Long-Haul Optical-Eigenvalue Transmission Using a Neural Network Demodulator and SD-FEC

Mishina, Ken; Harada, Ryotaro; Yoshida, Tsuyoshi; Hisano, Daisuke; Maruta, Akihiro

doi:https://doi.org/10.1109/JSAC.2025.3543512

Long-Haul Optical-Eigenvalue Transmission Using a Neural Network Demodulator and SD-FEC

Mishina, Ken; Harada, Ryotaro; Yoshida, Tsuyoshi et al.

IEEE Journal on Selected Areas in Communications, 2025, 43(5), 1498-1511

アクセス数:263件（2025-07-29 08:21 集計）

固定URL: https://hdl.handle.net/11094/101418

閲覧可能ファイル

ファイル	フォーマット	利用条件	サイズ	閲覧回数	利用開始日	説明	information
IEEEJSelAreasCommun_43_5_1498	pdf	なし	1.93 MB	9	2025.06.05

Creative Commons : 表示

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	Long-Haul Optical-Eigenvalue Transmission Using a Neural Network Demodulator and SD-FEC
著者	NRID 1000090466368 1000090466368 researchmap permalink KenMishina KenMishina Scopus Author ID 15030319700 15030319700 ORCID 0000-0001-9460-3870 0000-0001-9460-3870 著者名 Mishina, Ken
	著者名 Harada, Ryotaro
	著者名 Yoshida, Tsuyoshi
	NRID 1000040802088 1000040802088 researchmap permalink dhisano dhisano Scopus Author ID 55414479500 55414479500 ORCID 0000-0002-5766-3812 0000-0002-5766-3812 著者名 Hisano, Daisuke
	NRID 1000040252613 1000040252613 researchmap permalink read0042809 read0042809 Scopus Author ID 7006461957 7006461957 ORCID 0000-0001-7503-5097 0000-0001-7503-5097 著者名 Maruta, Akihiro
キーワード等	fiber nonlinear optics
	forward error correction
	neural networks
	Optical fiber communication
内容	Mishina K., Harada R., Yoshida T., et al. Long-Haul Optical-Eigenvalue Transmission Using a Neural Network Demodulator and SD-FEC. IEEE Journal on Selected Areas in Communications 43(5), 1498-1511 (2025); https://doi.org/10.1109/JSAC.2025.3543512.
抄録	Optical eigenvalue transmission based on inverse scattering transform (IST) has been studied for one of approaches to overcome the Kerr nonlinearity limit in fiber optic communications. In the recent decade, several multilevel modulation schemes that are based on IST, such as 16-ary and 64-ary signals using on-off encoding and b-modulation of multieigenvalues, have been proposed. To increase the transmission capacity and extend the transmission distance, applications of machine learning-based approaches to IST-based transmission have been proposed and demonstrated. Another prospective approach to increase the transmission capacity and extend the transmission distance in fiber optic communication involves the application of soft-decision forward error correction (SD-FEC). However, the applicability of SD-FEC to eigenvalue-modulated signals has not yet been investigated in detail because the distribution of the received signal is complicated for IST-based transmissions. In this paper, we describe in detail the theory of optical eigenvalue transmission, including the design of multilevel eigenvalue-modulated signals and the effects of noise and scaring parameters (coefficients for normalization of the nonlinear Schrödinger equation). We explain why neural network (NN) demodulators are advantageous for eigenvalue transmission systems. Consequently, we propose a combination of NN-based demodulators and SD-FEC decoding. A multilabel NN-based demodulator is employed to compute the L-value from the received eigenvalue pattern at the receiver. For a 16-ary eigenvalue-modulated signal, the proposed method outperformed a combination of the Gaussian approximation and SD-FEC in the simulation. Moreover, the experimental results show successful operation with error-free transmission through a 3000-km optical fiber line. In addition, we experimentally demonstrate the applicability of SD-FEC to a 4096-ary eigenvalue-modulated signal. The experimental results indicate that an achievable transmission distance can be extended to 1200 km using the NN demodulator and SD-FEC.
出版者	Institute of Electrical and Electronics Engineers Inc.
収録物名	IEEE Journal on Selected Areas in Communications
巻(号)	43(5)
ページ	1498-1511
刊行年月	2025-02-19
言語	英語
ハンドルURL	https://hdl.handle.net/11094/101418
PISSN	07338716
eISSN	15580008
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1109/JSAC.2025.3543512
アクセス権	open access
権利情報	This article is licensed under a Creative Commons Attribution 4.0 International License.
出版タイプ	Version of Record
カテゴリ	学術雑誌論文 Journal Article

資源タイプ	学術雑誌論文
ローカル資源タイプ	学術雑誌論文
DCMI資源タイプ	text
DCTERMS.bibliographicCitation	IEEE Journal on Selected Areas in Communications. 2025, 43(5), p. 1498-1511
DC.title	Long-Haul Optical-Eigenvalue Transmission Using a Neural Network Demodulator and SD-FEC
DC.creator	Mishina, Ken
	Harada, Ryotaro
	Yoshida, Tsuyoshi
	Hisano, Daisuke
	Maruta, Akihiro
DC.publisher	Institute of Electrical and Electronics Engineers Inc.
DC.language' scheme='DCTERMS.RFC1766	英語
DC.type' scheme='DCTERMS.DCMIType	text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-02-19
DC.identifier	https://doi.org/10.1109/JSAC.2025.3543512
DC.subject	fiber nonlinear optics
	forward error correction
	neural networks
	Optical fiber communication
DC.description	Mishina K., Harada R., Yoshida T., et al. Long-Haul Optical-Eigenvalue Transmission Using a Neural Network Demodulator and SD-FEC. IEEE Journal on Selected Areas in Communications 43(5), 1498-1511 (2025); https://doi.org/10.1109/JSAC.2025.3543512.
DCTERMS.abstract	Optical eigenvalue transmission based on inverse scattering transform (IST) has been studied for one of approaches to overcome the Kerr nonlinearity limit in fiber optic communications. In the recent decade, several multilevel modulation schemes that are based on IST, such as 16-ary and 64-ary signals using on-off encoding and b-modulation of multieigenvalues, have been proposed. To increase the transmission capacity and extend the transmission distance, applications of machine learning-based approaches to IST-based transmission have been proposed and demonstrated. Another prospective approach to increase the transmission capacity and extend the transmission distance in fiber optic communication involves the application of soft-decision forward error correction (SD-FEC). However, the applicability of SD-FEC to eigenvalue-modulated signals has not yet been investigated in detail because the distribution of the received signal is complicated for IST-based transmissions. In this paper, we describe in detail the theory of optical eigenvalue transmission, including the design of multilevel eigenvalue-modulated signals and the effects of noise and scaring parameters (coefficients for normalization of the nonlinear Schrödinger equation). We explain why neural network (NN) demodulators are advantageous for eigenvalue transmission systems. Consequently, we propose a combination of NN-based demodulators and SD-FEC decoding. A multilabel NN-based demodulator is employed to compute the L-value from the received eigenvalue pattern at the receiver. For a 16-ary eigenvalue-modulated signal, the proposed method outperformed a combination of the Gaussian approximation and SD-FEC in the simulation. Moreover, the experimental results show successful operation with error-free transmission through a 3000-km optical fiber line. In addition, we experimentally demonstrate the applicability of SD-FEC to a 4096-ary eigenvalue-modulated signal. The experimental results indicate that an achievable transmission distance can be extended to 1200 km using the NN demodulator and SD-FEC.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	101418
citation_title	Long-Haul Optical-Eigenvalue Transmission Using a Neural Network Demodulator and SD-FEC
citation_author	Mishina, Ken
	Harada, Ryotaro
	Yoshida, Tsuyoshi
	Hisano, Daisuke
	Maruta, Akihiro
citation_publisher	Institute of Electrical and Electronics Engineers Inc.
citation_language	英語
citation_date	2025-02-19
citation_journal_title	IEEE Journal on Selected Areas in Communications
citation_volume	43
citation_issue	5
citation_firstpage	1498
citation_lastpage	1511
citation_doi	https://doi.org/10.1109/JSAC.2025.3543512
citation_public_url	https://hdl.handle.net/11094/101418

Long-Haul Optical-Eigenvalue Transmission Using a Neural Network Demodulator and SD-FEC

閲覧可能ファイル

論文情報

論文詳細を表示