The Application of Machine Learning Techniques on Channel Frequency Response Based Indoor Positioning in Dynamic Environments

Josyl Mariela Rocamora; Ivan Wang Hei Ho; Man Wai Mak

doi:10.1109/SECONW.2018.8396358

The Application of Machine Learning Techniques on Channel Frequency Response Based Indoor Positioning in Dynamic Environments

Josyl Mariela Rocamora, Ivan Wang Hei Ho, Man Wai Mak

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

6 Citations (Scopus)

Abstract

Traditional IPS uses triangulation based on signal strength but its accuracy is impaired in non-line-of-sight (NLOS) situations. Among the available wireless technologies for indoor positioning, WiFi is a good candidate since it is supported by existing mobile devices and infrastructure indoors, and it can operate under both LOS and NLOS conditions. One of the cutting-edge WiFi-based localization techniques exploits time-reversal resonating strength (TRRS) of coherent channel frequency responses (CFR). The basic concept of CFR-based positioning is based on the similarity measure between the testing CFR and the pre-recorded CFR fingerprints. A common assumption in previous works is that the wireless channel is time invariant. In this paper, we study CFR-based positioning in a dynamic indoor environment. Using the collected channel response fingerprints for both LOS and NLOS scenarios, we exploit supervised machine learning techniques to enhance the processing speed while achieving high positioning accuracy under the effect of dynamic wireless channels.

Original language	English
Title of host publication	2018 IEEE International Conference on Sensing, Communication and Networking, SECON Workshops 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-4
Number of pages	4
ISBN (Electronic)	9781538652411
DOIs	https://doi.org/10.1109/SECONW.2018.8396358
Publication status	Published - 25 Jun 2018
Event	2018 IEEE International Conference on Sensing, Communication and Networking, SECON Workshops 2018 - Hung Hom, Kowloon, Hong Kong Duration: 11 Jun 2018 → …

Conference

Conference	2018 IEEE International Conference on Sensing, Communication and Networking, SECON Workshops 2018
Country/Territory	Hong Kong
City	Hung Hom, Kowloon
Period	11/06/18 → …

Keywords

Channel Frequency Response (CFR)
Indoor Positioning System (IPS)
Support Vector Machine (SVM)

ASJC Scopus subject areas

Aerospace Engineering
Computer Networks and Communications

More information

10.1109/SECONW.2018.8396358

http://hdl.handle.net/10397/107203

Cite this

Rocamora, J. M., Ho, I. W. H., & Mak, M. W. (2018). The Application of Machine Learning Techniques on Channel Frequency Response Based Indoor Positioning in Dynamic Environments. In 2018 IEEE International Conference on Sensing, Communication and Networking, SECON Workshops 2018 (pp. 1-4). Article 8396358 Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SECONW.2018.8396358

@inproceedings{74d43315153f4dd29a8291623ea7beca,

title = "The Application of Machine Learning Techniques on Channel Frequency Response Based Indoor Positioning in Dynamic Environments",

abstract = "Traditional IPS uses triangulation based on signal strength but its accuracy is impaired in non-line-of-sight (NLOS) situations. Among the available wireless technologies for indoor positioning, WiFi is a good candidate since it is supported by existing mobile devices and infrastructure indoors, and it can operate under both LOS and NLOS conditions. One of the cutting-edge WiFi-based localization techniques exploits time-reversal resonating strength (TRRS) of coherent channel frequency responses (CFR). The basic concept of CFR-based positioning is based on the similarity measure between the testing CFR and the pre-recorded CFR fingerprints. A common assumption in previous works is that the wireless channel is time invariant. In this paper, we study CFR-based positioning in a dynamic indoor environment. Using the collected channel response fingerprints for both LOS and NLOS scenarios, we exploit supervised machine learning techniques to enhance the processing speed while achieving high positioning accuracy under the effect of dynamic wireless channels.",

keywords = "Channel Frequency Response (CFR), Indoor Positioning System (IPS), Support Vector Machine (SVM)",

author = "Rocamora, {Josyl Mariela} and Ho, {Ivan Wang Hei} and Mak, {Man Wai}",

year = "2018",

month = jun,

day = "25",

doi = "10.1109/SECONW.2018.8396358",

language = "English",

pages = "1--4",

booktitle = "2018 IEEE International Conference on Sensing, Communication and Networking, SECON Workshops 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "2018 IEEE International Conference on Sensing, Communication and Networking, SECON Workshops 2018 ; Conference date: 11-06-2018",

}

Rocamora, JM, Ho, IWH & Mak, MW 2018, The Application of Machine Learning Techniques on Channel Frequency Response Based Indoor Positioning in Dynamic Environments. in 2018 IEEE International Conference on Sensing, Communication and Networking, SECON Workshops 2018., 8396358, Institute of Electrical and Electronics Engineers Inc., pp. 1-4, 2018 IEEE International Conference on Sensing, Communication and Networking, SECON Workshops 2018, Hung Hom, Kowloon, Hong Kong, 11/06/18. https://doi.org/10.1109/SECONW.2018.8396358

The Application of Machine Learning Techniques on Channel Frequency Response Based Indoor Positioning in Dynamic Environments. / Rocamora, Josyl Mariela; Ho, Ivan Wang Hei ; Mak, Man Wai.
2018 IEEE International Conference on Sensing, Communication and Networking, SECON Workshops 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-4 8396358.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - The Application of Machine Learning Techniques on Channel Frequency Response Based Indoor Positioning in Dynamic Environments

AU - Rocamora, Josyl Mariela

AU - Ho, Ivan Wang Hei

AU - Mak, Man Wai

PY - 2018/6/25

Y1 - 2018/6/25

N2 - Traditional IPS uses triangulation based on signal strength but its accuracy is impaired in non-line-of-sight (NLOS) situations. Among the available wireless technologies for indoor positioning, WiFi is a good candidate since it is supported by existing mobile devices and infrastructure indoors, and it can operate under both LOS and NLOS conditions. One of the cutting-edge WiFi-based localization techniques exploits time-reversal resonating strength (TRRS) of coherent channel frequency responses (CFR). The basic concept of CFR-based positioning is based on the similarity measure between the testing CFR and the pre-recorded CFR fingerprints. A common assumption in previous works is that the wireless channel is time invariant. In this paper, we study CFR-based positioning in a dynamic indoor environment. Using the collected channel response fingerprints for both LOS and NLOS scenarios, we exploit supervised machine learning techniques to enhance the processing speed while achieving high positioning accuracy under the effect of dynamic wireless channels.

AB - Traditional IPS uses triangulation based on signal strength but its accuracy is impaired in non-line-of-sight (NLOS) situations. Among the available wireless technologies for indoor positioning, WiFi is a good candidate since it is supported by existing mobile devices and infrastructure indoors, and it can operate under both LOS and NLOS conditions. One of the cutting-edge WiFi-based localization techniques exploits time-reversal resonating strength (TRRS) of coherent channel frequency responses (CFR). The basic concept of CFR-based positioning is based on the similarity measure between the testing CFR and the pre-recorded CFR fingerprints. A common assumption in previous works is that the wireless channel is time invariant. In this paper, we study CFR-based positioning in a dynamic indoor environment. Using the collected channel response fingerprints for both LOS and NLOS scenarios, we exploit supervised machine learning techniques to enhance the processing speed while achieving high positioning accuracy under the effect of dynamic wireless channels.

KW - Channel Frequency Response (CFR)

KW - Indoor Positioning System (IPS)

KW - Support Vector Machine (SVM)

UR - http://www.scopus.com/inward/record.url?scp=85050555642&partnerID=8YFLogxK

U2 - 10.1109/SECONW.2018.8396358

DO - 10.1109/SECONW.2018.8396358

M3 - Conference article published in proceeding or book

AN - SCOPUS:85050555642

SP - 1

EP - 4

BT - 2018 IEEE International Conference on Sensing, Communication and Networking, SECON Workshops 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE International Conference on Sensing, Communication and Networking, SECON Workshops 2018

Y2 - 11 June 2018

ER -

The Application of Machine Learning Techniques on Channel Frequency Response Based Indoor Positioning in Dynamic Environments

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this