Outdoor Visible Light Positioning Using Artificial Neural Networks for Autonomous Vehicle Application

Abdulrahman Mahmoud; Zahir Ahmad; Yousef Almadani; Muhammad Ijaz; Olivier Haas; Sujan Rajbhandari

doi:10.1109/CSNDSP49049.2020.9249440

Outdoor Visible Light Positioning Using Artificial Neural Networks for Autonomous Vehicle Application

Abdulrahman Mahmoud, Zahir Ahmad, Yousef Almadani, Muhammad Ijaz, Olivier Haas, Sujan Rajbhandari

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

1 Citation (Scopus)

27 Downloads (Pure)

Abstract

In this paper, a novel outdoor 2-D vehicular visible light positioning (VLP) using a linear array of streetlights and artificial neural network (ANN) is proposed. The classical position methods which are mostly based on triangulation will not work with the linear array of the street light. Hence, we proposed a spatial diversity receiver with ANN to overcome the collinearity condition. The proposed system is simulated for a realistic outdoor condition and provides an accurate positioning with an average RMS error of 0.53m.

Original language	English
Title of host publication	2020 12th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP)
Publisher	IEEE
Pages	1-4
Number of pages	4
ISBN (Electronic)	9781728167435
ISBN (Print)	9781728160511
DOIs	https://doi.org/10.1109/CSNDSP49049.2020.9249440
Publication status	Published - 10 Nov 2020
Event	12th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2020 - Porto, Portugal Duration: 20 Jul 2020 → 22 Jul 2020

Conference

Conference	12th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2020
Country/Territory	Portugal
City	Porto
Period	20/07/20 → 22/07/20

Bibliographical note

© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Funding Information:
This work is supported by Petroleum Technology Development Fund (PTDF).

Keywords

Artificial neural network
outdoor positioning
receiver diversity
visible light positioning

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing

Access to Document

10.1109/CSNDSP49049.2020.9249440

Post-PrintAccepted author manuscript, 2.35 MB

Cite this

Outdoor Visible Light Positioning Using Artificial Neural Networks for Autonomous Vehicle Application. / Mahmoud, Abdulrahman ; Ahmad, Zahir; Almadani, Yousef; Ijaz, Muhammad; Haas, Olivier; Rajbhandari, Sujan.

2020 12th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP). IEEE, 2020. p. 1-4.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

Mahmoud, A , Ahmad, Z, Almadani, Y, Ijaz, M, Haas, O & Rajbhandari, S 2020, Outdoor Visible Light Positioning Using Artificial Neural Networks for Autonomous Vehicle Application. in 2020 12th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP). IEEE, pp. 1-4, 12th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2020, Porto, Portugal, 20/07/20. https://doi.org/10.1109/CSNDSP49049.2020.9249440

@inproceedings{ff1d17a432a645ec9fd9c3ce38e17d17,

title = "Outdoor Visible Light Positioning Using Artificial Neural Networks for Autonomous Vehicle Application",

abstract = "In this paper, a novel outdoor 2-D vehicular visible light positioning (VLP) using a linear array of streetlights and artificial neural network (ANN) is proposed. The classical position methods which are mostly based on triangulation will not work with the linear array of the street light. Hence, we proposed a spatial diversity receiver with ANN to overcome the collinearity condition. The proposed system is simulated for a realistic outdoor condition and provides an accurate positioning with an average RMS error of 0.53m.",

keywords = "Artificial neural network, outdoor positioning, receiver diversity, visible light positioning",

author = "Abdulrahman Mahmoud and Zahir Ahmad and Yousef Almadani and Muhammad Ijaz and Olivier Haas and Sujan Rajbhandari",

note = "{\textcopyright} 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Funding Information: This work is supported by Petroleum Technology Development Fund (PTDF). ; 12th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2020 ; Conference date: 20-07-2020 Through 22-07-2020",

year = "2020",

month = nov,

day = "10",

doi = "10.1109/CSNDSP49049.2020.9249440",

language = "English",

isbn = "9781728160511",

pages = "1--4",

booktitle = "2020 12th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Outdoor Visible Light Positioning Using Artificial Neural Networks for Autonomous Vehicle Application

AU - Mahmoud, Abdulrahman

AU - Ahmad, Zahir

AU - Almadani, Yousef

AU - Ijaz, Muhammad

AU - Haas, Olivier

AU - Rajbhandari, Sujan

N1 - © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Funding Information: This work is supported by Petroleum Technology Development Fund (PTDF).

PY - 2020/11/10

Y1 - 2020/11/10

N2 - In this paper, a novel outdoor 2-D vehicular visible light positioning (VLP) using a linear array of streetlights and artificial neural network (ANN) is proposed. The classical position methods which are mostly based on triangulation will not work with the linear array of the street light. Hence, we proposed a spatial diversity receiver with ANN to overcome the collinearity condition. The proposed system is simulated for a realistic outdoor condition and provides an accurate positioning with an average RMS error of 0.53m.

AB - In this paper, a novel outdoor 2-D vehicular visible light positioning (VLP) using a linear array of streetlights and artificial neural network (ANN) is proposed. The classical position methods which are mostly based on triangulation will not work with the linear array of the street light. Hence, we proposed a spatial diversity receiver with ANN to overcome the collinearity condition. The proposed system is simulated for a realistic outdoor condition and provides an accurate positioning with an average RMS error of 0.53m.

KW - Artificial neural network

KW - outdoor positioning

KW - receiver diversity

KW - visible light positioning

UR - http://www.scopus.com/inward/record.url?scp=85097655783&partnerID=8YFLogxK

U2 - 10.1109/CSNDSP49049.2020.9249440

DO - 10.1109/CSNDSP49049.2020.9249440

M3 - Conference proceeding

SN - 9781728160511

SP - 1

EP - 4

BT - 2020 12th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP)

PB - IEEE

T2 - 12th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2020

Y2 - 20 July 2020 through 22 July 2020

ER -

Outdoor Visible Light Positioning Using Artificial Neural Networks for Autonomous Vehicle Application

Abstract

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this