KEIO RESEARCHERS INFORMATION SYSTEM

Career 【 Display / hide 】

Career 【 Display / hide 】

• 2014.04

  -

  2018.09

  日本電信電話株式会社, NTTアクセスサービスシステム研究所, 研究員

• 2014.04

  -

  2018.09

  NIPPON TELEGRAPH AND TELEPHONE CORPORATION, NTT Access Network Service Systems Laboratories, Engineer

• 2018.10

  -

  2026.03

  Osaka University, Graduate School of Engineering, 助教

• 2018.10

  -

  2026.03

  The University of Osaka, Graduate School of Engineering, Assistant Professor

• 2026.04

  -

  Present

  Keio University, 理工学部 電気情報工学科, 准教授

display all >>

Academic Background 【 Display / hide 】

Academic Background 【 Display / hide 】

• 2010.04

  -

  2012.03

  Osaka University, School of Engineering, Division of Electronic and Information Engineering

  University, Graduated

• 2012.04

  -

  2014.03

  Osaka University, Graduate School of Engineering, Division of Electrical, Electronic and Information Engineering

  Graduate School, Completed, Master's course

• 2017.10

  -

  2018.09

  Osaka University, Graduate School of Engineering, Division of Electrical, Electronic and Information Engineering

  Graduate School, Completed, Doctoral course

Academic Degrees 【 Display / hide 】

Academic Degrees 【 Display / hide 】

• Ph. D, Osaka University, Coursework, 2018.09

Research Areas 【 Display / hide 】

Research Areas 【 Display / hide 】

• Manufacturing Technology (Mechanical Engineering, Electrical and Electronic Engineering, Chemical Engineering) / Communication and network engineering

• Informatics / Information network

Research Keywords 【 Display / hide 】

Research Keywords 【 Display / hide 】

• Semantic Communications

• Signal Processing

• Optical Communications

• Communication Systems

Papers 【 Display / hide 】

Papers 【 Display / hide 】

• Image Value-Based Dynamic Spatial Stream Allocation in Deep Joint Source-Channel Coded MIMO Transmission for Extreme Environment

  S. Inokuma, G. Sawada, D. Hisano, K. Maruta

  Journal on Wireless Communications and Networking 2026 ( 1 )  2026.05

  Accepted

  　View Summary

  This paper proposes a value-aware spatial stream allocation strategy for deep joint source-channel coding (DeepJSCC) incorporated with multiple-input multiple-output (MIMO), aimed at enhancing image transmission quality under extreme environment such as underwater scenarios. In MIMO eigenmode transmission, each stream can achieve a different diversity combining gain, with the principal stream exhibiting the highest gain. The proposed scheme allocates spatial streams of individual eigenmodes to image blocks based on their perceptual importance, which is extracted using a saliency map. Simulation results confirm that the proposed scheme achieves higher perceptual quality and structural similarity, especially in low-SNR conditions. This work demonstrates the potential of integrating semantic awareness into physical layer design, contributing to robust and efficient image communication in mission-critical applications.

  • Access to Document (DOI)

• Toward Mobility-Aware Semantic Communication: DeepJSCC Over Time-Varying MIMO Channels

  G. Sawada, S. Inokuma, D. Hisano, K. Maruta

  Journal on Wireless Communications and Networking  2026.05

  Accepted

  • Access to Document (DOI)

• Channel-Wise Masked Deep Joint Source-Channel Coding for Rateless Size-Independent Image Transmission

  Hisano D.

  Proceedings IEEE Consumer Communications and Networking Conference Ccnc  2026

  ISSN  23319860

  　View Summary

  Deep joint source-channel coding (DeepJSCC) has emerged as a promising paradigm that integrates source and channel coding into an end-to-end learned transmission pipeline. While conventional DeepJSCC models are typically trained for a fixed compression rate, practical communication requires flexible adaptation to varying bandwidths and channel conditions. This work proposes a simple yet effective design of rateless DeepJSCC that applies stochastic masking along the channel dimension of the encoder's final convolutional layer. By assigning learned priorities to channels and transmitting only a subset according to available resources, the model achieves rateless adaptability while preserving the CNN-based property of being independent of input image resolution. Through experiments, we validate the effectiveness of the proposed approach. On CIFAR-10, the method achieves more stable training and slightly better PSNR and SSIM compared with the conventional rateless DeepJSCC, especially at low symbol-per-pixel (SPP) rates. On DIV2K, the proposed method achieves performance comparable to individually trained fixed-rate DeepJSCC models, while maintaining the advantage of size-independence. Overall, the results demonstrate that the proposed method provides stable and efficient rate adaptation.

  • Access to Document (DOI)

• LUT-GenNet: Target-PSNR- and Input-Guided Neural Lookup Table for Adaptive Rate Control in Deep Joint Source-Channel Coding

  Toyoshima K., Hisano D.

  IEEE International Conference on Communications  2026

  ISSN  15503607

  　View Summary

  Deep joint source-channel coding (DeepJSCC) is a promising technology for high efficiency wireless image transmission, but many existing models adopt a fixed compression rate. To address this problem, this paper proposes a DeepJSCC with lookup table generation network (LUT-GenNet), a novel scheme that provides peak signal-to-noise ratio (PSNR) guaranteed adaptive compression rate control. Conventional adaptive rate control approaches determine the compression ratio after encoding, which makes a processing bottleneck. Furthermore, since the encoder requires channel SNR information, if the channel SNR changes after it is obtained and encoding is performed, the image quality can degrade significantly. The proposed LUT-GenNet is a neural network that generates an image-specific LUT directly from the input image. This LUT instantaneously determines the optimal compression rate based on the target PSNR and channel SNR. This approach enables parallel processing of encoding and rate determination and avoids the SNR mismatch problem because the encoder does not rely on SNR feedback. A comparison with the conventional method under SNR mismatch conditions showed that while the conventional performance degrades significantly as the mismatch increases, the proposed method maintains stable.

  • Access to Document (DOI)

• GPU-Enabled Adaptive Frequency Domain Equalization for Fully Virtualized Coherent Access Networks

  Yamasaki A., Suzuki T., Kim S.Y., Kani J.I., Shimada T., Hisano D.

  IEEE Access 14   35669 - 35677 2026

  　View Summary

  In recent years, access and metro networks have been transitioning toward architectures based on disaggregation and virtualization, where software-based implementation of physical-layer signal processing on general-purpose computing platforms has become an important technical challenge. In next-generation access systems, digital coherent transmission enables high-order modulation and polarization multiplexing but requires computationally intensive digital signal processing, such as polarization demultiplexing and adaptive equalization, to be executed in real-time. However, conventional time-domain equalization suffers from computational complexity that increases linearly with the number of equalizer taps, making real-time operation challenging under long-tap conditions caused by chromatic dispersion compensation and future wideband transceivers. To address this issue, this paper proposes a multi-thread frequency-domain adaptive equalizer (MT-FDE) that fully exploits the parallel processing capability of a graphics processing unit (GPU). By combining fast Fourier transform (FFT)-based frequency-domain processing with batch processing, the proposed method reduces computational complexity to logarithmic order with respect to the tap length and enables real-time adaptive equalization including polarization demultiplexing. Numerical simulations and offline and real-time experiments demonstrate that the proposed MT-FDE improves the tolerance to increased tap numbers by a factor of 4.8 and achieves real-time operation under long-tap conditions while maintaining transmission performance comparable to that of conventional time-domain equalizers, providing practical design guidelines for fully virtualized coherent access networks.

  • Access to Document (DOI)

display all >>

Reviews, Commentaries, etc. 【 Display / hide 】

Reviews, Commentaries, etc. 【 Display / hide 】

• Efforts toward Underwater Large-Scale MIMO-OFDM Transmission

  丸田一輝, 野中柊次, 久野大介, 出口充康, 樹田行弘, 志村拓也

  電子情報通信学会技術研究報告(Web) 125 ( 131(RCC2025 18-32) )  2025

  ISSN  2432-6380

• Deep Joint Source-Channel Coding using Overlap Image Division for Block Noise Reduction

  山本龍之介, 井上文彰, 久野大介

  電子情報通信学会技術研究報告(Web) 123 ( 248(CS2023 62-79) )  2023

  ISSN  2432-6380

• Impact of Learning Models on Deep Joint Source Channel Coding Adaptable to 5G Systems

  山本龍之介, 松本啓吾, 井上文彰, 原祐子, 丸田一輝, 中山悠, 久野大介

  電子情報通信学会技術研究報告(Web) 123 ( 137(CS2023 18-58) )  2023

  ISSN  2432-6380

• ［ポスター講演］A-QLに基づく OCC における動的光源追従システム

  佐々木 友基, 丸田 一輝, 小島 駿, 久野 大介, 中山 悠

  信学技報  2022.10

• ［ポスター講演］情報源-通信路深層結合符号化器における量子化雑音の画像品質への影響解析

  松本 啓吾, 井上 文彰, 丸田 一輝, 原 祐子, 中山 悠, 久野 大介

  信学技報  2022.10

  Last author, Corresponding author

display all >>

Research Projects of Competitive Funds, etc. 【 Display / hide 】

Research Projects of Competitive Funds, etc. 【 Display / hide 】

• 極限通信環境に適応するTask-OrientedなAI連携型通信技術の開拓

  2025

  -

  2028

  科学技術振興機構, 戦略的な研究開発の推進/戦略的創造研究推進事業/さきがけ, No Setting

  　View Summary

  本研究は、通信資源が著しく制限される極限的実環境において、マルチモーダルデータを安定かつ効率的に取得・伝送可能とするAI連携型通信システム基盤を構築することを目的とする。特に、極限的実環境として、海中通信環境、深宇宙通信環境、狭帯域セルラー通信環境の3つに注力し、これらの現場から得られる情報をAIシステムが活用可能な形式で確実に伝送できる低遅延かつ高信頼な通信インフラの確立を目指す。

• Task-OrientedなAI連携型通信技術の開拓

  2024

  -

  2026

  科学技術振興機構, 戦略的な研究開発の推進/戦略的創造研究推進事業/ACT-X, No Setting

  　View Summary

  ビット情報のみならず情報源の意図や意味を通信するセマンティック通信に関する研究を行います。具体的には、深層学習を用いた情報源-通信路深層結合符号化（Deep JSCC）法の水中音響通信および光ファイバ通信への適用を加速させます。研究者が今までに取り組んできた5Gセルラー通信向けDeep JSCCをさらに発展させた将来技術として、等化機能をDeep JSCCに組み込んだDeep JSCCEの検討を行います。

• Signal Compression on Optical Wireless Transmission Systems

  2022.04

  -

  2025.03

  Japan Society for the Promotion of Science, Grants-in-Aid for Scientific Research Grant-in-Aid for Early-Career Scientists, Grant-in-Aid for Early-Career Scientists, Principal investigator

• Beyond 5G通信インフラを高効率に構成するメトロアクセス光技術の研究開発

  2021.10

  -

  2025.03

  情報通信研究機構, Beyond 5G研究開発促進事業 委託研究, Coinvestigator(s)

• 端末通信機能構成技術の開発

  2021.10

  -

  2024.10

  国立研究開発法人新エネルギー・産業技術総合開発機構（NEDO）, ポスト5G情報通信システム基盤強化研究開発事業／ポスト5G情報通信システムの開発, Coinvestigator(s)

display all >>

Intellectual Property Rights, etc. 【 Display / hide 】

Intellectual Property Rights, etc. 【 Display / hide 】

• 通信システム

  Date applied： 特願2017-122901  2017.06 

  Date announced： 特開2019-009588  2019.01 

  Patent

• 通信装置

  Date applied： 特願2017-123407  2017.06 

  Date announced： 特開2019-009611  2019.01 

  Patent

• ネットワークシステム

  Date applied： 特願2017-122263  2017.06 

  Date announced： 特開2019-009557  2019.01 

  Patent

• 通信装置及び信号転送方法

  Date applied： 特願2017-118820  2017.06 

  Date announced： 特開2019-004379  2019.01 

  Patent

• 通信装置

  Date applied： 特願2017-111072  2017.06 

  Date announced： 特開2018-207308  2018.12 

  Patent

display all >>

Awards 【 Display / hide 】

Awards 【 Display / hide 】

• 通信ソサイエティ活動功労賞

  2025.09, 電子情報通信学会

• 2024年 論文賞

  2024.12, 電子情報通信学会 光通信システム研究会

• Best Paper Award

  2024.11, ACP/IPOC2024

• 2024年度 委員長賞

  2024.07, 電子情報通信学会 コミュニケーションシステム研究会

• 大阪大学賞

  2023.11, 大阪大学

display all >>

Courses Taught 【 Display / hide 】

Courses Taught 【 Display / hide 】

• ELECTROMAGNETISM

  2026, Spring Semester, Undergraduate (specialized), Lecture, Within own ｆaculty

• GRADUATE RESEARCH ON ENGINEERING AND DESIGN 2

  2026

• DOCTORAL RESEARCH ON ENGINEERING AND DESIGN

  2026

• TOPICS IN ELECTRONICS AND INFORMATION ENGINEERING

  2026, Spring Semester

• SEMINAR IN ELECTRONICS AND INFORMATION ENGINEERING(1)

  2026

display all >>

Courses Previously Taught 【 Display / hide 】

Courses Previously Taught 【 Display / hide 】

• Electromagnetism

  Keio University

  2026.04

  -

  Present

• Signals and Systems

  Technische Universiteit Eindhoven (PIXNET Visiting Scholar)

  2022.07

• Signals and Systems

  School of Engineering, Osaka University

  2022.04

  -

  2022.09

• 学問への扉

  大阪大学

  2022.04

  -

  2022.09

• Signals and Systems

  Osaka University

  2022

  , 

  Spring Semester, Undergraduate (specialized), Lecture, Within own ｆaculty

display all >>