Modulation Format Identification in Coherent Receivers Using Deep Machine Learning

Faisal Nadeem Khan; Kangping Zhong; Waled Hussein Al-Arashi; Changyuan Yu; Chao Lu; Pak Tao Lau

doi:10.1109/LPT.2016.2574800

Modulation Format Identification in Coherent Receivers Using Deep Machine Learning

Faisal Nadeem Khan, Kangping Zhong, Waled Hussein Al-Arashi, Changyuan Yu, Chao Lu, Pak Tao Lau

The Hong Kong Polytechnic University

Research output: Journal article publication › Journal article › Academic research › peer-review

143 Citations (Scopus)

Abstract

We propose a novel technique for modulation format identification (MFI) in digital coherent receivers by applying deep neural network (DNN) based pattern recognition on signals' amplitude histograms obtained after constant modulus algorithm (CMA) equalization. Experimental results for three commonly-used modulation formats demonstrate MFI with an accuracy of 100% over a wide optical signal-to-noise ratio (OSNR) range. The effects of fiber nonlinearity on the performance of MFI technique are also investigated. The proposed technique is non-data-aided (NDA) and avoids any additional hardware on top of standard digital coherent receiver. Therefore, it is ideal for simple and cost-effective MFI in future heterogeneous optical networks.

Original language	English
Article number	7482803
Pages (from-to)	1886-1889
Number of pages	4
Journal	IEEE Photonics Technology Letters
Volume	28
Issue number	17
DOIs	https://doi.org/10.1109/LPT.2016.2574800
Publication status	Published - 1 Sept 2016

Keywords

coherent detection
deep machine learning
Modulation format identification

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Atomic and Molecular Physics, and Optics
Electrical and Electronic Engineering

More information

10.1109/LPT.2016.2574800

http://hdl.handle.net/10397/107263

Cite this

@article{c6f4742f053d4998953fb5cf3deaef6b,

title = "Modulation Format Identification in Coherent Receivers Using Deep Machine Learning",

abstract = "We propose a novel technique for modulation format identification (MFI) in digital coherent receivers by applying deep neural network (DNN) based pattern recognition on signals' amplitude histograms obtained after constant modulus algorithm (CMA) equalization. Experimental results for three commonly-used modulation formats demonstrate MFI with an accuracy of 100% over a wide optical signal-to-noise ratio (OSNR) range. The effects of fiber nonlinearity on the performance of MFI technique are also investigated. The proposed technique is non-data-aided (NDA) and avoids any additional hardware on top of standard digital coherent receiver. Therefore, it is ideal for simple and cost-effective MFI in future heterogeneous optical networks.",

keywords = "coherent detection, deep machine learning, Modulation format identification",

author = "Khan, {Faisal Nadeem} and Kangping Zhong and Al-Arashi, {Waled Hussein} and Changyuan Yu and Chao Lu and Lau, {Pak Tao}",

year = "2016",

month = sep,

day = "1",

doi = "10.1109/LPT.2016.2574800",

language = "English",

volume = "28",

pages = "1886--1889",

journal = "IEEE Photonics Technology Letters",

issn = "1041-1135",

publisher = "IEEE",

number = "17",

}

TY - JOUR

T1 - Modulation Format Identification in Coherent Receivers Using Deep Machine Learning

AU - Khan, Faisal Nadeem

AU - Zhong, Kangping

AU - Al-Arashi, Waled Hussein

AU - Yu, Changyuan

AU - Lu, Chao

AU - Lau, Pak Tao

PY - 2016/9/1

Y1 - 2016/9/1

N2 - We propose a novel technique for modulation format identification (MFI) in digital coherent receivers by applying deep neural network (DNN) based pattern recognition on signals' amplitude histograms obtained after constant modulus algorithm (CMA) equalization. Experimental results for three commonly-used modulation formats demonstrate MFI with an accuracy of 100% over a wide optical signal-to-noise ratio (OSNR) range. The effects of fiber nonlinearity on the performance of MFI technique are also investigated. The proposed technique is non-data-aided (NDA) and avoids any additional hardware on top of standard digital coherent receiver. Therefore, it is ideal for simple and cost-effective MFI in future heterogeneous optical networks.

AB - We propose a novel technique for modulation format identification (MFI) in digital coherent receivers by applying deep neural network (DNN) based pattern recognition on signals' amplitude histograms obtained after constant modulus algorithm (CMA) equalization. Experimental results for three commonly-used modulation formats demonstrate MFI with an accuracy of 100% over a wide optical signal-to-noise ratio (OSNR) range. The effects of fiber nonlinearity on the performance of MFI technique are also investigated. The proposed technique is non-data-aided (NDA) and avoids any additional hardware on top of standard digital coherent receiver. Therefore, it is ideal for simple and cost-effective MFI in future heterogeneous optical networks.

KW - coherent detection

KW - deep machine learning

KW - Modulation format identification

UR - http://www.scopus.com/inward/record.url?scp=84978958278&partnerID=8YFLogxK

U2 - 10.1109/LPT.2016.2574800

DO - 10.1109/LPT.2016.2574800

M3 - Journal article

SN - 1041-1135

VL - 28

SP - 1886

EP - 1889

JO - IEEE Photonics Technology Letters

JF - IEEE Photonics Technology Letters

IS - 17

M1 - 7482803

ER -

Modulation Format Identification in Coherent Receivers Using Deep Machine Learning

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this