Neural network based joint spatial and temporal equalization for MIMO-VLC system

Sujan Rajbhandari, Hyunchae Chun, Graheme Faulkner, Harald Haas, Enyuan Xie, Jonathan J. D. McKendry, Johannes Herrnsdorf, Erdan Gu, Martin D. Dawson, Dominic O'Brien

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The limited bandwidth of white light-emitting diode (LED) limits the achievable data rate in a visible light communication (VLC) system. A number of techniques, including multiple-input-multiple-output (MIMO) system, are investigated to increase the data rate. The high-speed optical MIMO system suffers from both spatial and temporal cross talks. The spatial cross-talk is often compensated by the MIMO decoding algorithm, while the temporal cross talk is mitigated using an equalizer. However, the LEDs have a non-linear transfer function and the performance of linear equalizers are limited. In this letter, we propose a joint spatial and temporal equalization using an artificial neural network (ANN) for an MIMO-VLC system. We demonstrate using a practical imaging/non-imaging optical MIMO link that the ANN-based joint equalization outperforms the joint equalization using a traditional decision feedback as ANN is able to compensate the non-linear transfer function as well as cross talk.

LanguageEnglish
Pages821-824
Number of pages4
JournalIEEE Photonics Technology Letters
Volume31
Issue number11
Early online date4 Apr 2019
DOIs
Publication statusPublished - 1 Jun 2019

Fingerprint

MIMO (control systems)
optical communication
telecommunication
Communication systems
Equalizers
Neural networks
Light emitting diodes
Transfer functions
transfer functions
light emitting diodes
Decoding
Feedback
Bandwidth
Imaging techniques
decoding
high speed
Visible light communication
bandwidth

Keywords

  • visible light communications
  • multiple input multiple output
  • MIMO
  • joint equalization
  • artificial neural network
  • non-linear transfer function

Cite this

@article{42615c1d9f6c416e9dc87e0848d4453c,
title = "Neural network based joint spatial and temporal equalization for MIMO-VLC system",
abstract = "The limited bandwidth of white light-emitting diode (LED) limits the achievable data rate in a visible light communication (VLC) system. A number of techniques, including multiple-input-multiple-output (MIMO) system, are investigated to increase the data rate. The high-speed optical MIMO system suffers from both spatial and temporal cross talks. The spatial cross-talk is often compensated by the MIMO decoding algorithm, while the temporal cross talk is mitigated using an equalizer. However, the LEDs have a non-linear transfer function and the performance of linear equalizers are limited. In this letter, we propose a joint spatial and temporal equalization using an artificial neural network (ANN) for an MIMO-VLC system. We demonstrate using a practical imaging/non-imaging optical MIMO link that the ANN-based joint equalization outperforms the joint equalization using a traditional decision feedback as ANN is able to compensate the non-linear transfer function as well as cross talk.",
keywords = "visible light communications, multiple input multiple output, MIMO, joint equalization, artificial neural network, non-linear transfer function",
author = "Sujan Rajbhandari and Hyunchae Chun and Graheme Faulkner and Harald Haas and Enyuan Xie and McKendry, {Jonathan J. D.} and Johannes Herrnsdorf and Erdan Gu and Dawson, {Martin D.} and Dominic O'Brien",
note = "{\circledC} 2019 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.",
year = "2019",
month = "6",
day = "1",
doi = "10.1109/LPT.2019.2909139",
language = "English",
volume = "31",
pages = "821--824",
journal = "IEEE Photonics Technology Letters",
issn = "1041-1135",
number = "11",

}

Neural network based joint spatial and temporal equalization for MIMO-VLC system. / Rajbhandari, Sujan; Chun, Hyunchae; Faulkner, Graheme; Haas, Harald; Xie, Enyuan; McKendry, Jonathan J. D.; Herrnsdorf, Johannes; Gu, Erdan; Dawson, Martin D.; O'Brien, Dominic.

In: IEEE Photonics Technology Letters, Vol. 31, No. 11, 01.06.2019, p. 821-824.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Neural network based joint spatial and temporal equalization for MIMO-VLC system

AU - Rajbhandari, Sujan

AU - Chun, Hyunchae

AU - Faulkner, Graheme

AU - Haas, Harald

AU - Xie, Enyuan

AU - McKendry, Jonathan J. D.

AU - Herrnsdorf, Johannes

AU - Gu, Erdan

AU - Dawson, Martin D.

AU - O'Brien, Dominic

N1 - © 2019 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.

PY - 2019/6/1

Y1 - 2019/6/1

N2 - The limited bandwidth of white light-emitting diode (LED) limits the achievable data rate in a visible light communication (VLC) system. A number of techniques, including multiple-input-multiple-output (MIMO) system, are investigated to increase the data rate. The high-speed optical MIMO system suffers from both spatial and temporal cross talks. The spatial cross-talk is often compensated by the MIMO decoding algorithm, while the temporal cross talk is mitigated using an equalizer. However, the LEDs have a non-linear transfer function and the performance of linear equalizers are limited. In this letter, we propose a joint spatial and temporal equalization using an artificial neural network (ANN) for an MIMO-VLC system. We demonstrate using a practical imaging/non-imaging optical MIMO link that the ANN-based joint equalization outperforms the joint equalization using a traditional decision feedback as ANN is able to compensate the non-linear transfer function as well as cross talk.

AB - The limited bandwidth of white light-emitting diode (LED) limits the achievable data rate in a visible light communication (VLC) system. A number of techniques, including multiple-input-multiple-output (MIMO) system, are investigated to increase the data rate. The high-speed optical MIMO system suffers from both spatial and temporal cross talks. The spatial cross-talk is often compensated by the MIMO decoding algorithm, while the temporal cross talk is mitigated using an equalizer. However, the LEDs have a non-linear transfer function and the performance of linear equalizers are limited. In this letter, we propose a joint spatial and temporal equalization using an artificial neural network (ANN) for an MIMO-VLC system. We demonstrate using a practical imaging/non-imaging optical MIMO link that the ANN-based joint equalization outperforms the joint equalization using a traditional decision feedback as ANN is able to compensate the non-linear transfer function as well as cross talk.

KW - visible light communications

KW - multiple input multiple output

KW - MIMO

KW - joint equalization

KW - artificial neural network

KW - non-linear transfer function

U2 - 10.1109/LPT.2019.2909139

DO - 10.1109/LPT.2019.2909139

M3 - Article

VL - 31

SP - 821

EP - 824

JO - IEEE Photonics Technology Letters

T2 - IEEE Photonics Technology Letters

JF - IEEE Photonics Technology Letters

SN - 1041-1135

IS - 11

ER -