Presentation 2019-08-30
Computational-Complexity Comparison of Time- and Frequency-Domain Artificial Neural Networks for Optical Nonlinearity Compensation
Takeru Kyono, Moriya Nakamura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We investigated and compared the computational complexity of a TD-ANN and an FD-ANN which are used for optical nonlinearity compensation. For linear equalization to compensate for, e.g., chromatic dispersion (CD), it is known that FD-equalization outperforms TD-equalization in terms of computational complexity over a wide range of CD values. Our investigation showed that the TD-ANN-based nonlinear equalization had lower computational complexity than the FD-ANN.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural network / Nonlinear compensation / Optical fiber communications
Paper # OCS2019-26
Date of Issue 2019-08-22 (OCS)

Conference Information
Committee OFT / OCS / LSJ
Conference Date 2019/8/29(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Fumihiko Ito(Shimane Univ.) / Joji Maeda(Tokyo Univ. of Science)
Vice Chair
Secretary (Sumitomo Electric) / (NTT) / (NTT)
Assistant Hajime Arao(Sumitomo Electric) / Hiroshi Watanabe(NTT)

Paper Information
Registration To Technical Committee on Optical Fiber Technology / Technical Committee on Optical Communication Systems / The Laser Society of Japan
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Computational-Complexity Comparison of Time- and Frequency-Domain Artificial Neural Networks for Optical Nonlinearity Compensation
Sub Title (in English)
Keyword(1) Neural network
Keyword(2) Nonlinear compensation
Keyword(3) Optical fiber communications
1st Author's Name Takeru Kyono
1st Author's Affiliation Meiji University(Meiji Univ.)
2nd Author's Name Moriya Nakamura
2nd Author's Affiliation Meiji University(Meiji Univ.)
Date 2019-08-30
Paper # OCS2019-26
Volume (vol) vol.119
Number (no) OCS-186
Page pp.pp.35-38(OCS),
#Pages 4
Date of Issue 2019-08-22 (OCS)