Updated on 2024/01/10

写真a

 
Keshi ikuo
 

Degree

  • Bachelor of Engineering   Coursework ( 1981.3   Osaka University )

  • Master of Engineering   Coursework ( 1983.3   Osaka University )

  • Dctor (Engineering)   Coursework ( 2017.9   Nara Institute of Science and Technology )

Research Interests

  • Artificial Intelligence

  • Natural Language Processing

  • Machine Learning

  • Text Mining

Research Areas

  • Informatics / Database

Education

  • Osaka University   Electronic Engineering   Graduated

    - 1981.3

  • Osaka University   Electronic Engineering   Master's Course   Completed

    - 1983.3

  • Nara Institute of Science and Technology   Doctor's Course   Completed

    - 2017.9

Research History

  • Nara Institute of Science and Technology   Part-time lecturer

    2017.11 - 2018.3

  • Sharp Corporation   Corporate R&D Group   Chief Technical Research Fellow

  • Fukui University of Technology   Professor

    2017.10

Professional Memberships

  • Japan Society of Health Information Management

Committee Memberships

  • 13th International Conference on Knowledge Discovery and Information Retrieval   Program Committee Membership  

    2021.4 - 2021.10   

  •   Program Committee Membership  

    2022.4 - 2022.10   

  • 15th International Conference on Knowledge Discovery and Information Retrieval   Program Committee Membership  

    2023.4 - 2023.10   

Studying abroad experiences

  • 1989.7 - 1990.1   Massachusetts Institute of Technology   Visiting Researcher, Artificial Intelligence Laboratory

  • 1988.9 - 1989.6   Massachusetts Institute of Technology   Fellow, Center for Advanced Engineering Study

Qualification acquired

  • JDLA Deep Learning for ENGINEER 2021#2

 

Papers

  • Interpretable Disease Name Estimation based on Learned Models using Semantic Representation Learning of Medical Terms. Reviewed

    Ikuo Keshi, Ryota Daimon, Atsushi Hayashi

    Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management   1   265 - 272   2022.10

     More details

    This paper describes a method for constructing a learned model for estimating disease names using semantic representation learning for medical terms and an interpretable disease-name estimation method based on the model. Experiments were conducted using old and new electronic medical records from Toyama University Hospital, where the data distribution of disease names differs significantly. The F1-score of the disease name estimation was improved by about 10 points compared with the conventional method using a general word semantic vector dictionary with a faster linear SVM. In terms of the interpretability of the estimation, it was confirmed that 70% of the disease names could provide higher-level concepts as the basis for disease name estimation. As a result of the experiments, we confirmed that both interpretability and accuracy for disease name estimation are possible to some extent.

  • Semantically Readable Distributed Representation Learning and Its Expandability Using a Word Semantic Vector Dictionary Reviewed

    Ikuo KESHI, Yu SUZUKI, Koichiro YOSHINO, Satoshi NAKAMURA

    IEICE TRANSACTIONS on Information and Systems   E101-D ( 4 )   1066 - 1078   2018.4

  • Semantically Readable Distributed Representation Learning for Social Media Mining Reviewed

    Ikuo Keshi, Yu Suzuki, Koichiro Yoshino, Satoshi Nakamura

    Proceedings of the International Conference on Web Intelligence   2017.8

  • Associative image retrieval using knowledge in encyclopedia text Invited Reviewed

    Ikuo Keshi, Hiroshi Ikeuchi, Ken'Ichi Kuromusha

    Systems and Computers in Japan   27 ( 12 )   53 - 62   1996

  • Speech-Act Based Message Conversation System Reviewed

    Ikuo Keshi, Boris Katz

    Proc. of International Workshop on CSCW   4 ( 91 )   59 - 73   1991.4

  • BMIR-J2: A Test Collection for Evaluation of Japanese Information Retrieval Systems Reviewed

    Tetsuya Sakai, Tsuyoshi Kitani, Yasushi Ogawa, Tetsuya Ishikawa, Haruo Kimoto, Ikuo Keshi, Jun Toyoura, Toshikazu Fukushima, Kunio Matsui, Yoshihiro Ueda, Takenobu Tokunaga, Hiroshi Tsuruoka, Hidekazu Nakawatase, Teru Agata, Noriko Kando

    SIGIR Forum   33 ( 1 )   13 - 17   1999

  • Lessons from BMIR-J2: A Test Collection for Japanese IR Systems Reviewed

    Tsuyoshi Kitani, Yasushi Ogawa, Tetsuya Ishikawa, Haruo Kimoto, Ikuo Keshi, Jun Toyoura, Toshikazu Fukushima, Kunio Matsui, Yoshihiro Ueda, Tetsuya Sakai, Takenobu Tokunaga, Hiroshi Tsuruoka, Hidekazu Nakawatase, Teru Agata

    Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval   1998.8

  • Semantically Readable Distributed Representation Learning and Its Expandability Using a Word Semantic Vector Dictionary

    Ikuo Keshi

    2017.9

  • 3D Revolving User Interface Optimized for Tablets and a Cloud-Based Media Service Invited

    Ikuo Keshi, Sunao Yamaguchi, Toshiro Mukai, Hiroyuki Yamamura, Haruo Hinode, Hironori Inoue, Masayuki Nakazawa, Shinichiro Ota, Akihiro Azuma, Yu Matsumoto

    In Proc. of International Display Workshops (IDW’11)   2011.11

  • Implementation of simultaneous video decoding on multicore processor Reviewed

    Yuki Kawamura, Yasutake Manabe, Takao Onoye, Kazuto Ohara, Hiroyuki Okada, Ikuo Keshi

    Communications, Control and Signal Processing (ISCCSP)   2010.3

  • Design and Implementation of Home Network Protocol for Appliance Control Based on IEEE 802.15.4 Reviewed

    Masanao Ise, Yasuhiro Ogasahara, Kenji Watanabe, Masahide Hatanaka, Takao Onoye, Hiroaki Niwamoto, Ikuo Keshi, Isao Shirakawa

    International Journal of Computer Science and Network Security   7 ( 7 )   20 - 30   2007.7

  • An energy-efficient architecture of wireless home network based on MAC broadcast and transmission power control Reviewed

    Kenji Watanabe, Masanao Ise, Takao Onoye, Hiroaki Niwamoto, Ikuo Keshi

    IEEE Trans. Consumer Electronics   53 ( 1 )   124 - 130   2007

  • Is home network application acceptable or not? Invited Reviewed

    Ikuo Keshi, Yumi Shiraishi, Hiroaki Niwamoto, Minoru Okada, Heiichi Yamamoto

    International Symposium on Circuits and Systems (ISCAS 2005)   5   5337 - 5340   2005.5

  • A knowledge-based framework in an intelligent assistant system for making documents Invited Reviewed

    Ikuo Keshi, Naoyuki Fukuda, Yoshiji Fujimoto

    Future Generation Computer Systems   5 ( 1 )   51 - 58   1989

▼display all

Presentations

  • Introduction of the NEDO Healthcare Application Protocol (HAP) for Health Monitoring Devices International conference

    Ikuo Keshi, et al.

    ISO/IEEE11073 Personal Health Data Work Group 

  • Speech-Act Based Message Conversation System

    Ikuo Keshi

    6th Symposium on Human Interface 

 

Teaching Experience

  • Artificial Intelligence

  • Software Engineering

  • Computer Fundamentals

    Institution:Fukui University of Technology

  • Advanced Computer Science

  • Electromagnetism I

    Institution:Fukui University of Technology

  • Electrical and electronic engineering experiment III

    Institution:Fukui University of Technology

  • Career Design II

    Institution:Fukui University of Technology

  • Electrical and electronic measurement I

    Institution:Fukui University of Technology

  • Advanced electromagnetism

    Institution:Fukui University of Technology

  • Carrier seminar I

    Institution:Fukui University of Technology

  • Electrical and electronic engineering experiment II

    Institution:Fukui University of Technology

  • Electrical and electronic measurement II

    Institution:Fukui University of Technology

  • Carrier seminar II

    Institution:Fukui University of Technology

  • Electrical and electronic engineering experiment I

    Institution:Fukui University of Technology

  • Creative science

    Institution:Fukui University of Technology

  • Computer literacy

    Institution:Fukui University of Technology

▼display all