TY - JOUR
T1 - A Deep Learning Approach to Universal Binary Visible Light Communication Transceiver
AU - Lee, Hoon
AU - Quek, Tony Q.S.
AU - Lee, Sang Hyun
N1 - Funding Information:
Manuscript received July 21, 2019; revised October 9, 2019; accepted October 22, 2019. Date of publication November 5, 2019; date of current version February 11, 2020. This work was supported in part by the National Research Foundation of Korea (NRF) Grant funded by the Korea Government (MSIT) under Grant 2019R1F1A1060648 and Grant 2019R1A2C1084855, in part by the Korea University Grant, in part by the SUTD Growth Plan Grant for AI, and in part by the SUTD-ZJU Research Collaboration under Grant SUTD-ZJU/RES/05/2016. This article is to be presented in part at the IEEE Global Communications Conference Workshop 2019, HI, USA, December 2019 [1]. The associate editor coordinating the review of this article and approving it for publication was J. Hoydis. (Corresponding author: Sang Hyun Lee.) H. Lee is with the Department of Information and Communications Engineering, Pukyong National University, Busan 48513, South Korea (e-mail: [email protected]).
Publisher Copyright:
© 2002-2012 IEEE.
PY - 2020/2
Y1 - 2020/2
N2 - This paper studies a deep learning (DL) framework for the design of binary modulated visible light communication (VLC) transceiver with universal dimming support. The dimming control for the optical binary signal boils down to a combinatorial codebook design so that the average Hamming weight of binary codewords matches with arbitrary dimming target. An unsupervised DL technique is employed for obtaining a neural network to replace the encoder-decoder pair that recovers the message from the optically transmitted signal. In such a task, a novel stochastic binarization method is developed to generate the set of binary codewords from continuous-valued neural network outputs. For universal support of arbitrary dimming target, the DL-based VLC transceiver is trained with multiple dimming constraints, which turns out to be a constrained training optimization that is very challenging to handle with existing DL methods. We develop a new training algorithm that addresses the dimming constraints through a dual formulation of the optimization. Based on the developed algorithm, the resulting VLC transceiver can be optimized via the end-to-end training procedure. Numerical results verify that the proposed codebook outperforms theoretically best constant weight codebooks under various VLC setups.
AB - This paper studies a deep learning (DL) framework for the design of binary modulated visible light communication (VLC) transceiver with universal dimming support. The dimming control for the optical binary signal boils down to a combinatorial codebook design so that the average Hamming weight of binary codewords matches with arbitrary dimming target. An unsupervised DL technique is employed for obtaining a neural network to replace the encoder-decoder pair that recovers the message from the optically transmitted signal. In such a task, a novel stochastic binarization method is developed to generate the set of binary codewords from continuous-valued neural network outputs. For universal support of arbitrary dimming target, the DL-based VLC transceiver is trained with multiple dimming constraints, which turns out to be a constrained training optimization that is very challenging to handle with existing DL methods. We develop a new training algorithm that addresses the dimming constraints through a dual formulation of the optimization. Based on the developed algorithm, the resulting VLC transceiver can be optimized via the end-to-end training procedure. Numerical results verify that the proposed codebook outperforms theoretically best constant weight codebooks under various VLC setups.
UR - http://www.scopus.com/inward/record.url?scp=85079793600&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85079793600&partnerID=8YFLogxK
U2 - 10.1109/TWC.2019.2950026
DO - 10.1109/TWC.2019.2950026
M3 - Article
AN - SCOPUS:85079793600
SN - 1536-1276
VL - 19
SP - 956
EP - 969
JO - IEEE Transactions on Wireless Communications
JF - IEEE Transactions on Wireless Communications
IS - 2
M1 - 8891920
ER -