Performance Evaluation of Various Training Algorithms for ANN Equalization in Visible Light Communications with an Organic LED

Zahra Nazari Chaleshtori; Paul A. Haigh; Petr Chvojka; Stanislav Zvanovec; Zabih Ghassemlooy

doi:10.1109/WACOWC.2019.8770203

Performance Evaluation of Various Training Algorithms for ANN Equalization in Visible Light Communications with an Organic LED

Zahra Nazari Chaleshtori, Paul A. Haigh, Petr Chvojka, Stanislav Zvanovec, Zabih Ghassemlooy

Mathematics, Physics and Electrical Engineering

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

5 Citations (Scopus)

19 Downloads (Pure)

Abstract

This paper evaluates the effect of training algorithms in an artificial neural network (ANN) equalizer for a feedforward multi-layer perceptron configuration in visible light communication systems using a low bandwidth organic light source. We test the scaled conjugate-gradient, conjugate-gradient backpropagation and Levenberg-Marquardt back propagation (LM) algorithms with 5, 10, 20, 30, and 40 neurons. We show that, LM offers superior bit error rate performance in comparison to other training algorithms based on the mean square error. The training methods can be selected based on the trade-off between complexity and performance.

Original language	English
Title of host publication	The 2nd West Asian Colloquium on Optical Wireless Communications (WACOWC2019)
Subtitle of host publication	27-28 April, Shahid Beheshti University, Tehran, Iran
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	11-15
Number of pages	5
ISBN (Electronic)	9781728137674
ISBN (Print)	9781728137681
DOIs	https://doi.org/10.1109/WACOWC.2019.8770203
Publication status	Published - Apr 2019
Event	2019 2nd West Asian Colloquium on Optical Wireless Communications (WACOWC) - Tehran, Iran Duration: 27 Apr 2019 → 28 Apr 2019

Conference

Conference	2019 2nd West Asian Colloquium on Optical Wireless Communications (WACOWC)
Period	27/04/19 → 28/04/19

Keywords

Artificial neural network equalizer
Equalization
Organic LEDs
Visible light communications

Access to Document

10.1109/WACOWC.2019.8770203

wacowc2019-final-19.3.2019Accepted author manuscript, 1 MB

Cite this

Nazari Chaleshtori, Z., Haigh, P. A., Chvojka, P., Zvanovec, S., & Ghassemlooy, Z. (2019). Performance Evaluation of Various Training Algorithms for ANN Equalization in Visible Light Communications with an Organic LED. In The 2nd West Asian Colloquium on Optical Wireless Communications (WACOWC2019): 27-28 April, Shahid Beheshti University, Tehran, Iran (pp. 11-15). Article 8770203 IEEE. https://doi.org/10.1109/WACOWC.2019.8770203

@inproceedings{0712f466f1c44546a59f32f66063d2af,

title = "Performance Evaluation of Various Training Algorithms for ANN Equalization in Visible Light Communications with an Organic LED",

abstract = "This paper evaluates the effect of training algorithms in an artificial neural network (ANN) equalizer for a feedforward multi-layer perceptron configuration in visible light communication systems using a low bandwidth organic light source. We test the scaled conjugate-gradient, conjugate-gradient backpropagation and Levenberg-Marquardt back propagation (LM) algorithms with 5, 10, 20, 30, and 40 neurons. We show that, LM offers superior bit error rate performance in comparison to other training algorithms based on the mean square error. The training methods can be selected based on the trade-off between complexity and performance.",

keywords = "Artificial neural network equalizer, Equalization, Organic LEDs, Visible light communications",

author = "{Nazari Chaleshtori}, Zahra and Haigh, {Paul A.} and Petr Chvojka and Stanislav Zvanovec and Zabih Ghassemlooy",

note = "Funding information: The work is supported by the European Union{\textquoteright}s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement no 764461 (VISION), the Czech Republic funded project GACR 17-17538S, and the UK EPSRC research grant EP/P006280/1: Multifunctional Polymer Light-Emitting Diodes with Visible Light Communications (MARVEL).; 2019 2nd West Asian Colloquium on Optical Wireless Communications (WACOWC) ; Conference date: 27-04-2019 Through 28-04-2019",

year = "2019",

month = apr,

doi = "10.1109/WACOWC.2019.8770203",

language = "English",

isbn = "9781728137681",

pages = "11--15",

booktitle = "The 2nd West Asian Colloquium on Optical Wireless Communications (WACOWC2019)",

publisher = "IEEE",

address = "United States",

}

Nazari Chaleshtori, Z, Haigh, PA, Chvojka, P, Zvanovec, S & Ghassemlooy, Z 2019, Performance Evaluation of Various Training Algorithms for ANN Equalization in Visible Light Communications with an Organic LED. in The 2nd West Asian Colloquium on Optical Wireless Communications (WACOWC2019): 27-28 April, Shahid Beheshti University, Tehran, Iran., 8770203, IEEE, Piscataway, NJ, pp. 11-15, 2019 2nd West Asian Colloquium on Optical Wireless Communications (WACOWC), 27/04/19. https://doi.org/10.1109/WACOWC.2019.8770203

Performance Evaluation of Various Training Algorithms for ANN Equalization in Visible Light Communications with an Organic LED. / Nazari Chaleshtori, Zahra; Haigh, Paul A.; Chvojka, Petr et al.
The 2nd West Asian Colloquium on Optical Wireless Communications (WACOWC2019): 27-28 April, Shahid Beheshti University, Tehran, Iran. Piscataway, NJ: IEEE, 2019. p. 11-15 8770203.

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

TY - GEN

T1 - Performance Evaluation of Various Training Algorithms for ANN Equalization in Visible Light Communications with an Organic LED

AU - Nazari Chaleshtori, Zahra

AU - Haigh, Paul A.

AU - Chvojka, Petr

AU - Zvanovec, Stanislav

AU - Ghassemlooy, Zabih

N1 - Funding information: The work is supported by the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement no 764461 (VISION), the Czech Republic funded project GACR 17-17538S, and the UK EPSRC research grant EP/P006280/1: Multifunctional Polymer Light-Emitting Diodes with Visible Light Communications (MARVEL).

PY - 2019/4

Y1 - 2019/4

N2 - This paper evaluates the effect of training algorithms in an artificial neural network (ANN) equalizer for a feedforward multi-layer perceptron configuration in visible light communication systems using a low bandwidth organic light source. We test the scaled conjugate-gradient, conjugate-gradient backpropagation and Levenberg-Marquardt back propagation (LM) algorithms with 5, 10, 20, 30, and 40 neurons. We show that, LM offers superior bit error rate performance in comparison to other training algorithms based on the mean square error. The training methods can be selected based on the trade-off between complexity and performance.

AB - This paper evaluates the effect of training algorithms in an artificial neural network (ANN) equalizer for a feedforward multi-layer perceptron configuration in visible light communication systems using a low bandwidth organic light source. We test the scaled conjugate-gradient, conjugate-gradient backpropagation and Levenberg-Marquardt back propagation (LM) algorithms with 5, 10, 20, 30, and 40 neurons. We show that, LM offers superior bit error rate performance in comparison to other training algorithms based on the mean square error. The training methods can be selected based on the trade-off between complexity and performance.

KW - Artificial neural network equalizer

KW - Equalization

KW - Organic LEDs

KW - Visible light communications

UR - http://www.scopus.com/inward/record.url?scp=85073901826&partnerID=8YFLogxK

U2 - 10.1109/WACOWC.2019.8770203

DO - 10.1109/WACOWC.2019.8770203

M3 - Conference contribution

SN - 9781728137681

SP - 11

EP - 15

BT - The 2nd West Asian Colloquium on Optical Wireless Communications (WACOWC2019)

PB - IEEE

CY - Piscataway, NJ

T2 - 2019 2nd West Asian Colloquium on Optical Wireless Communications (WACOWC)

Y2 - 27 April 2019 through 28 April 2019

ER -

Nazari Chaleshtori Z, Haigh PA, Chvojka P, Zvanovec S, Ghassemlooy Z. Performance Evaluation of Various Training Algorithms for ANN Equalization in Visible Light Communications with an Organic LED. In The 2nd West Asian Colloquium on Optical Wireless Communications (WACOWC2019): 27-28 April, Shahid Beheshti University, Tehran, Iran. Piscataway, NJ: IEEE. 2019. p. 11-15. 8770203 doi: 10.1109/WACOWC.2019.8770203

Performance Evaluation of Various Training Algorithms for ANN Equalization in Visible Light Communications with an Organic LED

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this