• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Transfer learning technique for user-friendly human-computer interfaces

Research Project

Project/Area Number 20K19854
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 61020:Human interface and interaction-related
Research InstitutionNational Institute of Advanced Industrial Science and Technology

Principal Investigator

Kanoga Suguru  国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 研究員 (40803903)

Project Period (FY) 2020-04-01 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2021: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2020: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Keywords転移学習 / 機械学習 / 信号処理 / ブレインコンピュータインタフェース / 筋電位 / ヒューマンインタフェース / 深層学習
Outline of Research at the Start

2020年度に【課題1】を実施する。2021年度は【課題2】を実施しつつ、キャリブレーションに必要なデータ数や転移学習法の計算コストに合わせて【課題1】のアルゴリズムの簡略化もしくは高度化を試みる。【課題1】は信号処理や機械学習に関する国際会議あるいは論文誌に投稿することを目指し、【課題2】はロボティクスやエンジニアリングに関する国際会議あるいは論文誌に投稿することを目指す。

Outline of Final Research Achievements

This study aimed to develope transfer learning methods that statistically correct the distributions of target and source data with large inter- and intra-subject valiability by using a small amount of calibration data under short calibration session. For this purpose, we used surface electromyogram (sEMG) data, which are known to have large individual differences. I developed a framework that incorporates domain adaptation transfer learning methods for both labeled and unlabeled sEMG data for a small number of target sEMG data.

Academic Significance and Societal Importance of the Research Achievements

研究成果はIF付論文誌2報と国際論文誌1報として公開されている。論文誌についてはオープンアクセスであり、だれでも内容を確認することができる。また、開発されたコードはgithubと呼ばれる開発プラットフォームにおいて公開されている。これにより生体信号処理分野での研究開発を透明感のある状態とした。
近年、ウェアラブルセンサを用いて個人がデータを簡単にデータを計測できるようになってきている。このような状況において、既存のモデルを個々に合わせてチューニングできる転移学習法の開発は今後のヒューマンインタフェースをより発展させる意義を持つ。

Report

(3 results)
  • 2021 Annual Research Report   Final Research Report ( PDF )
  • 2020 Research-status Report
  • Research Products

    (11 results)

All 2022 2021 2020 Other

All Journal Article (5 results) (of which Peer Reviewed: 5 results,  Open Access: 5 results) Presentation (5 results) (of which Int'l Joint Research: 3 results,  Invited: 2 results) Remarks (1 results)

  • [Journal Article] Comparing subject-to-subject transfer learning methods in surface electromyogram-based motion recognition with shallow and deep classifiers2022

    • Author(s)
      Hoshino Takayuki、Kanoga Suguru、Tsubaki Masashi、Aoyama Atsushi
    • Journal Title

      Neurocomputing

      Volume: - Pages: 599-612

    • DOI

      10.1016/j.neucom.2021.12.081

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Subject-transfer framework with unlabeled data based on multiple distance measures for surface electromyogram pattern recognition2022

    • Author(s)
      Kanoga Suguru、Hoshino Takayuki、Asoh Hideki
    • Journal Title

      Biomedical Signal Processing and Control

      Volume: 74 Pages: 103522-103522

    • DOI

      10.1016/j.bspc.2022.103522

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Semi-supervised style transfer mapping-based framework for sEMG-based pattern recognition with 1- or 2-DoF forearm motions2021

    • Author(s)
      Kanoga Suguru、Hoshino Takayuki、Asoh Hideki
    • Journal Title

      Biomedical Signal Processing and Control

      Volume: 68 Pages: 102817-102817

    • DOI

      10.1016/j.bspc.2021.102817

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Semi-Supervised Learning for Auditory Event-Related Potential-Based Brain-Computer Interface2021

    • Author(s)
      Ogino Mikito、Kanoga Suguru、Ito Shin-Ichi、Mitsukura Yasue
    • Journal Title

      IEEE Access

      Volume: 9 Pages: 47008-47023

    • DOI

      10.1109/access.2021.3067337

    • NAID

      120007153316

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Are armband sEMG devices dense enough for long-term use? Sensor placement shifts cause significant reduction in recognition accuracy2020

    • Author(s)
      Kanoga Suguru、Kanemura Atsunori、Asoh Hideki
    • Journal Title

      Biomedical Signal Processing and Control

      Volume: 60 Pages: 101981-101981

    • DOI

      10.1016/j.bspc.2020.101981

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] A Style Transfer Mapping and Fine-tuning Subject Transfer Framework Using Convolutional Neural Networks for Surface Electromyogram Pattern Recognition2022

    • Author(s)
      Kanoga Suguru, Hoshino Takayuki, Tada Mitsunori
    • Organizer
      2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'22)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 機械学習を用いた脳波・筋電信号の応用例紹介およびアーチファクト除去・転移学習によるロバスト性向上2022

    • Author(s)
      叶賀 卓
    • Organizer
      日本生体工学会 専門別研究会 第32回実社会におけるマルチモーダル脳情報応用技術研究会
    • Related Report
      2021 Annual Research Report
    • Invited
  • [Presentation] 生体信号時系列への機械学習技術の適用と日常的な技術適用での問題点・解決アプローチの紹介2021

    • Author(s)
      叶賀 卓
    • Organizer
      第32回日本急性血液浄化学会学術集会
    • Related Report
      2021 Annual Research Report
    • Invited
  • [Presentation] Analysis and Usage: Subject-to-subject Linear Domain Adaptation in sEMG Classification2020

    • Author(s)
      Takayuki Hoshino、Suguru Kanoga、Masashi Tsubaki、Atsushi Aoyama
    • Organizer
      2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Subject Transfer Framework Based on Source Selection and Semi-Supervised Style Transfer Mapping for sEMG Pattern Recognition2020

    • Author(s)
      Suguru Kanoga、Takayuki Hoshino、Hideki Asoh
    • Organizer
      ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Remarks] Suguru KANOGA/Publications

    • URL

      https://sites.google.com/view/u4ag2knosr1/publication

    • Related Report
      2021 Annual Research Report 2020 Research-status Report

URL: 

Published: 2020-04-28   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi