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

Efficient Deep Learning and its implementation for Robot-Based Rehabilitation Using Brain Signals

Research Project

Project/Area Number 21K03970
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 20020:Robotics and intelligent system-related
Research InstitutionHosei University

Principal Investigator

Capi Genci  法政大学, 理工学部, 教授 (20389399)

Project Period (FY) 2021-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2023: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2022: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2021: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Keywords深層学習 / BMI / ロ ボ ッ ト 動作 / 転移学習 / ロボット動作 / リハビリテーション / ロボットハンド / 遺伝的アルゴリズム / 効率的な深層学習
Outline of Research at the Start

本研究では、深層学習の一角をなすConvolution Neural Network (CNN)とEvolutionary Algorithm(EA)を組み合わせた新しい手法を提案する。EAにより学習済みCNNのゲノム部および訓練データをコード化し、分類成功率低下を抑制しつつ、訓練データ量および学習時間を従来比で半減させる。提案アルゴリズムにより生成したモデルを脳波信号に基づくロボットハンドの把持制御に適用し、その性能を検証するとともに、富山大学附属病院の協力の下、脳波信号制御のリハビリテーションロボットに応用する。

Outline of Final Research Achievements

In this research work, we developed efficient deep-learning algorithms for Brain Machine Interface (BMI) systems. The two main research topics were: 1) Optimization of electrode channels to improve the recognition rate of CNNs. We evaluated the performance in motor execution (ME) and motor imagery (MI) tasks. For channel optimization, we integrated DL and Deep Reinforcement Learning (DQL) algorithms. The primary objective of this system is to minimize the computational complexity and training time of the DL network without deterioration in the system performance. 2) Training data optimization for high-accuracy EEG classification using Genetic Algorithm (GA). EEG data from motor imagery and real hand/arm motion tasks were considered. The developed optimized systems are implemented in efficient robotic applications. The robots are controlled using EEG/EMG bio-signals. Such applications can be implemented in rehabilitation, human-robot interactions, and assistive robotic systems.

Academic Significance and Societal Importance of the Research Achievements

研究結果の科学的および社会的意義は以下の通りである:1. 訓練データの質を向上させることで、BMIシステムに向けたDLベースのネットワークを改善した。2. 訓練データを最適化し、CNNの認識精度の顕著な向上と訓練時間の短縮を実現した。3. Deep Q-learningベースの手法を用いて、BMIシステムにおけるEEGチャネルの最適化を実現した。
これらの結果は、脳信号を使用したCNNの高速訓練にも利用することが可能である。
また、このような柔軟性があり訓練が容易なCNNは、リハビリテーションなどのヒューマン・ロボット・インタラクションに応用することができる。

Report

(4 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • Research Products

    (19 results)

All 2024 2023 2022 2021 Other

All Journal Article (2 results) (of which Peer Reviewed: 2 results,  Open Access: 1 results) Presentation (14 results) (of which Int'l Joint Research: 12 results,  Invited: 1 results) Remarks (3 results)

  • [Journal Article] Genetic Algorithm-Based Data Optimization for Efficient Transfer Learning in Convolutional Neural Networks: A Brain Machine Interface Implementation2024

    • Author(s)
      G. Pongthanisorn, and G. Capi
    • Journal Title

      Robotics

      Volume: 13(1) Issue: 1 Pages: 1-12

    • DOI

      10.3390/robotics13010014

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Improving the Convolutional Neural Network Performance through Transfer Learning for Brain-Machine Interface Systems2022

    • Author(s)
      Eneo Petoku, Ryota Takahashi, Genci Capi
    • Journal Title

      International Journal of Innovative Computing, Information and Control

      Volume: 18 Issue: 05 Pages: 1587

    • DOI

      10.24507/ijicic.18.05.1587

    • ISSN
      1349-4198
    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Presentation] Combining Transfer Learning and Genetic Algorithms for Real-Time Gesture Recognition using EMG Signals2024

    • Author(s)
      G. Capi, K. Iizawa, S. Kaneko
    • Organizer
      The 10th International Conference on Mechatronics and Robotics Engineering
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] SEMI-SUPERVISED VARIATIONAL AUTOENCODER BASED OBJECT GRASPING RECOGNITION AND RECONSTRUCTION - A HUMAN ROBOT INTERACTION APPLICATION2024

    • Author(s)
      G. Pongthanisorn, Y. Lai, G. Capi
    • Organizer
      29th International Symposium on Artificial Life and Robotics
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Combining Genetic Algorithms and CNNs for Efficient Brain-Machine Interface Systems2023

    • Author(s)
      G. Pongthanisorn, and G. Capi
    • Organizer
      2023 IEEE 15th International Conference on Computational Intelligence and Communication Networks (CICN)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Data Selection Using Genetic Algorithm to Improve Transfer Learning Efficiency in Brain-Machine-Interface Systems2023

    • Author(s)
      S. Suguro, G. Pongthanisorn, S. Kaneko and G. Capi
    • Organizer
      2023 the 5th International Conference on Control and Robotics (ICCR 2023)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Image Reconstruction from Visual Perception and Visual Imagery for BMI systems2023

    • Author(s)
      Y, Sugimoto, G. Pongthanisorn, and G. Capi
    • Organizer
      The 16th edition of the IEEE International Symposium on Robotic and Sensors Environments, ROSE2023
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 変分オートエンコーダを用いたEMGデータの物体把持動作の認識―協働ロボットへの実装2023

    • Author(s)
      Y. Lai,G. Capi
    • Organizer
      人工生命研究会第8回ワークショップ,人工知能学会
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] EEG Channels Optimization for Wireless BMI-based Robot Interaction for Internet of Robotic Things2023

    • Author(s)
      Satoki Sugiyama, Goragod Pongthanisorn, Shirai Aya and Genci Capi
    • Organizer
      2023 6th Conference on Cloud and Internet of Things (CIoT)
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] Combination of Reinforcement and Deep Learning for EEG Channel Optimization on Brain-machine Interface Systems2023

    • Author(s)
      Goragod Pongthanisorn, Satoki Sugiyama, Shirai Aya and Genci Capi
    • Organizer
      2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] Optimizing Convolutional Neural Networks to Control the Robotic Hand using Brain Signals2022

    • Author(s)
      Satoki Sugiyama, Eneo Petoku, Ryota Takahashi and Genci Capi
    • Organizer
      2022 JSME-IIP/ASME-ISPS Joint Conference on Micromechatronics for Information and Precision Equipment (MIPE2022)
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] INTELLIGENT ASSISTIVE ROBOTS OPERATING IN HUMAN ENVIRONMENTS: DIRECTIONS AND CHALLENGES2022

    • Author(s)
      Genci Capi
    • Organizer
      2022 JSME-IIP/ASME-ISPS Joint Conference on Micromechatronics for Information and Precision Equipment (MIPE2022)
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] Effect of Number of Electrodes on Gesture Recognition: A Robotic Hand Implementation2022

    • Author(s)
      Kazuma Iizawa, Takuto Soeda, Aya Shirai and Genci Capi
    • Organizer
      2022 JSME-IIP/ASME-ISPS Joint Conference on Micromechatronics for Information and Precision Equipment (MIPE2022)
    • Related Report
      2022 Research-status Report
  • [Presentation] Mobile Humanoid Robot Control through Object Movement Imagery2022

    • Author(s)
      Eneo Petoku, Genci Capi
    • Organizer
      2022 4th International Conference on Control and Robotics
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research
  • [Presentation] BMIにおける転移学習を用いたCNNの性能向上2021

    • Author(s)
      R. Takahashi, S. Sugiyama, E. Petoku, A. Shirai and G. Capi
    • Organizer
      第19回コンピューテーショナル・インテリジェンス研究会
    • Related Report
      2021 Research-status Report
  • [Presentation] Deep Learning for Gesture Recognition based on Surface EMG Data2021

    • Author(s)
      Kaichi Fukano, Kazuma Iiazawa, Takuto Soeda, Aya Shirai, Genci Capi
    • Organizer
      The 2021 (11th) International Conference on Advanced Mechatronic Systems (ICAMechS 2021)
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Remarks] Brain-Robot Interface Research Group

    • URL

      https://assistrobotics.ws.hosei.ac.jp/research_group_bci.html

    • Related Report
      2023 Annual Research Report
  • [Remarks] デ ィ ー プ ラ ー ニ ン グ を 用い た BMIシ ス テ ム の 開発

    • URL

      http://assistrobotics.ws.hosei.ac.jp/research_group_bci_jp.html

    • Related Report
      2022 Research-status Report
  • [Remarks] ディープラーニングを用いたBMIシステムの開発

    • URL

      http://assistrobotics.ws.hosei.ac.jp/research_group_bci_jp.html

    • Related Report
      2021 Research-status Report

URL: 

Published: 2021-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi