location determination system shows that the average system accuracy is increased by more than 64%. This significant enhancement in the accuracy of WLAN location determination systems helps increase the set of context-aware applications implemented on top of these systems.

Original languageEnglish
Title of host publicationMobiQuitous 2005: Second Annual International Conference on Mobile and Ubiquitous Systems -Networking and Services
Pages353-362
Number of pages10
DOIs
Publication statusPublished - 2005
Externally publishedYes
EventMobiQuitous 2005: Second Annual International Conference on Mobile and Ubiquitous Systems -Networking and Services - San Diego, CA, United States
Duration: 17 Jul 200521 Jul 2005

Other

OtherMobiQuitous 2005: Second Annual International Conference on Mobile and Ubiquitous Systems -Networking and Services
CountryUnited States
CitySan Diego, CA
Period17/7/0521/7/05

Fingerprint

Wireless local area networks (WLAN)
Autocorrelation
Distribution functions
Multivariate Analysis
Wireless networks

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Youssef, M., Abdallah, M., & Agrawala, A. (2005). Multivariate analysis for probabilistic WLAN location determination systems. In MobiQuitous 2005: Second Annual International Conference on Mobile and Ubiquitous Systems -Networking and Services (pp. 353-362). [1541015] https://doi.org/10.1109/MOBIQUITOUS.2005.41

Multivariate analysis for probabilistic WLAN location determination systems. / Youssef, Moustafa; Abdallah, Mohamed; Agrawala, Ashok.

MobiQuitous 2005: Second Annual International Conference on Mobile and Ubiquitous Systems -Networking and Services. 2005. p. 353-362 1541015.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Youssef, M, Abdallah, M & Agrawala, A 2005, Multivariate analysis for probabilistic WLAN location determination systems. in MobiQuitous 2005: Second Annual International Conference on Mobile and Ubiquitous Systems -Networking and Services., 1541015, pp. 353-362, MobiQuitous 2005: Second Annual International Conference on Mobile and Ubiquitous Systems -Networking and Services, San Diego, CA, United States, 17/7/05. https://doi.org/10.1109/MOBIQUITOUS.2005.41
Youssef M, Abdallah M, Agrawala A. Multivariate analysis for probabilistic WLAN location determination systems. In MobiQuitous 2005: Second Annual International Conference on Mobile and Ubiquitous Systems -Networking and Services. 2005. p. 353-362. 1541015 https://doi.org/10.1109/MOBIQUITOUS.2005.41
Youssef, Moustafa ; Abdallah, Mohamed ; Agrawala, Ashok. / Multivariate analysis for probabilistic WLAN location determination systems. MobiQuitous 2005: Second Annual International Conference on Mobile and Ubiquitous Systems -Networking and Services. 2005. pp. 353-362
@inproceedings{bf8ee3b3c9be4fac9656ec817cc5a22e,
title = "Multivariate analysis for probabilistic WLAN location determination systems",
abstract = "WLAN location determination systems are gaining increasing attention due to the value they add to wireless networks. In this paper, we present a multivariate analysis technique for enhancing the performance of WLAN location determination systems by taking the correlation between samples from the same access point into account. We show that the autocorrelation between consecutive samples from the same access point can be as high as 0.9. Giving a sequence of correlated signal strength samples from an access point, the technique estimates the user location based on the calculated probability of this sequence from the multivariate distribution. We use a linear autoregressive model to derive the multivariate distribution function for the correlated samples. Using analytical analysis, we show that the proposed technique provides better location accuracy over previous techniques especially for the highly correlated samples in a typical WLAN environment. Implementation of the technique in the Horus WLAN location determination system shows that the average system accuracy is increased by more than 64{\%}. This significant enhancement in the accuracy of WLAN location determination systems helps increase the set of context-aware applications implemented on top of these systems.",
author = "Moustafa Youssef and Mohamed Abdallah and Ashok Agrawala",
year = "2005",
doi = "10.1109/MOBIQUITOUS.2005.41",
language = "English",
isbn = "0769523757",
pages = "353--362",
booktitle = "MobiQuitous 2005: Second Annual International Conference on Mobile and Ubiquitous Systems -Networking and Services",

}

TY - GEN

T1 - Multivariate analysis for probabilistic WLAN location determination systems

AU - Youssef, Moustafa

AU - Abdallah, Mohamed

AU - Agrawala, Ashok

PY - 2005

Y1 - 2005

N2 - WLAN location determination systems are gaining increasing attention due to the value they add to wireless networks. In this paper, we present a multivariate analysis technique for enhancing the performance of WLAN location determination systems by taking the correlation between samples from the same access point into account. We show that the autocorrelation between consecutive samples from the same access point can be as high as 0.9. Giving a sequence of correlated signal strength samples from an access point, the technique estimates the user location based on the calculated probability of this sequence from the multivariate distribution. We use a linear autoregressive model to derive the multivariate distribution function for the correlated samples. Using analytical analysis, we show that the proposed technique provides better location accuracy over previous techniques especially for the highly correlated samples in a typical WLAN environment. Implementation of the technique in the Horus WLAN location determination system shows that the average system accuracy is increased by more than 64%. This significant enhancement in the accuracy of WLAN location determination systems helps increase the set of context-aware applications implemented on top of these systems.

AB - WLAN location determination systems are gaining increasing attention due to the value they add to wireless networks. In this paper, we present a multivariate analysis technique for enhancing the performance of WLAN location determination systems by taking the correlation between samples from the same access point into account. We show that the autocorrelation between consecutive samples from the same access point can be as high as 0.9. Giving a sequence of correlated signal strength samples from an access point, the technique estimates the user location based on the calculated probability of this sequence from the multivariate distribution. We use a linear autoregressive model to derive the multivariate distribution function for the correlated samples. Using analytical analysis, we show that the proposed technique provides better location accuracy over previous techniques especially for the highly correlated samples in a typical WLAN environment. Implementation of the technique in the Horus WLAN location determination system shows that the average system accuracy is increased by more than 64%. This significant enhancement in the accuracy of WLAN location determination systems helps increase the set of context-aware applications implemented on top of these systems.

UR - http://www.scopus.com/inward/record.url?scp=33749507872&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33749507872&partnerID=8YFLogxK

U2 - 10.1109/MOBIQUITOUS.2005.41

DO - 10.1109/MOBIQUITOUS.2005.41

M3 - Conference contribution

SN - 0769523757

SN - 9780769523750

SP - 353

EP - 362

BT - MobiQuitous 2005: Second Annual International Conference on Mobile and Ubiquitous Systems -Networking and Services

ER -