5G Indoor/Outdoor Field Trial of Deep Joint Source-Channel Coding Method

Hisano, Daisuke; Matsumoto, Keigo; Inoue, Yoshiaki; Hara, Yuko; Maruta, Kazuki; Nakayama, Yu; Tatsukawa, Hiroshi; Kawai, Yuji; Shinohara, Yoshinori; Ikeda, Hiroki

doi:https://doi.org/10.1109/OJCOMS.2025.3576502

5G Indoor/Outdoor Field Trial of Deep Joint Source-Channel Coding Method

Hisano, Daisuke; Matsumoto, Keigo; Inoue, Yoshiaki et al.

IEEE Open Journal of the Communications Society, 2025, 6, 4894-4907

アクセス数:335件（2026-02-15 18:42 集計）

固定URL: https://hdl.handle.net/11094/103251

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
IEEEopenJCommunSoc_6_4894	pdf	なし	7.41 MB	100	2025.12.02

Creative Commons : 表示 - 非営利 - 改変禁止

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	5G Indoor/Outdoor Field Trial of Deep Joint Source-Channel Coding Method
著者	NRID 1000040802088 1000040802088 ORCID 0000-0002-5766-3812 0000-0002-5766-3812 researchmap permalink dhisano dhisano Scopus Author ID 55414479500 55414479500 著者名 Hisano, Daisuke
	著者名 Matsumoto, Keigo
	NRID 1000040779914 1000040779914 ORCID 0000-0002-2483-7652 0000-0002-2483-7652 researchmap permalink q_yoshiaki q_yoshiaki Scopus Author ID 55911704200 55911704200 著者名 Inoue, Yoshiaki
	NRID 1000020640999 1000020640999 著者名 Hara, Yuko
	NRID 1000030801170 1000030801170 著者名 Maruta, Kazuki
	NRID 1000080802058 1000080802058 著者名 Nakayama, Yu
	著者名 Tatsukawa, Hiroshi
	著者名 Kawai, Yuji
	著者名 Shinohara, Yoshinori
	著者名 Ikeda, Hiroki
キーワード等	5G mobile communication
	data compression
	deep learning
	edge computing
	image communication
内容	Hisano D., Matsumoto K., Inoue Y., et al. 5G Indoor/Outdoor Field Trial of Deep Joint Source-Channel Coding Method. IEEE Open Journal of the Communications Society 6, 4894 (2025); https://doi.org/10.1109/OJCOMS.2025.3576502.
抄録	This paper presents the first outdoor field trials of deep joint source-channel coding (DeepJSCC) for image transmission over a 5G system. DeepJSCC is a deep learning-based end-to-end method that unifies source and channel coding to enable robust and low-latency image transmission, particularly in low signal-to-noise power ratio (SNR) environments. Unlike conventional methods, DeepJSCC inherently avoids the cliff effect and maintains stable image quality under harsh channel conditions. To evaluate its feasibility of practical environments, we modified a commercial 5G base station (gNB) and user equipment (UE) to support DeepJSCC signal transmission and reception. Extensive experiments were conducted under indoor and outdoor settings, including line-of-sight (LoS) and non-line-of-sight (NLoS) conditions. A key contribution of this study is the empirical verification that even a DeepJSCC model trained solely on an additive white Gaussian noise (AWGN) channel can maintain stable reconstruction performance in real 5G environments, demonstrating its generalization capability. Compared to baseline systems using JPEG2000 and LDPC, DeepJSCC achieved higher PSNR stability and was able to restore image content even when conventional schemes completely failed. These findings suggest that DeepJSCC is a promising candidate for next-generation visual communication over 5G infrastructure.
出版者	Institute of Electrical and Electronics Engineers Inc.
収録物名	IEEE Open Journal of the Communications Society
巻(号)	6
ページ	4894-4907
刊行年月	2025-06-04
言語	英語
ハンドルURL	https://hdl.handle.net/11094/103251
eISSN	2644125X
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1109/OJCOMS.2025.3576502
アクセス権	open access
権利情報	This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 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 Open Journal of the Communications Society. 2025, 6, p. 4894-4907
DC.title	5G Indoor/Outdoor Field Trial of Deep Joint Source-Channel Coding Method
DC.creator	Hisano, Daisuke
	Matsumoto, Keigo
	Inoue, Yoshiaki
	Hara, Yuko
	Maruta, Kazuki
	Nakayama, Yu
	Tatsukawa, Hiroshi
	Kawai, Yuji
	Shinohara, Yoshinori
	Ikeda, Hiroki
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	2025-06-04
DC.identifier	https://doi.org/10.1109/OJCOMS.2025.3576502
DC.subject	5G mobile communication
	data compression
	deep learning
	edge computing
	image communication
DC.description	Hisano D., Matsumoto K., Inoue Y., et al. 5G Indoor/Outdoor Field Trial of Deep Joint Source-Channel Coding Method. IEEE Open Journal of the Communications Society 6, 4894 (2025); https://doi.org/10.1109/OJCOMS.2025.3576502.
DCTERMS.abstract	This paper presents the first outdoor field trials of deep joint source-channel coding (DeepJSCC) for image transmission over a 5G system. DeepJSCC is a deep learning-based end-to-end method that unifies source and channel coding to enable robust and low-latency image transmission, particularly in low signal-to-noise power ratio (SNR) environments. Unlike conventional methods, DeepJSCC inherently avoids the cliff effect and maintains stable image quality under harsh channel conditions. To evaluate its feasibility of practical environments, we modified a commercial 5G base station (gNB) and user equipment (UE) to support DeepJSCC signal transmission and reception. Extensive experiments were conducted under indoor and outdoor settings, including line-of-sight (LoS) and non-line-of-sight (NLoS) conditions. A key contribution of this study is the empirical verification that even a DeepJSCC model trained solely on an additive white Gaussian noise (AWGN) channel can maintain stable reconstruction performance in real 5G environments, demonstrating its generalization capability. Compared to baseline systems using JPEG2000 and LDPC, DeepJSCC achieved higher PSNR stability and was able to restore image content even when conventional schemes completely failed. These findings suggest that DeepJSCC is a promising candidate for next-generation visual communication over 5G infrastructure.
DC.rights	This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
DC.format	103251
citation_title	5G Indoor/Outdoor Field Trial of Deep Joint Source-Channel Coding Method
citation_author	Hisano, Daisuke
	Matsumoto, Keigo
	Inoue, Yoshiaki
	Hara, Yuko
	Maruta, Kazuki
	Nakayama, Yu
	Tatsukawa, Hiroshi
	Kawai, Yuji
	Shinohara, Yoshinori
	Ikeda, Hiroki
citation_publisher	Institute of Electrical and Electronics Engineers Inc.
citation_language	英語
citation_date	2025-06-04
citation_journal_title	IEEE Open Journal of the Communications Society
citation_volume	6
citation_firstpage	4894
citation_lastpage	4907
citation_doi	https://doi.org/10.1109/OJCOMS.2025.3576502
citation_public_url	https://hdl.handle.net/11094/103251

5G Indoor/Outdoor Field Trial of Deep Joint Source-Channel Coding Method

閲覧可能ファイル

論文情報

論文詳細を表示