NLOS Identification and Mitigation for Geolocation Using Least-squares Support Vector Machines

Benny Chitambira; Simon M D Armour; Stephen W Wales; Mark A Beach

doi:10.1109/WCNC.2017.7925566

NLOS Identification and Mitigation for Geolocation Using Least-squares Support Vector Machines

Benny Chitambira, Simon M D Armour, Stephen W Wales, Mark A Beach

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

8 Citations (Scopus)

206 Downloads (Pure)

Abstract

This paper examines the problem of non-line-of- sight (NLOS) identification and mitigation for geolocation signals in mobile networks. A ray tracing tool is used to simulate a mobile radio network with fixed base stations and thousands of mobile stations. The channel data between these mobile stations and base stations is used to extract parameters or features that are used for classification. Techniques for NLOS identification using a Least-Squares Support Vector Machine (LSSVM), are devised, producing greater than 98 percent accuracy for the proposed location specific approach, and 87 percent for the location independent approach. Respective LSSVM NLOS mitigation techniques are also proposed and evaluated. A usage context for the location specific approach is suggested, where the approach can help in addressing some of the challenges of next-generation wireless systems like massive MIMO.

Original language	English
Title of host publication	Wireless Networks of the IEEE WCNC 2017
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Number of pages	6
ISBN (Electronic)	9781509041831
ISBN (Print)	9781509041848
DOIs	https://doi.org/10.1109/WCNC.2017.7925566
Publication status	Published - 11 May 2017

Publication series

Name	IEEE Wireless Communications and Networking Conference (WCNC)
Publisher	IEEE
ISSN (Print)	1558-2612

Access to Document

10.1109/WCNC.2017.7925566

Full-text PDF (accepted author manuscript)
This is the accepted author manuscript (AAM). The final published version (version of record) is available online via IEEE at https://doi.org/10.1109/WCNC.2017.7925566 . Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 399 KBLicence: Other

Fingerprint Dive into the research topics of 'NLOS Identification and Mitigation for Geolocation Using Least-squares Support Vector Machines'. Together they form a unique fingerprint.

Cite this

Chitambira, B., Armour, S. M. D., Wales, S. W., & Beach, M. A. (2017). NLOS Identification and Mitigation for Geolocation Using Least-squares Support Vector Machines. In Wireless Networks of the IEEE WCNC 2017 (IEEE Wireless Communications and Networking Conference (WCNC)). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/WCNC.2017.7925566

@inproceedings{5184051863ef45fab82b0806ea791138,

title = "NLOS Identification and Mitigation for Geolocation Using Least-squares Support Vector Machines",

abstract = "This paper examines the problem of non-line-of- sight (NLOS) identification and mitigation for geolocation signals in mobile networks. A ray tracing tool is used to simulate a mobile radio network with fixed base stations and thousands of mobile stations. The channel data between these mobile stations and base stations is used to extract parameters or features that are used for classification. Techniques for NLOS identification using a Least-Squares Support Vector Machine (LSSVM), are devised, producing greater than 98 percent accuracy for the proposed location specific approach, and 87 percent for the location independent approach. Respective LSSVM NLOS mitigation techniques are also proposed and evaluated. A usage context for the location specific approach is suggested, where the approach can help in addressing some of the challenges of next-generation wireless systems like massive MIMO.",

author = "Benny Chitambira and Armour, {Simon M D} and Wales, {Stephen W} and Beach, {Mark A}",

year = "2017",

month = may,

day = "11",

doi = "10.1109/WCNC.2017.7925566",

language = "English",

isbn = "9781509041848",

series = "IEEE Wireless Communications and Networking Conference (WCNC)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

booktitle = "Wireless Networks of the IEEE WCNC 2017",

address = "United States",

}

NLOS Identification and Mitigation for Geolocation Using Least-squares Support Vector Machines. / Chitambira, Benny ; Armour, Simon M D; Wales, Stephen W; Beach, Mark A.

Wireless Networks of the IEEE WCNC 2017. Institute of Electrical and Electronics Engineers (IEEE), 2017. (IEEE Wireless Communications and Networking Conference (WCNC)).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - NLOS Identification and Mitigation for Geolocation Using Least-squares Support Vector Machines

AU - Chitambira, Benny

AU - Armour, Simon M D

AU - Wales, Stephen W

AU - Beach, Mark A

PY - 2017/5/11

Y1 - 2017/5/11

N2 - This paper examines the problem of non-line-of- sight (NLOS) identification and mitigation for geolocation signals in mobile networks. A ray tracing tool is used to simulate a mobile radio network with fixed base stations and thousands of mobile stations. The channel data between these mobile stations and base stations is used to extract parameters or features that are used for classification. Techniques for NLOS identification using a Least-Squares Support Vector Machine (LSSVM), are devised, producing greater than 98 percent accuracy for the proposed location specific approach, and 87 percent for the location independent approach. Respective LSSVM NLOS mitigation techniques are also proposed and evaluated. A usage context for the location specific approach is suggested, where the approach can help in addressing some of the challenges of next-generation wireless systems like massive MIMO.

AB - This paper examines the problem of non-line-of- sight (NLOS) identification and mitigation for geolocation signals in mobile networks. A ray tracing tool is used to simulate a mobile radio network with fixed base stations and thousands of mobile stations. The channel data between these mobile stations and base stations is used to extract parameters or features that are used for classification. Techniques for NLOS identification using a Least-Squares Support Vector Machine (LSSVM), are devised, producing greater than 98 percent accuracy for the proposed location specific approach, and 87 percent for the location independent approach. Respective LSSVM NLOS mitigation techniques are also proposed and evaluated. A usage context for the location specific approach is suggested, where the approach can help in addressing some of the challenges of next-generation wireless systems like massive MIMO.

U2 - 10.1109/WCNC.2017.7925566

DO - 10.1109/WCNC.2017.7925566

M3 - Conference Contribution (Conference Proceeding)

SN - 9781509041848

T3 - IEEE Wireless Communications and Networking Conference (WCNC)

BT - Wireless Networks of the IEEE WCNC 2017

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -