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

doi:10.1007/978-3-642-15822-3_55

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

Aston Institute of Photonic Technologies (AiPT)

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

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 language	English
Title of host publication	Artificial Neural Networks – ICANN 2010
Subtitle of host publication	20th International Conference, Thessaloniki, Greece, September 15-18, 2010, Proceedings, Part II
Editors	Konstantinos Diamantaras, Wlodek Duch, Lazaros S. Iliadis
Place of Publication	Berlin/Heidelberg
Publisher	Springer
Pages	448-457
Number of pages	10
Volume	6353
Edition	PART 2
ISBN (Print)	3-642-15821-8, 978-3-642-15821-6
DOIs	https://doi.org/10.1007/978-3-642-15822-3_55
Publication status	Published - 2010
Event	20th International Conference on Artificial Neural Networks – ICANN 2010 - Thessaloniki, Greece Duration: 15 Sept 2010 → 18 Sept 2010

Publication series

Name	Lecture notes in computer science
Publisher	Springer
Volume	6353
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	20th International Conference on Artificial Neural Networks – ICANN 2010
Country/Territory	Greece
City	Thessaloniki
Period	15/09/10 → 18/09/10

Keywords

error correction
classification
optical communication
adaptive signal processing

Access to Document

10.1007/978-3-642-15822-3_55

Cite this

Hunt, S., Sun, Y., Shafarenko, A., Adams, R., Davey, N., Slater, B., Bhamber, R., Boscolo, S., & Turitsyn, S. K. (2010). Correcting errors in optical data transmission using neural networks. In K. Diamantaras, W. Duch, & L. S. Iliadis (Eds.), Artificial Neural Networks – ICANN 2010: 20th International Conference, Thessaloniki, Greece, September 15-18, 2010, Proceedings, Part II (PART 2 ed., Vol. 6353, pp. 448-457). (Lecture notes in computer science; Vol. 6353). Springer. https://doi.org/10.1007/978-3-642-15822-3_55

Hunt, Stephen ; Sun, Yi ; Shafarenko, Alex et al. / Correcting errors in optical data transmission using neural networks. Artificial Neural Networks – ICANN 2010: 20th International Conference, Thessaloniki, Greece, September 15-18, 2010, Proceedings, Part II. editor / Konstantinos Diamantaras ; Wlodek Duch ; Lazaros S. Iliadis. Vol. 6353 PART 2. ed. Berlin/Heidelberg : Springer, 2010. pp. 448-457 (Lecture notes in computer science).

@inproceedings{0bf74532f9fc47a287cc08b368497cbb,

title = "Correcting errors in optical data transmission using neural networks",

abstract = "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.",

keywords = "error correction, classification, optical communication, adaptive signal processing",

author = "Stephen Hunt and Yi Sun and Alex Shafarenko and Rod Adams and Neil Davey and Brendan Slater and Ranjeet Bhamber and Sonia Boscolo and Turitsyn, {Sergei K.}",

year = "2010",

doi = "10.1007/978-3-642-15822-3_55",

language = "English",

isbn = "3-642-15821-8",

volume = "6353",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "448--457",

editor = "Konstantinos Diamantaras and Wlodek Duch and Iliadis, {Lazaros S.}",

booktitle = "Artificial Neural Networks – ICANN 2010",

address = "Germany",

edition = "PART 2",

note = "20th International Conference on Artificial Neural Networks – ICANN 2010 ; Conference date: 15-09-2010 Through 18-09-2010",

}

Hunt, S, Sun, Y, Shafarenko, A, Adams, R, Davey, N, Slater, B, Bhamber, R, Boscolo, S & Turitsyn, SK 2010, Correcting errors in optical data transmission using neural networks. in K Diamantaras, W Duch & LS Iliadis (eds), Artificial Neural Networks – ICANN 2010: 20th International Conference, Thessaloniki, Greece, September 15-18, 2010, Proceedings, Part II. PART 2 edn, vol. 6353, Lecture notes in computer science, vol. 6353, Springer, Berlin/Heidelberg, pp. 448-457, 20th International Conference on Artificial Neural Networks – ICANN 2010, Thessaloniki, Greece, 15/09/10. https://doi.org/10.1007/978-3-642-15822-3_55

Correcting errors in optical data transmission using neural networks. / Hunt, Stephen; Sun, Yi; Shafarenko, Alex et al.
Artificial Neural Networks – ICANN 2010: 20th International Conference, Thessaloniki, Greece, September 15-18, 2010, Proceedings, Part II. ed. / Konstantinos Diamantaras; Wlodek Duch; Lazaros S. Iliadis. Vol. 6353 PART 2. ed. Berlin/Heidelberg: Springer, 2010. p. 448-457 (Lecture notes in computer science; Vol. 6353).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - Correcting errors in optical data transmission using neural networks

AU - Hunt, Stephen

AU - Sun, Yi

AU - Shafarenko, Alex

AU - Adams, Rod

AU - Davey, Neil

AU - Slater, Brendan

AU - Bhamber, Ranjeet

AU - Boscolo, Sonia

AU - Turitsyn, Sergei K.

PY - 2010

Y1 - 2010

N2 - 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.

AB - 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.

KW - error correction

KW - classification

KW - optical communication

KW - adaptive signal processing

UR - http://www.scopus.com/inward/record.url?scp=78049388312&partnerID=8YFLogxK

UR - http://www.springerlink.com/content/52h02p103784m203/

U2 - 10.1007/978-3-642-15822-3_55

DO - 10.1007/978-3-642-15822-3_55

M3 - Conference publication

SN - 3-642-15821-8

SN - 978-3-642-15821-6

VL - 6353

T3 - Lecture notes in computer science

SP - 448

EP - 457

BT - Artificial Neural Networks – ICANN 2010

A2 - Diamantaras, Konstantinos

A2 - Duch, Wlodek

A2 - Iliadis, Lazaros S.

PB - Springer

CY - Berlin/Heidelberg

T2 - 20th International Conference on Artificial Neural Networks – ICANN 2010

Y2 - 15 September 2010 through 18 September 2010

ER -

Hunt S, Sun Y, Shafarenko A, Adams R, Davey N, Slater B et al. Correcting errors in optical data transmission using neural networks. In Diamantaras K, Duch W, Iliadis LS, editors, Artificial Neural Networks – ICANN 2010: 20th International Conference, Thessaloniki, Greece, September 15-18, 2010, Proceedings, Part II. PART 2 ed. Vol. 6353. Berlin/Heidelberg: Springer. 2010. p. 448-457. (Lecture notes in computer science). doi: 10.1007/978-3-642-15822-3_55

Correcting errors in optical data transmission using neural networks

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this