Deep learning based transceiver design for multi-colored VLC systems

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

This paper presents a deep-learning (DL) based approach to the design of multicolored visible light communication (VLC) systems where RGB light-emitting diode (LED) lamps accomplish multi-dimensional color modulation under color and illuminance requirements. It is aimed to identify a pair of multi-color modulation transmitter and receiver leading to e cient symbol recovery performance. To this end, an autoencoder (AE), an unsupervised deep learning technique, is adopted to train the end-to-end symbol recovery process that includes the VLC transceiver pair and a channel layer characterizing the optical channel along with additional LED intensity control features. As a result, the VLC transmitter and receiver are jointly designed and optimized. Intensive numerical results demonstrate that the learned VLC system outperforms existing techniques in terms of the average symbol error probability. This framework sheds light on the viability of DL techniques in the optical communication system design.

Original languageEnglish
Pages (from-to)6222-6238
Number of pages17
JournalOptics Express
Volume26
Issue number5
DOIs
Publication statusPublished - 2018 Mar 5

Fingerprint

transmitter receivers
learning
optical communication
telecommunication
color
transmitters
light emitting diodes
receivers
recovery
modulation
illuminance
viability
systems engineering
luminaires
requirements

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics

Cite this

Deep learning based transceiver design for multi-colored VLC systems. / Lee, Hoon; Lee, Inkyu; Lee, Sang Hyun.

In: Optics Express, Vol. 26, No. 5, 05.03.2018, p. 6222-6238.

Research output: Contribution to journalArticle

@article{088d5098ab974fa69edfab4f6d75bbaf,
title = "Deep learning based transceiver design for multi-colored VLC systems",
abstract = "This paper presents a deep-learning (DL) based approach to the design of multicolored visible light communication (VLC) systems where RGB light-emitting diode (LED) lamps accomplish multi-dimensional color modulation under color and illuminance requirements. It is aimed to identify a pair of multi-color modulation transmitter and receiver leading to e cient symbol recovery performance. To this end, an autoencoder (AE), an unsupervised deep learning technique, is adopted to train the end-to-end symbol recovery process that includes the VLC transceiver pair and a channel layer characterizing the optical channel along with additional LED intensity control features. As a result, the VLC transmitter and receiver are jointly designed and optimized. Intensive numerical results demonstrate that the learned VLC system outperforms existing techniques in terms of the average symbol error probability. This framework sheds light on the viability of DL techniques in the optical communication system design.",
author = "Hoon Lee and Inkyu Lee and Lee, {Sang Hyun}",
year = "2018",
month = "3",
day = "5",
doi = "10.1364/OE.26.006222",
language = "English",
volume = "26",
pages = "6222--6238",
journal = "Optics Express",
issn = "1094-4087",
publisher = "The Optical Society",
number = "5",

}

TY - JOUR

T1 - Deep learning based transceiver design for multi-colored VLC systems

AU - Lee, Hoon

AU - Lee, Inkyu

AU - Lee, Sang Hyun

PY - 2018/3/5

Y1 - 2018/3/5

N2 - This paper presents a deep-learning (DL) based approach to the design of multicolored visible light communication (VLC) systems where RGB light-emitting diode (LED) lamps accomplish multi-dimensional color modulation under color and illuminance requirements. It is aimed to identify a pair of multi-color modulation transmitter and receiver leading to e cient symbol recovery performance. To this end, an autoencoder (AE), an unsupervised deep learning technique, is adopted to train the end-to-end symbol recovery process that includes the VLC transceiver pair and a channel layer characterizing the optical channel along with additional LED intensity control features. As a result, the VLC transmitter and receiver are jointly designed and optimized. Intensive numerical results demonstrate that the learned VLC system outperforms existing techniques in terms of the average symbol error probability. This framework sheds light on the viability of DL techniques in the optical communication system design.

AB - This paper presents a deep-learning (DL) based approach to the design of multicolored visible light communication (VLC) systems where RGB light-emitting diode (LED) lamps accomplish multi-dimensional color modulation under color and illuminance requirements. It is aimed to identify a pair of multi-color modulation transmitter and receiver leading to e cient symbol recovery performance. To this end, an autoencoder (AE), an unsupervised deep learning technique, is adopted to train the end-to-end symbol recovery process that includes the VLC transceiver pair and a channel layer characterizing the optical channel along with additional LED intensity control features. As a result, the VLC transmitter and receiver are jointly designed and optimized. Intensive numerical results demonstrate that the learned VLC system outperforms existing techniques in terms of the average symbol error probability. This framework sheds light on the viability of DL techniques in the optical communication system design.

UR - http://www.scopus.com/inward/record.url?scp=85042844567&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042844567&partnerID=8YFLogxK

U2 - 10.1364/OE.26.006222

DO - 10.1364/OE.26.006222

M3 - Article

AN - SCOPUS:85042844567

VL - 26

SP - 6222

EP - 6238

JO - Optics Express

JF - Optics Express

SN - 1094-4087

IS - 5

ER -