Binary signaling design for visible light communication: a deep learning framework

Hoon Lee; Inkyu Lee; Tony Q. S. Quek; Sang Hyun Lee

doi:10.1364/OE.26.018131

Abstract

This paper develops a deep learning framework for the design of on-off keying (OOK) based binary signaling transceiver in dimmable visible light communication (VLC) systems. The dimming support for the OOK optical signal is achieved by adjusting the number of ones in a binary codeword, which boils down to a combinatorial design problem for the codebook of a constant weight code (CWC) over signal-dependent noise channels. To tackle this challenge, we employ an autoencoder (AE) approach to learn a neural network of the encoder-decoder pair that reconstructs the output identical to an input. In addition, optical channel layers and binarization techniques are introduced to reflect the physical and discrete nature of the OOK-based VLC systems. The VLC transceiver is designed and optimized via the end-to-end training procedure for the AE. Numerical results verify that the proposed transceiver performs better than baseline CWC schemes.

Full Article | PDF Article

OSA Recommended Articles

Deep learning based transceiver design for multi-colored VLC systems

Hoon Lee, Inkyu Lee, and Sang Hyun Lee
Opt. Express 26(5) 6222-6238 (2018)

Efficient hierarchical list decoder for massive optical MIMO Transmission

Maxim Greenberg, Moshe Nazarathy, and Meir Orenstein
Opt. Express 16(2) 718-724 (2008)

On the Time Dynamics of Optical Communication Through Atmospheric Turbulence With Feedback

Andrew Puryear and Vincent W. S. Chan
J. Opt. Commun. Netw. 3(8) 594-609 (2011)

References

View by:
Article Order
|
Year
|
Author
|
Publication

T. Komine and M. Nakagawa, “Fundamental analysis for visible light communication system using LED light,” IEEE Trans. Consum. Electron. 56(1), 100–107 (2004).
[Crossref]
S. H. Lee, S.-Y. Jung, and J. K. Kwon, “Modulation and coding for dimmable visible light communication,” IEEE Commun. Mag. 53(2), 136–143 (2015).
[Crossref]
S. Kim and S.-Y. Jung, “Novel FEC coding scheme for dimmable visible light communication based on the modified Reed. Muller codes,” IEEE Photon. Techno. Lett. 23(20), 1514–1516 (2011).
[Crossref]
S. H. Lee and J. K. Kwon, “Turbo code-based error correction scheme for dimmable visible light communication systems,” IEEE Photon. Techno. Lett. 24(17), 1463–1465 (2012).
[Crossref]
S. Zhao, “A serial concatenation-based coding scheme for dimmable visible light communication systems,” IEEE Commun. Lett. 20(10), 1951–1954 (2016).
[Crossref]
C. E. Mejia, C. N. Georghiades, M. M. Abdallah, and Y. H. Al-Badarneh, “Code design for flicker mitigation in visible light communications using finite state machines,” IEEE Trans. Commun. 65(5), 2091–2100 (2017).
[Crossref]
P. Ostergard, “Classification of binary constant weight codes,” IEEE Trans. Inf. Theory 56(8), 3779–3785 (2010).
[Crossref]
H. Lee, I. Lee, and S. H. Lee, “Deep learning based transceiver design for multi-colored VLC systems,” Opt. Express 26(5), 6222–6238 (2018).
[Crossref] [PubMed]
T. O’Shea and J. Hoydis, “An introduction to deep learning for the physical layer,” IEEE Trans. Cogn. Commun. Netw. 3(4), 563–575 (2017).
[Crossref]
S. Dorner, S. Cammer, J. Hoydis, and S. Brink, “Deep learning based communication over the air,” IEEE J. Sel. Topics Signal Process. 12(1), 132–143 (2017).
[Crossref]
O. Vinyals, S. Bengio, and M. Kudlur, “Order matters: sequence to sequence for sets,” in Proccedings of International Conference on Learning Representations (ICLR, 2016).
A. Siddique and M. Tahir, “Joint error-brightness control coding for LED based VLC link,” in Proccedings of Wireless Communications and Networking Conference (IEEE, 2014), pp. 400–404.
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature 512(7553), 436–444 (2015).
[Crossref]
Z. Cao, M. Long, J. Wang, and P. Yu, “HashNet: deep learning to hash by continuation,” in Proccedings of IEEE International Conferenece on Computer Vision (ICCV, 2017).
D. Kingma and J. Ba, “Adam: a method for stochastic optimization,” in).Proccedings of International Conference on Learning Representations (ICLR, 2015).

2018 (1)

H. Lee, I. Lee, and S. H. Lee, “Deep learning based transceiver design for multi-colored VLC systems,” Opt. Express 26(5), 6222–6238 (2018).
[Crossref] [PubMed]

2017 (3)

T. O’Shea and J. Hoydis, “An introduction to deep learning for the physical layer,” IEEE Trans. Cogn. Commun. Netw. 3(4), 563–575 (2017).
[Crossref]

S. Dorner, S. Cammer, J. Hoydis, and S. Brink, “Deep learning based communication over the air,” IEEE J. Sel. Topics Signal Process. 12(1), 132–143 (2017).
[Crossref]

C. E. Mejia, C. N. Georghiades, M. M. Abdallah, and Y. H. Al-Badarneh, “Code design for flicker mitigation in visible light communications using finite state machines,” IEEE Trans. Commun. 65(5), 2091–2100 (2017).
[Crossref]

2016 (1)

S. Zhao, “A serial concatenation-based coding scheme for dimmable visible light communication systems,” IEEE Commun. Lett. 20(10), 1951–1954 (2016).
[Crossref]

2015 (2)

Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature 512(7553), 436–444 (2015).
[Crossref]

S. H. Lee, S.-Y. Jung, and J. K. Kwon, “Modulation and coding for dimmable visible light communication,” IEEE Commun. Mag. 53(2), 136–143 (2015).
[Crossref]

2012 (1)

S. H. Lee and J. K. Kwon, “Turbo code-based error correction scheme for dimmable visible light communication systems,” IEEE Photon. Techno. Lett. 24(17), 1463–1465 (2012).
[Crossref]

2011 (1)

S. Kim and S.-Y. Jung, “Novel FEC coding scheme for dimmable visible light communication based on the modified Reed. Muller codes,” IEEE Photon. Techno. Lett. 23(20), 1514–1516 (2011).
[Crossref]

2010 (1)

P. Ostergard, “Classification of binary constant weight codes,” IEEE Trans. Inf. Theory 56(8), 3779–3785 (2010).
[Crossref]

2004 (1)

T. Komine and M. Nakagawa, “Fundamental analysis for visible light communication system using LED light,” IEEE Trans. Consum. Electron. 56(1), 100–107 (2004).
[Crossref]

Abdallah, M. M.

C. E. Mejia, C. N. Georghiades, M. M. Abdallah, and Y. H. Al-Badarneh, “Code design for flicker mitigation in visible light communications using finite state machines,” IEEE Trans. Commun. 65(5), 2091–2100 (2017).
[Crossref]

Al-Badarneh, Y. H.

C. E. Mejia, C. N. Georghiades, M. M. Abdallah, and Y. H. Al-Badarneh, “Code design for flicker mitigation in visible light communications using finite state machines,” IEEE Trans. Commun. 65(5), 2091–2100 (2017).
[Crossref]

Ba, J.

D. Kingma and J. Ba, “Adam: a method for stochastic optimization,” in).Proccedings of International Conference on Learning Representations (ICLR, 2015).

Bengio, S.

O. Vinyals, S. Bengio, and M. Kudlur, “Order matters: sequence to sequence for sets,” in Proccedings of International Conference on Learning Representations (ICLR, 2016).

Bengio, Y.

Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature 512(7553), 436–444 (2015).
[Crossref]

Brink, S.

S. Dorner, S. Cammer, J. Hoydis, and S. Brink, “Deep learning based communication over the air,” IEEE J. Sel. Topics Signal Process. 12(1), 132–143 (2017).
[Crossref]

Cammer, S.

S. Dorner, S. Cammer, J. Hoydis, and S. Brink, “Deep learning based communication over the air,” IEEE J. Sel. Topics Signal Process. 12(1), 132–143 (2017).
[Crossref]

Cao, Z.

Z. Cao, M. Long, J. Wang, and P. Yu, “HashNet: deep learning to hash by continuation,” in Proccedings of IEEE International Conferenece on Computer Vision (ICCV, 2017).

Dorner, S.

S. Dorner, S. Cammer, J. Hoydis, and S. Brink, “Deep learning based communication over the air,” IEEE J. Sel. Topics Signal Process. 12(1), 132–143 (2017).
[Crossref]

Georghiades, C. N.

C. E. Mejia, C. N. Georghiades, M. M. Abdallah, and Y. H. Al-Badarneh, “Code design for flicker mitigation in visible light communications using finite state machines,” IEEE Trans. Commun. 65(5), 2091–2100 (2017).
[Crossref]

Hinton, G.

Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature 512(7553), 436–444 (2015).
[Crossref]

Hoydis, J.

S. Dorner, S. Cammer, J. Hoydis, and S. Brink, “Deep learning based communication over the air,” IEEE J. Sel. Topics Signal Process. 12(1), 132–143 (2017).
[Crossref]

T. O’Shea and J. Hoydis, “An introduction to deep learning for the physical layer,” IEEE Trans. Cogn. Commun. Netw. 3(4), 563–575 (2017).
[Crossref]

Jung, S.-Y.

S. H. Lee, S.-Y. Jung, and J. K. Kwon, “Modulation and coding for dimmable visible light communication,” IEEE Commun. Mag. 53(2), 136–143 (2015).
[Crossref]

S. Kim and S.-Y. Jung, “Novel FEC coding scheme for dimmable visible light communication based on the modified Reed. Muller codes,” IEEE Photon. Techno. Lett. 23(20), 1514–1516 (2011).
[Crossref]

Kim, S.

S. Kim and S.-Y. Jung, “Novel FEC coding scheme for dimmable visible light communication based on the modified Reed. Muller codes,” IEEE Photon. Techno. Lett. 23(20), 1514–1516 (2011).
[Crossref]

Kingma, D.

D. Kingma and J. Ba, “Adam: a method for stochastic optimization,” in).Proccedings of International Conference on Learning Representations (ICLR, 2015).

Komine, T.

T. Komine and M. Nakagawa, “Fundamental analysis for visible light communication system using LED light,” IEEE Trans. Consum. Electron. 56(1), 100–107 (2004).
[Crossref]

Kudlur, M.

O. Vinyals, S. Bengio, and M. Kudlur, “Order matters: sequence to sequence for sets,” in Proccedings of International Conference on Learning Representations (ICLR, 2016).

Kwon, J. K.

S. H. Lee, S.-Y. Jung, and J. K. Kwon, “Modulation and coding for dimmable visible light communication,” IEEE Commun. Mag. 53(2), 136–143 (2015).
[Crossref]

S. H. Lee and J. K. Kwon, “Turbo code-based error correction scheme for dimmable visible light communication systems,” IEEE Photon. Techno. Lett. 24(17), 1463–1465 (2012).
[Crossref]

LeCun, Y.

Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature 512(7553), 436–444 (2015).
[Crossref]

S. H. Lee, S.-Y. Jung, and J. K. Kwon, “Modulation and coding for dimmable visible light communication,” IEEE Commun. Mag. 53(2), 136–143 (2015).
[Crossref]

S. H. Lee and J. K. Kwon, “Turbo code-based error correction scheme for dimmable visible light communication systems,” IEEE Photon. Techno. Lett. 24(17), 1463–1465 (2012).
[Crossref]

Long, M.

Z. Cao, M. Long, J. Wang, and P. Yu, “HashNet: deep learning to hash by continuation,” in Proccedings of IEEE International Conferenece on Computer Vision (ICCV, 2017).

Mejia, C. E.

C. E. Mejia, C. N. Georghiades, M. M. Abdallah, and Y. H. Al-Badarneh, “Code design for flicker mitigation in visible light communications using finite state machines,” IEEE Trans. Commun. 65(5), 2091–2100 (2017).
[Crossref]

Nakagawa, M.

T. Komine and M. Nakagawa, “Fundamental analysis for visible light communication system using LED light,” IEEE Trans. Consum. Electron. 56(1), 100–107 (2004).
[Crossref]

O’Shea, T.

T. O’Shea and J. Hoydis, “An introduction to deep learning for the physical layer,” IEEE Trans. Cogn. Commun. Netw. 3(4), 563–575 (2017).
[Crossref]

Ostergard, P.

P. Ostergard, “Classification of binary constant weight codes,” IEEE Trans. Inf. Theory 56(8), 3779–3785 (2010).
[Crossref]

Siddique, A.

A. Siddique and M. Tahir, “Joint error-brightness control coding for LED based VLC link,” in Proccedings of Wireless Communications and Networking Conference (IEEE, 2014), pp. 400–404.

Tahir, M.

A. Siddique and M. Tahir, “Joint error-brightness control coding for LED based VLC link,” in Proccedings of Wireless Communications and Networking Conference (IEEE, 2014), pp. 400–404.

Vinyals, O.

O. Vinyals, S. Bengio, and M. Kudlur, “Order matters: sequence to sequence for sets,” in Proccedings of International Conference on Learning Representations (ICLR, 2016).

Wang, J.

Z. Cao, M. Long, J. Wang, and P. Yu, “HashNet: deep learning to hash by continuation,” in Proccedings of IEEE International Conferenece on Computer Vision (ICCV, 2017).

Yu, P.

Z. Cao, M. Long, J. Wang, and P. Yu, “HashNet: deep learning to hash by continuation,” in Proccedings of IEEE International Conferenece on Computer Vision (ICCV, 2017).

Zhao, S.

S. Zhao, “A serial concatenation-based coding scheme for dimmable visible light communication systems,” IEEE Commun. Lett. 20(10), 1951–1954 (2016).
[Crossref]

IEEE Commun. Lett. (1)

S. Zhao, “A serial concatenation-based coding scheme for dimmable visible light communication systems,” IEEE Commun. Lett. 20(10), 1951–1954 (2016).
[Crossref]

IEEE Commun. Mag. (1)

S. H. Lee, S.-Y. Jung, and J. K. Kwon, “Modulation and coding for dimmable visible light communication,” IEEE Commun. Mag. 53(2), 136–143 (2015).
[Crossref]

IEEE J. Sel. Topics Signal Process. (1)

S. Dorner, S. Cammer, J. Hoydis, and S. Brink, “Deep learning based communication over the air,” IEEE J. Sel. Topics Signal Process. 12(1), 132–143 (2017).
[Crossref]

IEEE Photon. Techno. Lett. (2)

S. Kim and S.-Y. Jung, “Novel FEC coding scheme for dimmable visible light communication based on the modified Reed. Muller codes,” IEEE Photon. Techno. Lett. 23(20), 1514–1516 (2011).
[Crossref]

S. H. Lee and J. K. Kwon, “Turbo code-based error correction scheme for dimmable visible light communication systems,” IEEE Photon. Techno. Lett. 24(17), 1463–1465 (2012).
[Crossref]

IEEE Trans. Cogn. Commun. Netw. (1)

T. O’Shea and J. Hoydis, “An introduction to deep learning for the physical layer,” IEEE Trans. Cogn. Commun. Netw. 3(4), 563–575 (2017).
[Crossref]

IEEE Trans. Commun. (1)

C. E. Mejia, C. N. Georghiades, M. M. Abdallah, and Y. H. Al-Badarneh, “Code design for flicker mitigation in visible light communications using finite state machines,” IEEE Trans. Commun. 65(5), 2091–2100 (2017).
[Crossref]

IEEE Trans. Consum. Electron. (1)

T. Komine and M. Nakagawa, “Fundamental analysis for visible light communication system using LED light,” IEEE Trans. Consum. Electron. 56(1), 100–107 (2004).
[Crossref]

IEEE Trans. Inf. Theory (1)

P. Ostergard, “Classification of binary constant weight codes,” IEEE Trans. Inf. Theory 56(8), 3779–3785 (2010).
[Crossref]

Nature (1)

Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature 512(7553), 436–444 (2015).
[Crossref]

Opt. Express (1)

H. Lee, I. Lee, and S. H. Lee, “Deep learning based transceiver design for multi-colored VLC systems,” Opt. Express 26(5), 6222–6238 (2018).
[Crossref] [PubMed]

Other (4)

Z. Cao, M. Long, J. Wang, and P. Yu, “HashNet: deep learning to hash by continuation,” in Proccedings of IEEE International Conferenece on Computer Vision (ICCV, 2017).

D. Kingma and J. Ba, “Adam: a method for stochastic optimization,” in).Proccedings of International Conference on Learning Representations (ICLR, 2015).

O. Vinyals, S. Bengio, and M. Kudlur, “Order matters: sequence to sequence for sets,” in Proccedings of International Conference on Learning Representations (ICLR, 2016).

A. Siddique and M. Tahir, “Joint error-brightness control coding for LED based VLC link,” in Proccedings of Wireless Communications and Networking Conference (IEEE, 2014), pp. 400–404.

Cited By

OSA participates in Crossref's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.

Click here to see a list of articles that cite this paper

Fig. 1 System model for OOK-based dimmable VLC.

Download Full Size | PPT Slide | PDF

Fig. 2 AE structure for OOK-based dimmable VLC.

Download Full Size | PPT Slide | PDF

Fig. 3 Sigmoid activation with different δ.

Download Full Size | PPT Slide | PDF

Fig. 4 Multi-stage training strategy for dimming constraint.

Download Full Size | PPT Slide | PDF

Fig. 5 Convergence behavior of AE with different binarization methods for W = k = 5, ψ² = 0, and SNR = 10 dB.

Download Full Size | PPT Slide | PDF

Fig. 6 Average SER performance as a function of SNR with ψ² = 0 and 5 for W = 4.

Download Full Size | PPT Slide | PDF

Fig. 7 Average SER performance as a function of SNR with ψ² = 0 and 5 for W = 5.

Download Full Size | PPT Slide | PDF

Tables (2)

Table 1 Proposed multi-stage training strategy.

View Table | View all tables in this article

Table 2 Minimum Hamming distance for ψ² = 0.

View Table | View all tables in this article

Equations (8)

Equations on this page are rendered with MathJax. Learn more.

\sum_{i = 1}^{N} {[s_{b}]}_{i} = W, for s_{b} \in S .

y = s_{b} + n_{t h} + n_{s h},

x_{l} = f_{l} (W_{l} x_{l - 1} + b_{l}), for l = 1, \dots, L,

\min_{Θ} C (Θ) ≜ \frac{1}{J} \sum_{j \in J} c (x_{0}^{(j)}, x_{L}^{(j)}),

Θ_{t} = Θ_{t - 1} - η \nabla C (Θ_{t - 1}),

{[s_{b}]}_{i} = \frac{1}{1 + e^{- δ {[x_{2}]}_{i}}}, for i = 1, \dots, N .

{[p]}_{m} = \frac{e^{{[z]}_{m}}}{\sum_{q = 1}^{M} e^{{[z]}_{q}}}, for m = 1, \dots, M,

C (Θ) = \frac{1}{J} \sum_{j = 1}^{J} \log ({[p]}_{b^{(j)}}) + \frac{λ}{J} \sum_{j = 1}^{J} {(\sum_{i = 1}^{N} {[s_{b^{(j)}}]}_{i} - W)}^{2},

Multi-stage training strategy
Initialize Θ[⁰] and {δ[g} such tat δ[1] < ⋯ < δ[G].
for = g = 1: G
Set the initial point of the SGD algorithm to Θ₀ = Θ[g − 1].
Train (8) with δ = δ[g] from (5) until convergence.
Obtain the learned parameter Θ[g] of the AE.
end

	Optimal [7]				AE
k\W	3	4	5	6	3	4	5	6
4	4	4	4	6	4	4	4	6
5	2	4	4	4	2	4	4	4
6	2	2	4	4	2	2	4	4

Multi-stage training strategy
Initialize Θ[⁰] and {δ[g} such tat δ[1] < ⋯ < δ[G].
for = g = 1: G
Set the initial point of the SGD algorithm to Θ₀ = Θ[g − 1].
Train (8) with δ = δ[g] from (5) until convergence.
Obtain the learned parameter Θ[g] of the AE.
end

	Optimal [7]				AE
k\W	3	4	5	6	3	4	5	6
4	4	4	4	6	4	4	4	6
5	2	4	4	4	2	4	4	4
6	2	2	4	4	2	2	4	4

Abstract

References

2018 (1)

2017 (3)

2016 (1)

2015 (2)

2012 (1)

2011 (1)

2010 (1)

2004 (1)

Abdallah, M. M.

Al-Badarneh, Y. H.

Ba, J.

Bengio, S.

Bengio, Y.

Brink, S.

Cammer, S.

Cao, Z.

Dorner, S.

Georghiades, C. N.

Hinton, G.

Hoydis, J.

Jung, S.-Y.

Kim, S.

Kingma, D.

Komine, T.

Kudlur, M.

Kwon, J. K.

LeCun, Y.

Lee, H.

Lee, I.

Lee, S. H.

Long, M.

Mejia, C. E.

Nakagawa, M.

O’Shea, T.

Ostergard, P.

Siddique, A.

Tahir, M.

Vinyals, O.

Wang, J.

Yu, P.

Zhao, S.

IEEE Commun. Lett. (1)

IEEE Commun. Mag. (1)

IEEE J. Sel. Topics Signal Process. (1)

IEEE Photon. Techno. Lett. (2)

IEEE Trans. Cogn. Commun. Netw. (1)

IEEE Trans. Commun. (1)

IEEE Trans. Consum. Electron. (1)

IEEE Trans. Inf. Theory (1)

Nature (1)

Opt. Express (1)

Other (4)

Cited By

Figures (7)

Tables (2)

Equations (8)

Metrics

Login or Create Account