Directional Hidden Markov Model for Indoor Tracking of Mobile Users and Realistic Case Study

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

5 Citations (Scopus)

Abstract

Indoors, mobile users tend to exhibit some level of determinism in their movement patterns during a day, for example when arriving to their office, going for coffee, going for lunch break, picking up print outs, etc. In this work we exploit this determinism to improve the accuracy of indoor localization systems. We consider two Hidden Markov Model (HMM) based filtering algorithms that use previous observations to estimate a user’s most likely movement trajectory, given a sequence of inaccurate location coordinates. The proposed Directional HMM algorithm is able to learn user habits by discriminating between different movement directions when populating the state transition probability matrix from training data. The proposed algorithm is compared to a Standard HMM algorithm that does not distinguish different movement directions.
Evaluation results for a simple test scenario with two op- positely intersecting trajectories demonstrated a significant im- provement of location accuracy with the Directional HMM algorithm. Further results for a scenario with realistic simulation based movement trajectories also showed improvements for 60% of the cases, however only if the HMM models are trained with usually unknown true trajectories. When trained with inaccurate location estimations, the HMM based algorithms showed no benefit compared to just using the localization system.
Original languageEnglish
Title of host publicationProceedings of the European Wireless, 2013. EW. 19th European Wireless Conference
Number of pages6
PublisherVDE Verlag GMBH
Publication date16 Apr 2013
ISBN (Electronic)978-3-8007-3498-6
Publication statusPublished - 16 Apr 2013
EventThe 19th European Wireless Conference - Guildford, United Kingdom
Duration: 16 Apr 201318 Apr 2013

Conference

ConferenceThe 19th European Wireless Conference
CountryUnited Kingdom
CityGuildford
Period16/04/201318/04/2013

Fingerprint

Hidden Markov models
Trajectories
Coffee

Bibliographical note

SNO/CNO for "European Wireless Conference" series: 5010943

Cite this

Nielsen, J. J., Amiot, N., & Madsen, T. K. (2013). Directional Hidden Markov Model for Indoor Tracking of Mobile Users and Realistic Case Study. In Proceedings of the European Wireless, 2013. EW. 19th European Wireless Conference VDE Verlag GMBH.
Nielsen, Jimmy Jessen ; Amiot, Nicolas ; Madsen, Tatiana Kozlova. / Directional Hidden Markov Model for Indoor Tracking of Mobile Users and Realistic Case Study. Proceedings of the European Wireless, 2013. EW. 19th European Wireless Conference. VDE Verlag GMBH, 2013.
@inproceedings{de6772951e144a1db8ad47b84ac4d2f2,
title = "Directional Hidden Markov Model for Indoor Tracking of Mobile Users and Realistic Case Study",
abstract = "Indoors, mobile users tend to exhibit some level of determinism in their movement patterns during a day, for example when arriving to their office, going for coffee, going for lunch break, picking up print outs, etc. In this work we exploit this determinism to improve the accuracy of indoor localization systems. We consider two Hidden Markov Model (HMM) based filtering algorithms that use previous observations to estimate a user’s most likely movement trajectory, given a sequence of inaccurate location coordinates. The proposed Directional HMM algorithm is able to learn user habits by discriminating between different movement directions when populating the state transition probability matrix from training data. The proposed algorithm is compared to a Standard HMM algorithm that does not distinguish different movement directions.Evaluation results for a simple test scenario with two op- positely intersecting trajectories demonstrated a significant im- provement of location accuracy with the Directional HMM algorithm. Further results for a scenario with realistic simulation based movement trajectories also showed improvements for 60{\%} of the cases, however only if the HMM models are trained with usually unknown true trajectories. When trained with inaccurate location estimations, the HMM based algorithms showed no benefit compared to just using the localization system.",
author = "Nielsen, {Jimmy Jessen} and Nicolas Amiot and Madsen, {Tatiana Kozlova}",
note = "SNO/CNO for {"}European Wireless Conference{"} series: 5010943",
year = "2013",
month = "4",
day = "16",
language = "English",
booktitle = "Proceedings of the European Wireless, 2013. EW. 19th European Wireless Conference",
publisher = "VDE Verlag GMBH",

}

Nielsen, JJ, Amiot, N & Madsen, TK 2013, Directional Hidden Markov Model for Indoor Tracking of Mobile Users and Realistic Case Study. in Proceedings of the European Wireless, 2013. EW. 19th European Wireless Conference. VDE Verlag GMBH, The 19th European Wireless Conference, Guildford, United Kingdom, 16/04/2013.

Directional Hidden Markov Model for Indoor Tracking of Mobile Users and Realistic Case Study. / Nielsen, Jimmy Jessen; Amiot, Nicolas; Madsen, Tatiana Kozlova.

Proceedings of the European Wireless, 2013. EW. 19th European Wireless Conference. VDE Verlag GMBH, 2013.

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

TY - GEN

T1 - Directional Hidden Markov Model for Indoor Tracking of Mobile Users and Realistic Case Study

AU - Nielsen, Jimmy Jessen

AU - Amiot, Nicolas

AU - Madsen, Tatiana Kozlova

N1 - SNO/CNO for "European Wireless Conference" series: 5010943

PY - 2013/4/16

Y1 - 2013/4/16

N2 - Indoors, mobile users tend to exhibit some level of determinism in their movement patterns during a day, for example when arriving to their office, going for coffee, going for lunch break, picking up print outs, etc. In this work we exploit this determinism to improve the accuracy of indoor localization systems. We consider two Hidden Markov Model (HMM) based filtering algorithms that use previous observations to estimate a user’s most likely movement trajectory, given a sequence of inaccurate location coordinates. The proposed Directional HMM algorithm is able to learn user habits by discriminating between different movement directions when populating the state transition probability matrix from training data. The proposed algorithm is compared to a Standard HMM algorithm that does not distinguish different movement directions.Evaluation results for a simple test scenario with two op- positely intersecting trajectories demonstrated a significant im- provement of location accuracy with the Directional HMM algorithm. Further results for a scenario with realistic simulation based movement trajectories also showed improvements for 60% of the cases, however only if the HMM models are trained with usually unknown true trajectories. When trained with inaccurate location estimations, the HMM based algorithms showed no benefit compared to just using the localization system.

AB - Indoors, mobile users tend to exhibit some level of determinism in their movement patterns during a day, for example when arriving to their office, going for coffee, going for lunch break, picking up print outs, etc. In this work we exploit this determinism to improve the accuracy of indoor localization systems. We consider two Hidden Markov Model (HMM) based filtering algorithms that use previous observations to estimate a user’s most likely movement trajectory, given a sequence of inaccurate location coordinates. The proposed Directional HMM algorithm is able to learn user habits by discriminating between different movement directions when populating the state transition probability matrix from training data. The proposed algorithm is compared to a Standard HMM algorithm that does not distinguish different movement directions.Evaluation results for a simple test scenario with two op- positely intersecting trajectories demonstrated a significant im- provement of location accuracy with the Directional HMM algorithm. Further results for a scenario with realistic simulation based movement trajectories also showed improvements for 60% of the cases, however only if the HMM models are trained with usually unknown true trajectories. When trained with inaccurate location estimations, the HMM based algorithms showed no benefit compared to just using the localization system.

M3 - Article in proceeding

BT - Proceedings of the European Wireless, 2013. EW. 19th European Wireless Conference

PB - VDE Verlag GMBH

ER -

Nielsen JJ, Amiot N, Madsen TK. Directional Hidden Markov Model for Indoor Tracking of Mobile Users and Realistic Case Study. In Proceedings of the European Wireless, 2013. EW. 19th European Wireless Conference. VDE Verlag GMBH. 2013