Correcting errors in optical data transmission using neural networks

Stephen Hunt, Yi Sun, Alex Shafarenko, Rod Adams, Neil Davey, Brendan Slater, Ranjeet Bhamber, Sonia Boscolo, Sergei K. Turitsyn

Research output: Chapter in Book/Published conference outputConference publication


Optical data communication systems are prone to a variety of processes that modify the transmitted signal, and contribute errors in the determination of 1s from 0s. This is a difficult, and commercially important, problem to solve. Errors must be detected and corrected at high speed, and the classifier must be very accurate; ideally it should also be tunable to the characteristics of individual communication links. We show that simple single layer neural networks may be used to address these problems, and examine how different input representations affect the accuracy of bit error correction. Our results lead us to conclude that a system based on these principles can perform at least as well as an existing non-trainable error correction system, whilst being tunable to suit the individual characteristics of different communication links.
Original languageEnglish
Title of host publicationArtificial Neural Networks – ICANN 2010
Subtitle of host publication20th International Conference, Thessaloniki, Greece, September 15-18, 2010, Proceedings, Part II
EditorsKonstantinos Diamantaras, Wlodek Duch, Lazaros S. Iliadis
Place of PublicationBerlin/Heidelberg
Number of pages10
EditionPART 2
ISBN (Print)3-642-15821-8, 978-3-642-15821-6
Publication statusPublished - 2010
Event20th International Conference on Artificial Neural Networks – ICANN 2010 - Thessaloniki, Greece
Duration: 15 Sept 201018 Sept 2010

Publication series

NameLecture notes in computer science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference20th International Conference on Artificial Neural Networks – ICANN 2010


  • error correction
  • classification
  • optical communication
  • adaptive signal processing


Dive into the research topics of 'Correcting errors in optical data transmission using neural networks'. Together they form a unique fingerprint.

Cite this