Yamada Koji




Researcher Number(JSPS Kakenhi)


Current Affiliation Organization 【 display / non-display

  • Duty   University of the Ryukyus   Faculty of Engineering   School of Engineering_Computer Science and Intelligent Systems Program   Professor  

Academic degree 【 display / non-display

  • Hokkaido University -  Doctor of Engineering

External Career 【 display / non-display

  • 1999.04

    University of the Ryukyus, Faculty of Engineering, Associate Professor  

  • 2014.04

    University of the Ryukyus, Faculty of Engineering, Professor  

Research Interests 【 display / non-display

  • Intelligent Robotics,Artificial Intelligence and Life,Emergent Systems

  • 創発システム

  • マルチエージェントシステム

  • 複雑系工学

Research Areas 【 display / non-display

  • Informatics / Intelligent informatics

  • Informatics / Perceptual information processing

  • Informatics / Perceptual information processing

Research Theme 【 display / non-display

  • Game Strategy Acquisition by Competitive co-evolution algorithm

  • Collective behavior of Multi-agent systems for Mollusk-Type Robot

Published Papers 【 display / non-display

  • Development of the Estimation Model for Intentions to Move Based on Gaze and Face Information with 1DCNN-LSTM and Evaluation of Electric Wheelchair Driving

    Sho Higa, Koji Yamada, Shihoko Kamisato

    2021 Ninth International Symposium on Computing and Networking Workshops (CANDARW) ( IEEE )    429 - 433   2021.11 [ Peer Review Accepted ]

    Type of publication: Research paper (international conference proceedings)

  • MolGANの拡張による文章グラフを用いた文章生成手法の提案

    澤崎 夏希, 遠藤 聡志, 當間 愛晃, 山田 孝治, 赤嶺 有平

    知能と情報 ( 日本知能情報ファジィ学会 )  32 ( 2 ) 668 - 677   2020 [ Peer Review Accepted ]

    Type of publication: Research paper (scientific journal)

     View Summary

    <p>深層学習によって様々な分類問題が解決されているが,分類カテゴリ毎のデータ量が不均衡な問題を扱う場合,多くの課題がある.不均衡データへの対策として,少量カテゴリのデータ量を増加させ均衡化する手法がある.これをかさ増しと呼び画像処理分野ではノイズの付与や回転による方法が一般的である.最近ではGenerative Adversarial Network: GANによる画像生成手法を用いる場合がある.一方で,自然言語処理の分野では有効なかさ増し手法はいまだ確立されておらず,人手によるかさ増しが行われている.人手によるかさ増しではルールの設計など負担が大きく,機械的なかさ増し手法が必要となる.しかし,文章生成における機械的なかさ増しは画像生成に比べ不安定である.これは文章の特徴獲得の難しさが原因だと考えられる.そこで本論文ではグラフ情報に注目した機械学習による文章生成手法を提案する.CaboChaによって生成されたグラフ情報をGraph Convolutionにより畳み込み処理する.提案するGANにより生成されたかさ増し文章を3つの計算実験により評価し有効性を示した.</p>

  • 多様化する大学教育シリーズ(第1回)社会課題に取り組むワークショップとその効果 : 琉球大学・京都大学合同デザインスクールの経験

    當間 愛晃, 山田 孝治, 遠藤 聡志, 十河 卓司, 石田 亨

    電子情報通信学会誌 = The journal of the Institute of Electronics, Information and Communication Engineers ( 電子情報通信学会 )  102 ( 2 ) 172 - 178   2019.02 [ Peer Review Accepted ]

    Type of publication: Research paper (scientific journal)

     View Summary


  • 畳み込みニューラルネットワークを用いた表情表現の獲得と顔特徴量の分析

    西銘 大喜, 遠藤 聡志, 當間 愛晃, 山田 孝治, 赤嶺 有平

    人工知能学会論文誌 ( 社団法人 人工知能学会 )  32 ( 5 ) F - H34_1-8   2017

    Type of publication: Research paper (scientific journal)

     View Summary

    <p>Facial expressions play an important role in communication as much as words. In facial expression recognition by human, it is difficult to uniquely judge, because facial expression has the sway of recognition by individual difference and subjective recognition. Therefore, it is difficult to evaluate the reliability of the result from recognition accuracy alone, and the analysis for explaining the result and feature learned by Convolutional Neural Networks (CNN) will be considered important. In this study, we carried out the facial expression recognition from facial expression images using CNN. In addition, we analysed CNN for understanding learned features and prediction results. Emotions we focused on are "happiness", "sadness", "surprise", "anger", "disgust", "fear" and "neutral". As a result, using 32286 facial expression images, have obtained an emotion recognition score of about 57%; for two emotions (Happiness, Surprise) the recognition score exceeded 70%, but Anger and Fear was less than 50%. In the analysis of CNN, we focused on the learning process, input and intermediate layer. Analysis of the learning progress confirmed that increased data can be recognised in the following order "happiness", "surprise", "neutral", "anger", "disgust", "sadness" and "fear". From the analysis result of the input and intermediate layer, we confirmed that the feature of the eyes and mouth strongly influence the facial expression recognition, and intermediate layer neurons had active patterns corresponding to facial expressions, and also these activate patterns do not respond to partial features of facial expressions. From these results, we concluded that CNN has learned the partial features of eyes and mouth from input, and recognise the facial expression using hidden layer units having the area corresponding to each facial expression.</p>

  • 反応角度を自動調節可能なジョイスティック型コントローラの開発

    比嘉 聖, 神里 志穂子, 山田 孝治, 眞喜志 隆, 佐竹 卓彦, 山田 親稔

    電気学会論文誌. D, 産業応用部門誌 ( 一般社団法人 電気学会 )  136 ( 10 ) 703 - 710   2016

    Type of publication: Research paper (scientific journal)

     View Summary

    <p>In nearby special support schools, the practice of driving a motorized wheelchair using a joystick has been conducted for physically disabled children. However, physically disabled children require support and adjustment of the equipment corresponding to their disabilities because it is difficult to operate a joystick in a specific direction owing to their disabilities. In this study, we develop a joystick-type controller that can be automatically adjusted to the reaction angle suitable for the actual conditions of physically disabled children. Moreover, we conduct a quantitative evaluation of upper limb motion when operating the joystick-type controller that we developed to examine the effectiveness of the proposed method. The evaluation results confirm an effective improvement in the operability when the acquired reaction angle is suitable for the actual conditions of the user by the proposed method.</p>

display all >>

Other Papers 【 display / non-display

display all >>

Presentations 【 display / non-display

  • Modeling and Simulation of Motion Control for Modular Robots

    Sunil Pranit Lal,山田 孝治,遠藤 聡志

    The 9th SICE conference on System Integration (SI 2008)  2008.12  -  2008.12 

  • A novel approach towards controlling modular robotic systems.

    Sunil Pranit Lal,山田 孝治,遠藤 聡志

    The 18th Intelligent System Symposium (FAN 2008)  2008.10  -  2008.10