Hidden Markov Model based Mobility Learning for Improving Indoor Tracking of Mobile Users

Nikolaj Bisgaard Pedersen, Troels Laursen, Jimmy Jessen Nielsen, Tatiana Kozlova Madsen

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

6 Citations (Scopus)

Abstract

Indoors, a user's movements are typically confined by walls, corridors, and doorways, and further he is typically repeating the same movements such as walking between certain points in the building. Conventional indoor localization systems do usually not take these properties of the user's movements into account. In this paper we propose a Hidden Markov Model (HMM) based tracking algorithm, which takes a user's previous movements into account. In a quantized grid representation of an indoor scenario, past movement information is used to update the HMM transition probabilities. The user's most likely trajectory is then calculated using and extended version of the Viterbi algorithm. The results show significant improvements of the proposed algorithm compared to a simpler moving average smoothing.
Original languageEnglish
Title of host publicationProceedings of the WPNC 2012
Number of pages5
Place of PublicationDresden, Germany
PublisherIEEE Press
Publication date2012
Pages100-104
ISBN (Print)978-1-4673-1437-4
DOIs
Publication statusPublished - 2012
Event2012 9th Workshop on Positioning Navigation and Communication - Dresden, Germany
Duration: 15 Mar 201216 Mar 2012

Workshop

Workshop2012 9th Workshop on Positioning Navigation and Communication
CountryGermany
CityDresden
Period15/03/201216/03/2012

Fingerprint

Hidden Markov models
Viterbi algorithm
Trajectories

Cite this

Pedersen, N. B., Laursen, T., Nielsen, J. J., & Madsen, T. K. (2012). Hidden Markov Model based Mobility Learning for Improving Indoor Tracking of Mobile Users. In Proceedings of the WPNC 2012 (pp. 100-104). Dresden, Germany: IEEE Press. https://doi.org/10.1109/WPNC.2012.6268746
Pedersen, Nikolaj Bisgaard ; Laursen, Troels ; Nielsen, Jimmy Jessen ; Madsen, Tatiana Kozlova. / Hidden Markov Model based Mobility Learning for Improving Indoor Tracking of Mobile Users. Proceedings of the WPNC 2012. Dresden, Germany : IEEE Press, 2012. pp. 100-104
@inproceedings{7d59a3befb314df2b21e03c050aed9f0,
title = "Hidden Markov Model based Mobility Learning for Improving Indoor Tracking of Mobile Users",
abstract = "Indoors, a user's movements are typically confined by walls, corridors, and doorways, and further he is typically repeating the same movements such as walking between certain points in the building. Conventional indoor localization systems do usually not take these properties of the user's movements into account. In this paper we propose a Hidden Markov Model (HMM) based tracking algorithm, which takes a user's previous movements into account. In a quantized grid representation of an indoor scenario, past movement information is used to update the HMM transition probabilities. The user's most likely trajectory is then calculated using and extended version of the Viterbi algorithm. The results show significant improvements of the proposed algorithm compared to a simpler moving average smoothing.",
author = "Pedersen, {Nikolaj Bisgaard} and Troels Laursen and Nielsen, {Jimmy Jessen} and Madsen, {Tatiana Kozlova}",
year = "2012",
doi = "10.1109/WPNC.2012.6268746",
language = "English",
isbn = "978-1-4673-1437-4",
pages = "100--104",
booktitle = "Proceedings of the WPNC 2012",
publisher = "IEEE Press",

}

Pedersen, NB, Laursen, T, Nielsen, JJ & Madsen, TK 2012, Hidden Markov Model based Mobility Learning for Improving Indoor Tracking of Mobile Users. in Proceedings of the WPNC 2012. IEEE Press, Dresden, Germany, pp. 100-104, 2012 9th Workshop on Positioning Navigation and Communication, Dresden, Germany, 15/03/2012. https://doi.org/10.1109/WPNC.2012.6268746

Hidden Markov Model based Mobility Learning for Improving Indoor Tracking of Mobile Users. / Pedersen, Nikolaj Bisgaard; Laursen, Troels; Nielsen, Jimmy Jessen; Madsen, Tatiana Kozlova.

Proceedings of the WPNC 2012. Dresden, Germany : IEEE Press, 2012. p. 100-104.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Hidden Markov Model based Mobility Learning for Improving Indoor Tracking of Mobile Users

AU - Pedersen, Nikolaj Bisgaard

AU - Laursen, Troels

AU - Nielsen, Jimmy Jessen

AU - Madsen, Tatiana Kozlova

PY - 2012

Y1 - 2012

N2 - Indoors, a user's movements are typically confined by walls, corridors, and doorways, and further he is typically repeating the same movements such as walking between certain points in the building. Conventional indoor localization systems do usually not take these properties of the user's movements into account. In this paper we propose a Hidden Markov Model (HMM) based tracking algorithm, which takes a user's previous movements into account. In a quantized grid representation of an indoor scenario, past movement information is used to update the HMM transition probabilities. The user's most likely trajectory is then calculated using and extended version of the Viterbi algorithm. The results show significant improvements of the proposed algorithm compared to a simpler moving average smoothing.

AB - Indoors, a user's movements are typically confined by walls, corridors, and doorways, and further he is typically repeating the same movements such as walking between certain points in the building. Conventional indoor localization systems do usually not take these properties of the user's movements into account. In this paper we propose a Hidden Markov Model (HMM) based tracking algorithm, which takes a user's previous movements into account. In a quantized grid representation of an indoor scenario, past movement information is used to update the HMM transition probabilities. The user's most likely trajectory is then calculated using and extended version of the Viterbi algorithm. The results show significant improvements of the proposed algorithm compared to a simpler moving average smoothing.

UR - http://www.scopus.com/inward/record.url?scp=84867005683&partnerID=8YFLogxK

U2 - 10.1109/WPNC.2012.6268746

DO - 10.1109/WPNC.2012.6268746

M3 - Article in proceeding

SN - 978-1-4673-1437-4

SP - 100

EP - 104

BT - Proceedings of the WPNC 2012

PB - IEEE Press

CY - Dresden, Germany

ER -

Pedersen NB, Laursen T, Nielsen JJ, Madsen TK. Hidden Markov Model based Mobility Learning for Improving Indoor Tracking of Mobile Users. In Proceedings of the WPNC 2012. Dresden, Germany: IEEE Press. 2012. p. 100-104 https://doi.org/10.1109/WPNC.2012.6268746