Machine learning techniques in optical communication

Darko Zibar; Molly Piels; Rasmus Thomas Jones; C. G. Schaeffer

doi:10.1109/ECOC.2015.7341896

Machine learning techniques in optical communication

Darko Zibar, Molly Piels, Rasmus Thomas Jones, C. G. Schaeffer

IT Service

Helmut-Schmidt-University

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

Abstract

Techniques from the machine learning community are reviewed and employed for laser characterization, signal detection in the presence of nonlinear phase noise, and nonlinearity mitigation. Bayesian filtering and expectation maximization are employed within nonlinear state-space framework for parameter tracking.

Original language	English
Title of host publication	2015 41st European Conference on Optical Communication (ECOC)
Number of pages	3
Publisher	IEEE
Publication date	2015
Pages	1-3
ISBN (Print)	9788460817413
DOIs	https://doi.org/10.1109/ECOC.2015.7341896
Publication status	Published - 2015
Event	Opto Electronics and Communications Conference 2015 - Shanghai Everbright Convention Center, Shanghai , China Duration: 28 Jun 2015 → 2 Jul 2015

Conference

Conference	Opto Electronics and Communications Conference 2015
Location	Shanghai Everbright Convention Center
Country/Territory	China
City	Shanghai
Period	28/06/2015 → 02/07/2015

Keywords

expectation-maximisation algorithm
lasers
learning (artificial intelligence)
nonlinear optics
optical communication
optical filters
optical noise
optical signal detection
phase noise
Communication, Networking and Broadcast Technologies
Photonics and Electrooptics
Bayes methods
Bayesian filtering
expectation maximization
laser characterization
machine learning techniques
Nonlinear optics
nonlinear phase noise
nonlinear state-space framework
Optical noise
Optical polarization
Optical signal processing
Optical variables measurement
parameter tracking
Phase noise
signal detection

Access to Document

10.1109/ECOC.2015.7341896

OpenUrl availability

Full text

Cite this

@inproceedings{88badc16de6b444b9006c020e8a1f405,

title = "Machine learning techniques in optical communication",

abstract = "Techniques from the machine learning community are reviewed and employed for laser characterization, signal detection in the presence of nonlinear phase noise, and nonlinearity mitigation. Bayesian filtering and expectation maximization are employed within nonlinear state-space framework for parameter tracking.",

keywords = "expectation-maximisation algorithm, lasers, learning (artificial intelligence), nonlinear optics, optical communication, optical filters, optical noise, optical signal detection, phase noise, Communication, Networking and Broadcast Technologies, Photonics and Electrooptics, Bayes methods, Bayesian filtering, expectation maximization, laser characterization, machine learning techniques, Nonlinear optics, nonlinear phase noise, nonlinear state-space framework, Optical noise, Optical polarization, Optical signal processing, Optical variables measurement, parameter tracking, Phase noise, signal detection",

author = "Darko Zibar and Molly Piels and Jones, {Rasmus Thomas} and Schaeffer, {C. G.}",

year = "2015",

doi = "10.1109/ECOC.2015.7341896",

language = "English",

isbn = "9788460817413",

pages = "1--3",

booktitle = "2015 41st European Conference on Optical Communication (ECOC)",

publisher = "IEEE",

address = "United States",

note = "Opto Electronics and Communications Conference 2015, OECC 2015 ; Conference date: 28-06-2015 Through 02-07-2015",

}

TY - GEN

T1 - Machine learning techniques in optical communication

AU - Zibar, Darko

AU - Piels, Molly

AU - Jones, Rasmus Thomas

AU - Schaeffer, C. G.

PY - 2015

Y1 - 2015

N2 - Techniques from the machine learning community are reviewed and employed for laser characterization, signal detection in the presence of nonlinear phase noise, and nonlinearity mitigation. Bayesian filtering and expectation maximization are employed within nonlinear state-space framework for parameter tracking.

AB - Techniques from the machine learning community are reviewed and employed for laser characterization, signal detection in the presence of nonlinear phase noise, and nonlinearity mitigation. Bayesian filtering and expectation maximization are employed within nonlinear state-space framework for parameter tracking.

KW - expectation-maximisation algorithm

KW - lasers

KW - learning (artificial intelligence)

KW - nonlinear optics

KW - optical communication

KW - optical filters

KW - optical noise

KW - optical signal detection

KW - phase noise

KW - Communication, Networking and Broadcast Technologies

KW - Photonics and Electrooptics

KW - Bayes methods

KW - Bayesian filtering

KW - expectation maximization

KW - laser characterization

KW - machine learning techniques

KW - Nonlinear optics

KW - nonlinear phase noise

KW - nonlinear state-space framework

KW - Optical noise

KW - Optical polarization

KW - Optical signal processing

KW - Optical variables measurement

KW - parameter tracking

KW - Phase noise

KW - signal detection

U2 - 10.1109/ECOC.2015.7341896

DO - 10.1109/ECOC.2015.7341896

M3 - Article in proceedings

SN - 9788460817413

SP - 1

EP - 3

BT - 2015 41st European Conference on Optical Communication (ECOC)

PB - IEEE

T2 - Opto Electronics and Communications Conference 2015

Y2 - 28 June 2015 through 2 July 2015

ER -

Machine learning techniques in optical communication

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this