Experimental comparison of artificial neural network and volterra based nonlinear equalization for CO-OFDM

Elias Giacoumidis, Son T. Le, Ivan Aldaya, Jinlong Wei, Mary McCarthy, Nick Doran, Benjamin Eggleton

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A novel artificial neural network (ANN)-based nonlinear equalizer (NLE) of low complexity is demonstrated for 40-Gb/s CO-OFDM at 2000 km, revealing ∼1.5 dB enhancement in Q-factor compared to inverse Volterra-series transfer function based NLE.

Original languageEnglish
Title of host publicationOptical Fiber Communication Conference 2016
PublisherOptical Society of America
ISBN (Print)978-1-943580-07-1
DOIs
Publication statusPublished - 22 Mar 2016
EventOptical Fiber Communication Conference 2016 - Anaheim, CA, United States
Duration: 20 Mar 201622 Mar 2016

Conference

ConferenceOptical Fiber Communication Conference 2016
CountryUnited States
CityAnaheim, CA
Period20/03/1622/03/16

Fingerprint

Equalizers
Orthogonal frequency division multiplexing
Neural networks
transfer functions
Transfer functions
Q factors
augmentation

Bibliographical note

-

Cite this

Giacoumidis, E., Le, S. T., Aldaya, I., Wei, J., McCarthy, M., Doran, N., & Eggleton, B. (2016). Experimental comparison of artificial neural network and volterra based nonlinear equalization for CO-OFDM. In Optical Fiber Communication Conference 2016 [paper W3A.4] Optical Society of America. https://doi.org/10.1364/OFC.2016.W3A.4
Giacoumidis, Elias ; Le, Son T. ; Aldaya, Ivan ; Wei, Jinlong ; McCarthy, Mary ; Doran, Nick ; Eggleton, Benjamin. / Experimental comparison of artificial neural network and volterra based nonlinear equalization for CO-OFDM. Optical Fiber Communication Conference 2016. Optical Society of America, 2016.
@inproceedings{0adb72c36b0141598226c90a330f0882,
title = "Experimental comparison of artificial neural network and volterra based nonlinear equalization for CO-OFDM",
abstract = "A novel artificial neural network (ANN)-based nonlinear equalizer (NLE) of low complexity is demonstrated for 40-Gb/s CO-OFDM at 2000 km, revealing ∼1.5 dB enhancement in Q-factor compared to inverse Volterra-series transfer function based NLE.",
author = "Elias Giacoumidis and Le, {Son T.} and Ivan Aldaya and Jinlong Wei and Mary McCarthy and Nick Doran and Benjamin Eggleton",
note = "-",
year = "2016",
month = "3",
day = "22",
doi = "10.1364/OFC.2016.W3A.4",
language = "English",
isbn = "978-1-943580-07-1",
booktitle = "Optical Fiber Communication Conference 2016",
publisher = "Optical Society of America",

}

Giacoumidis, E, Le, ST, Aldaya, I, Wei, J, McCarthy, M, Doran, N & Eggleton, B 2016, Experimental comparison of artificial neural network and volterra based nonlinear equalization for CO-OFDM. in Optical Fiber Communication Conference 2016., paper W3A.4, Optical Society of America, Optical Fiber Communication Conference 2016, Anaheim, CA, United States, 20/03/16. https://doi.org/10.1364/OFC.2016.W3A.4

Experimental comparison of artificial neural network and volterra based nonlinear equalization for CO-OFDM. / Giacoumidis, Elias; Le, Son T.; Aldaya, Ivan; Wei, Jinlong; McCarthy, Mary; Doran, Nick; Eggleton, Benjamin.

Optical Fiber Communication Conference 2016. Optical Society of America, 2016. paper W3A.4.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Experimental comparison of artificial neural network and volterra based nonlinear equalization for CO-OFDM

AU - Giacoumidis, Elias

AU - Le, Son T.

AU - Aldaya, Ivan

AU - Wei, Jinlong

AU - McCarthy, Mary

AU - Doran, Nick

AU - Eggleton, Benjamin

N1 - -

PY - 2016/3/22

Y1 - 2016/3/22

N2 - A novel artificial neural network (ANN)-based nonlinear equalizer (NLE) of low complexity is demonstrated for 40-Gb/s CO-OFDM at 2000 km, revealing ∼1.5 dB enhancement in Q-factor compared to inverse Volterra-series transfer function based NLE.

AB - A novel artificial neural network (ANN)-based nonlinear equalizer (NLE) of low complexity is demonstrated for 40-Gb/s CO-OFDM at 2000 km, revealing ∼1.5 dB enhancement in Q-factor compared to inverse Volterra-series transfer function based NLE.

UR - http://www.scopus.com/inward/record.url?scp=84986192010&partnerID=8YFLogxK

UR - https://www.osapublishing.org/abstract.cfm?URI=OFC-2016-W3A.4

U2 - 10.1364/OFC.2016.W3A.4

DO - 10.1364/OFC.2016.W3A.4

M3 - Conference contribution

SN - 978-1-943580-07-1

BT - Optical Fiber Communication Conference 2016

PB - Optical Society of America

ER -

Giacoumidis E, Le ST, Aldaya I, Wei J, McCarthy M, Doran N et al. Experimental comparison of artificial neural network and volterra based nonlinear equalization for CO-OFDM. In Optical Fiber Communication Conference 2016. Optical Society of America. 2016. paper W3A.4 https://doi.org/10.1364/OFC.2016.W3A.4