Updated on 2026/02/13

写真a

 
FUCHIDA Takayasu
 
Organization
Research Field in Cooperation, Integrated Arts and Sciences Area Computing and Communications Center Professor
Title
Professor
Degree
(2002.6 Kagoshima University)
(1990.3 Kagoshima University)
(1988.3 Kagoshima University)

Research Interests

  • 3次元形状モデリング

  • 自己組織的特徴写像

  • 離散ボロノイ図

  • 強化学習

Research Areas

数理情報工学, ニューラルネットワーク

Research History

  • 2020.4    Kagoshima University   Research Field in Engineering, Science and Engineering Area Graduate School of Science and Engineering (Engineering) Department of Engineering Information Science and Biomedical Engineering Program   Associate Professor

  • 1993.3 - 2020.3    Kagoshima University   Research Field in Engineering, Science and Engineering Area Graduate School of Science and Engineering (Engineering) Information Science and Biomedical Engineering Course   Associate Professor

Professional Memberships

  • 2015.10    情報処理学会

  • 2015.10    電子情報通信学会

 

Papers

  • Yamao K., Kawahara H., Kashima M., Fuchida T., Oda K. .  Remote Ship Control Through Head Mounted Display (HMD) Based User Experience .  ACM International Conference Proceeding Series   148 - 154   2024.12

    　More details

    Language：Japanese   Publisher：ACM International Conference Proceeding Series  

    This research aims to revolutionize the remote travel experience by addressing the lack of proactiveness of user often associated with virtual tours and pre-recorded videos. We propose a novel approach that utilizes a remote-controlled boat equipped with a 360-degree camera, stationed at popular coastal tourist destinations. This innovative setup enables users to engage in immersive experiences such as remote sightseeing, racing game simulations, and interactive fish feeding activities. During the development process, we encountered various challenges, including the selection of a suitable omnidirectional camera that balances quality, price, and compatibility with the boat’s system. Ensuring low-latency communication between the user’s device and the remote-controlled boat was also crucial for a seamless and responsive experience. Additionally, maintainability, battery operating time, and navigating regulatory requirements posed significant hurdles. To overcome these challenges, we implemented creative solutions. We opted for a compact digital camera capable of capturing 360-degree footage using the USB UVC protocol, striking a balance between image quality and affordability. We leveraged WebRTC protocol to achieve low-latency video streaming and control input transmission, minimizing perceptible delays and enhancing the user experience. To validate the effectiveness of our remote ship control system, we conducted an experiment using the Meta Quest 2 head-mounted display (HMD). Participants controlled the remote boat while immersed in the 360-degree video feed, experiencing the coastal environment as if they were physically present. The results confirmed the system’s ability to deliver an immersive and engaging remote travel experience. Looking ahead, we aim to address challenges such as reducing boat rocking, enhancing the sense of presence through additional sensory feedback, and implementing collision avoidance and automatic return functions for the boat. By refining and optimizing the system, we strive to offer users a truly transformative remote travel experience that brings them closer to the wonders of coastal destinations worldwide.

    DOI： 10.1145/3688268.3688290

    Scopus

  • 川原 弘暉, 小田 謙太郎, 渕田 孝康, 森 邦彦 .  放物面鏡を利用した全方位立体像の再生 .  三次元画像コンファレンス講演論文集30 ( 0 ) 43 - 46   2022.7

    　More details

    Language：Japanese   Publisher：3次元画像コンファレンス実行委員会  

    DOI： 10.60374/sanjigen.30.0_43

    CiNii Research

  • Wang R.H. .  Object discrimination performance and dynamics evaluated by inferotemporal cell population activity .  IBRO Neuroscience Reports10   171 - 177   2021.6

    　More details

    Language：Japanese   Publisher：IBRO Neuroscience Reports  

    We have previously reported an increase in response tolerance of inferotemporal cells around trained views. However, an inferotemporal cell usually displays different response patterns in an initial response phase immediately after the stimulus onset and in a late phase from approximately 260 ms after stimulus onset. This study aimed to understand the difference between the two time periods and their involvement in the view-invariant object recognition. Responses to object images with and without prior experience of object discrimination across views, recorded by microelectrodes, were pooled together from our previous experiments. With a machine learning algorithm, we trained to build classifiers for object discrimination. In the early phase, the performance of classifiers created based on data of responses to the object images with prior training of object discrimination across views did not significantly differ from that based on data of responses to the object images without prior experience of object discrimination across views. However, the performance was significantly better in the late phase. Furthermore, compared to the preferred stimulus image in the early phase, we found 2/3 of cells changed their preference in the late phase. For object images with prior experience of training with object discrimination across views, a significant higher percentage of cells responded in the late phase to the same objects as in the early phase, but under different views. The results demonstrate the dynamics of selectivity changes and suggest the involvement of the late phase in the view-invariant object recognition rather than that of the early phase.

    DOI： 10.1016/j.ibneur.2021.02.008

    Scopus

    PubMed

  • Hisanaga Tadanori, Fuchida Takayasu .  A proposal of calculation method for degree of cooperation between open data using predicate vector .    30 ( 1 ) 42 - 61   2020.2Reviewed

    　More details

    Authorship：Lead author   Language：Japanese   Publishing type：Research paper (scientific journal)  

  • CHEN Bo, FUCHIDA Takayasu, TOMARI Daiki, HISANAGA Tadanori .  A study on suggestion of predicates using the clustering of item names for making RDF of Open Data .  Joho Chishiki Gakkaishi30 ( 2 ) 236 - 241   2020

    　More details

    Language：Japanese   Publisher：Japan Society of Information and Knowledge  

    <p>　In recent years, there has been increasing interest in Open Data. The utilization of Open Data has been promoted, and many organizations including the national government, local governments and other organizations are working on publishing and utilizing Open Data. Open data of Kagoshima City has been published in July 2016 as CSV format. Under Open Data of local governments, even if they are disclosed due to the difference in data format and the lack of linkage of data, there is no active utilization yet. In this research, we focused on the vocabulary that corresponds to the predicate of RDF form for Open Data, and proposed a method to suggest predicates by the clustering of item names for RDF of Open Data as teacher signals of Deep Learning. Then, we presented results of the predicate suggestion.</p>

    DOI： 10.2964/jsik_2020_024

    CiNii Research

  • HISANAGA Tadanori, FUCHIDA Takayasu .  A study on the possibility of cooperation among Open Data using predicate vector .  Joho Chishiki Gakkaishi29 ( 2 ) 123 - 128   2019

    　More details

    Language：Japanese   Publisher：Japan Society of Information and Knowledge  

    <p>　In recent years, many administrative organizations and local governments are engaged in opening and utilizing open data but until the data utilization has not reached where the government promotes "data can be secondarily used without much manpower being machine-readable". The government has been promoting open data by formulating the "Electronic Administrative Open Data Strategy" in 2012 and operating the data catalog site "DATA.GO.JP" in 2014. Under the open data of local governments, even if they are disclosed due to the difference in data format and the lack of linkage of data, there is no active utilization yet. In this research, we propose a predicate vector method that measures the similarity of data by vectorizing item names and item values of CSV data disclosed to explore the possibility of open data of a local government. We also investigated the possibility of linkage between each data using the predicate vector method.</p>

    DOI： 10.2964/jsik_2019_024

    CiNii Research

  • HISANAGA Tadanori, FUCHIDA Takayasu .  Proposal of a recommendation method of Open Data Predicates using statistical processing .  Joho Chishiki Gakkaishi28 ( 2 ) 127 - 133   2018

    　More details

    Language：Japanese   Publisher：Japan Society of Information and Knowledge  

    <p>　In recent years, many administrative organizations and local governments are engaged in opening and utilizing open data but until the data utilization has not reached where the government promotes "data can be secondarily used without much manpower being machine-readable". If these open data can be easily converted to RDF format by using common predicates, utilization of open data by linking data is promoted. In this research, we applied an application of automatic generation of predicates using Word2Vec algorithm to convert data disclosed as open data into RDF format. We propose a predicate recommendation method to convert predicates corresponding to item names by using statistical processing called "predicate vector method" which is vectorizing each data item of open data and converting it to RDF format.</p>

    DOI： 10.2964/jsik_2018_010

    CiNii Research

  • HISANAGA Tadanori, FUCHIDA Takayasu, NOTO Daisuke, GUO hong, CHEN Bo .  Study on RDF conversion in Open Data .  Joho Chishiki Gakkaishi27 ( 2 ) 207 - 212   2017

    　More details

    Language：Japanese   Publisher：Japan Society of Information and Knowledge  

    <p>　In recent years, utilization of big data and open data has been promoted, and many organizations including the national government, local government and other organizations are working on opening and utilizing open data. These disclosed data formats are still many files in Word, Excel and CSV format. The data utilization that "It is machine-readable and second-hand use of data is possible without spending a lot of manpower" clearly stated in the 2012 e-administration open data strategy formulated in 2012 is not yet reached. If many disclosed data can be easily converted to RDF format<tt>，</tt>mechanical linkage of multiple open data becomes possible and it becomes possible to promote utilization of open data. In this research, we focused on the vocabulary that corresponds to the predicate of the RDF form, and experimented about the approximation of the vocabulary by utilizing the neural network called Wrod2Vec in order to share the vocabulary. We also propose a method to convert common Open Data to RDF format file by using vocabulary based on common vocabulary recommended by IPA to share common vocabulary.</p>

    DOI： 10.2964/jsik_2017_025

    CiNii Research

  • Takayasu Fuchida, Kathy Thi Aung .  A proposition of adaptive state space partition in reinforcement learning with Voronoi tessellation .  Artificial Life and Robotics, Springer18 ( 42067 ) 172 - 177   2013.11Reviewed

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

  • Kathy Thi Aung, Takayasu Fuchida .  A comparison of learning performance in two-dimensional Q-learning by the difference of Q-values alignment .  Artificial Life and Robotics, Springer16 ( 4 ) 473 - 477   2012.3Reviewed

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

  • Takayasu Fuchida, Kathy Thi Aung, Atsushi Sakuragi .  A study of Q-learning considering negative rewards .  Artificial Life and Robotics, Springer15 ( 3 ) 351 - 354   2010Reviewed

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

  • Kathy Thi Aung, Takayasu Fuchida .  Reinforcement learning using Voronoi space division .  Artificial Life and Robotics, Springer15 ( 3 ) 330 - 334   2010Reviewed

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

  • Akira Hiramatsu, Korakot Prachumrak, Takayasu Fuchida, Sadayuki Murashima .  Lossless Image Reconstruction of Image based on Contractive Mapping of Neighboring Pixels .  Proceedings of 2006 International Symposium on Nonlinear Theory and its Applications   1055 - 1058   2006.9Reviewed

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

  • Takayasu FUCHIDA, Sadayuki MURASHIMA, Hirofumi NAKAMURA .  Domain Search Using Shrunken Images for Fractal Image Compression .  Japan Journal of Industrial and Applied Mathematics   205 - 222   2005.6Reviewed

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

  • T. Fuchida, S. Murashima .  The Effectiveness of Discrete Voronoi Diagram in Fractal Image Compression .  Proceedings of 2004 International Symposium on Nonlinear Theory and its Application   561 - 564   2004.11Reviewed

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

  • 村島 定行, ゴラゴッド・プラチュムラック*, 平松章, 渕田孝康, 中村博文* .  離散画像の可逆フラクタル表現と関連する連立1次方程式とその収束特性 .  電子情報通信学会論文誌 A   1152 - 1157   2004.8Reviewed

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)  

  • 渕田孝康(FUCHIDA TAKAYASU),中村 博文(H. Nakamura),森邦彦(MoriKunihiko),村島定行 .  母点を一つずつ追加することにより効率良く２次元離散ボロノイ図を作成する方法 .  電子情報通信学会論文誌 ( 5 ) 571 - 583   2002.5Reviewed

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)  

  • 渕田孝康(FUCHIDA TAKAYASU),上原 修平(S. Uehara),森邦彦(MoriKunihiko),村島定行 .  離散ボロノイ図における母点の追加と削除のアルゴリズム .  電子情報通信学会論文誌 ( 8 ) 1027 - 1036   2001.8Reviewed

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)  

  • 森邦彦(MoriKunihiko),南元 淳一(J. Minamimoto),渕田孝康(FUCHIDA TAKAYASU),村島定行 .  One-Dimensional Resolution Improvement of Images in Time Series by Genetic Algorithm .  Sys. and Comp. in Japan32 ( 7 ) 12 - 19   2001.5Reviewed

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

  • 鹿嶋雅之,渕田孝康(FUCHIDA TAKAYASU),佐藤 明美(A. Satoh),森邦彦(MoriKunihiko),村島定行 .  位相表現回路網の結合数と入力次元の関係 .  電子情報通信学会論文誌 ( 12 ) 2855 - 2858   2000.12Reviewed

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)  

  • 渕田孝康(FUCHIDA TAKAYASU),森邦彦(MoriKunihiko),村島定行 .  波面法を用いた２次元一般離散ボロノイ図の作成 .  電子情報通信学会論文誌 ( 9 ) 927 - 935   2000.9Reviewed

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)  

  • 森邦彦(MoriKunihiko),南元 淳一(J. Minamimoto),渕田孝康(FUCHIDA TAKAYASU),村島定行 .  遺伝的アルゴリズムによる時系列画像の１次元高解像化 .  電子情報通信学会論文誌 ( 5 ) 1224 - 1231   2000.5Reviewed

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)  

  • 渕田孝康(FUCHIDA TAKAYASU),村島定行,渡辺 貴史(T. Watanabe),森邦彦(MoriKunihiko),栗園 貢(M. Kurizono) .  ２次元離散画面上の高次のボロノイ図作成について .  電子情報通信学会論文誌 ( 2 ) 283 - 288   1999.2Reviewed

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)  

  • 川田 一範(K. Kawata),森邦彦(MoriKunihiko),渕田孝康(FUCHIDA TAKAYASU),村島定行 .  時系列１次元画像の高解像化 .  電子情報通信学会論文誌 ( 12 ) 2879 - 2882   1998.12Reviewed

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)  

  • 鹿嶋雅之,村島定行,渕田孝康(FUCHIDA TAKAYASU),森邦彦(MoriKunihiko) .  マルチネスの位相表現回路網の位相保持率 .  電子情報通信学会論文誌 ( 12 ) 2892 - 2896   1998.12Reviewed

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)  

  • 倉田 俊一(S. Kurata),森邦彦(MoriKunihiko),渕田孝康(FUCHIDA TAKAYASU),村島定行 .  遺伝的アルゴリズムと反復処理を用いた劣化画像の回復 .  電子情報通信学会論文誌 ( 9 ) 2104 - 2111   1998.9Reviewed

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)  

  • 村島定行,渡辺 貴史(T. Watanabe),渕田孝康(FUCHIDA TAKAYASU),森邦彦(MoriKunihiko),M. Kurizono(栗園 貢) .  非ユークリッド距離に基づく２次元離散ボロノイ図の作成 .  電子情報通信学会論文誌 ( 6 ) 691 - 699   1998.6Reviewed

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)  

  • 渕田孝康(FUCHIDA TAKAYASU),村島定行,森邦彦(MoriKunihiko) .  ランダム論理ニューロン場の凍結状態に関する確率的考察 .  電子情報通信学会論文誌 ( 1 ) 203 - 207   1998.1Reviewed

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)  

▼display all

Presentations

  • Tadanori Hisanaga, Bo Chen, Daiki Tomari, Takayasu Fuchida   A proposal of the degree of linkage of open data using the predicate vector method   International conference

    25th International Symposium on Artificial Life and Robotics 2020  International Society of Artificial Life and Robotics

    　More details

    Event date： 2020.1

    Language：English   Presentation type：Oral presentation (general)  

    Venue：B-Con Plaza, Beppu, Oita, JAPAN  

  • Bo Chen, Tadanori Hisanaga, Daiki Tomari, Takayasu Fuchida   A study on suggestion of predicates using the clustering of item names for making RDF of Open Data   International conference

    25th International Symposium on Artificial Life and Robotics 2020  International Society of Artificial Life and Robotics

    　More details

    Event date： 2020.1

    Language：English   Presentation type：Oral presentation (general)  

    Venue：B-Con Plaza, Beppu, Oita, JAPAN  

  • 中野涼平, 伊藤研志, 富永　匠, 渕田孝康   VRを用いた直感的形状モデリングの研究  

    電機・情報関係学会九州支部連合大会 

    　More details

    Event date： 2019.9

    Language：Japanese   Presentation type：Oral presentation (general)  

  • 陳　博, 久永忠範, 泊　大貴, 永住拓視, 濱平　陸, 渕田孝康   オープンデータの述語サジェストのためのWord2Vecを用いた項目名のクラスタリング  

    電機・情報関係学会九州支部連合大会 

    　More details

    Event date： 2019.9

    Language：Japanese   Presentation type：Oral presentation (general)  

  • 福本光佑, 中野涼平, 伊藤研志, 富永　匠, 渕田孝康   音声認識による漫画への吹き出し作成の研究  

    電機・情報関係学会九州支部連合大会 

    　More details

    Event date： 2019.9

    Language：Japanese   Presentation type：Oral presentation (general)  

  • 久永忠範, 陳　博, 永住拓視, 濱平　陸, 泊　大貴, 渕田孝康   述語ベクトル法を用いたオープンデータの類似度の研究  

    電機・情報関係学会九州支部連合大会 

    　More details

    Event date： 2019.9

    Language：English   Presentation type：Oral presentation (general)  

  • 外園将太, 泊　大貴, 満園大輔, 早稲田凌亮, 中原航大, 渕田孝康   深層学習を用いたマルチエージェント強化学習の研究  

    電機・情報関係学会九州支部連合大会 

    　More details

    Event date： 2019.9

    Language：Japanese   Presentation type：Oral presentation (general)  

  • Tadanori HISANAGA, Takayasu FUCHIDA   A study on the possibility of cooperation among Open Data using predicate vector  

    　More details

    Event date： 2019.5

    Language：Japanese   Presentation type：Oral presentation (general)  

  • Kathy Thi Aung, Takayasu Fuchida   A proposition of adaptive state space partition in reinforcement learning with Voronoi Tessellation   International conference

    THE SEVENTEENTH INTERNATIONAL SYMPOSIUM ON ARTIFICIAL LIFE AND ROBOTICS  THE SEVENTEENTH INTERNATIONAL SYMPOSIUM ON ARTIFICIAL LIFE AND ROBOTICS

    　More details

    Event date： 2012.1

    Language：English  

    Venue：大分  

    国際学会

  • K.T. Aung, T. Fuchida   A comparison of learning performance in two-dimensional Q-learning by the difference of Q-values alignment   International conference

    THE SIXTEENTH INTERNATIONAL SYMPOSIUM ON ARTIFICIAL LIFE AND ROBOTICS  THE SIXTEENTH INTERNATIONAL SYMPOSIUM ON ARTIFICIAL LIFE AND ROBOTICS

    　More details

    Event date： 2011.1

    Language：English  

    Venue：大分  

    国際学会

▼display all

Research Projects

  • オープンデータ活用のための名前空間の整合性の研究

    2016.10 - 2019.3

    科学研究費補助金  基盤研究(C)