Endo Satoshi

写真a

Title

Professor

Researcher Number(JSPS Kakenhi)

00223686

Mail Address

E-mail address

To the head of this page.▲

Current Affiliation Organization 【 display / non-display 】

  • Concurrently   University of the Ryukyus   Graduate School of Engineering and Science   Interdisciplinary Intelligent Systems Engineering   Professor  

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

  • Concurrently   University of the Ryukyus   Graduate School of Engineering and Science   Computer Science and Intelligent Systems   Professor  

To the head of this page.▲

Academic degree 【 display / non-display 】

  • Hokkaido University -  Doctor of Engineering

To the head of this page.▲

External Career 【 display / non-display 】

  • 1990.04
    -
    1995.03

    Hokkaido University Faculty of Engineering Department of Information Engineering, Research Assistants  

  • 2005.02
    　
    　

    University of the Ryukyus, Faculty of Engineering, Department of Information Engineering, Information Systems, Professor  

To the head of this page.▲

Research Interests 【 display / non-display 】

  • Artificial Intelligence

  • Complex Systems Engineering

To the head of this page.▲

Research Areas 【 display / non-display 】

  • Manufacturing Technology (Mechanical Engineering, Electrical and Electronic Engineering, Chemical Engineering) / Control and system engineering

  • Informatics / Intelligent informatics

  • Informatics / Kansei informatics

To the head of this page.▲

Published Papers 【 display / non-display 】

  • Sentence Generation Method by Extension of MolGAN Using Sentence Graph

    Natsuki SAWASAKI, Satoshi ENDO, Naruaki TOMA, Koji YAMADA, Yuhei AKAMINE

    Journal of Japan Society for Fuzzy Theory and Intelligent Informatics ( Japan Society for Fuzzy Theory and Intelligent Informatics )  32 ( 2 ) 668 - 677   2020.04 [ Peer Review Accepted ]

    Type of publication: Research paper (scientific journal)

    　View Summary

    Deep learning solves many classification problems. However, it is difficult to solve problems with imbalanced data. Therefore, the data volume is increased for the purpose of balancing. This is called data augmentation. Generally, the method of image data augmentation uses noise addition, rotation, and the like. Recently, images are generated using the generative adversary network: GAN. However, data augmentation methods are difficult in natural language processing. In addition, manual data augmentation is burdensome and requires mechanical methods. Mechanical text augmentation is more difficult than images. Because it is difficult to analyze the feature of sentences. This paper proposes a sentence generation method by machine learning focusing on graph information. The graph information obtained by CaboCha is processed by graph Convolution. The proposed GAN was used to generate sentences, and then three experiments were performed to evaluate its effectiveness.

  • Monocular Depth Estimation with a Multi-Task and Multiple-Input Architecture Using Depth Gradient

    Michiru Takamine, Satoshi Endo

    2020 Joint 11th International Conference on Soft Computing and Intelligent Systems and 21st International Symposium on Advanced Intelligent Systems (SCIS-ISIS) ( Japan Society for Fuzzy Theory and intelligent informatics (SOFT) )    379 - 384   2020.12 [ Peer Review Accepted ]

    Type of publication: Research paper (international conference proceedings)

  • Workshop on Social Problems and Its Effects : From Our Experience with University of the Ryukyus and Kyoto University Joint Design School

    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)

  • Feature Acquisition and Analysis for Facial Expression Recognition Using Convolutional Neural Networks

    Nishime Taiki, Endo Satoshi, Toma Naruaki, Yamada Koji, Akamine Yuhei

    Transactions of the Japanese Society for Artificial Intelligence ( The Japanese Society for Artificial Intelligence )  32 ( 5 ) F - H34_1-8   2017.09 [ Peer Review Accepted ]

    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>

    • Access this article
      DOI

  • A study on emotion estimation of narratives using cognitive appraisals of the reader

    Toma N.

    2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings ( 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings )    572 - 576   2017.02 [ Peer Review Accepted ]

    Type of publication: Research paper (scientific journal)

    • Access this article
      DOI

display all >>

To the head of this page.▲

Books 【 display / non-display 】

  • The Immune Distributed Competitive Problem Solver Using Major Histocompatibility Complex and Immune Network OPERATIONS RESEARCH

    Naruaki Toma, ENDO SATOSHI ( Part: Multiple Authorship )

    その他の出版機関  2002.03

To the head of this page.▲

Presentations 【 display / non-display 】

  • Deep Learning におけるコストを考慮した Dropout率制御に関する検証

    玉城 翔, 當間愛晃, 赤嶺有平, 山田孝治, 遠藤聡志

    第77回全国大会  2015.03  -  2015.03 

  • 投稿時間のクラスター分析によるTwitterユーザの年齢層推定

    遠藤　聡志

    2015年度 人工知能学会全国大会  2015  -  2015 

  • 感情推定に基づく小説推薦システムのための認知的評価質問セットを用いたシミュレーション

    遠藤　聡志

    第77回全国大会  2015  -  2015 

  • 可変長N-gramに基づいたトピックへのラベル選択の検証

    Endo Satoshi

    第77回全国大会  2015  -  2015 

  • フーリガン集団による暴力行為シミュレーションの基礎研究

    遠藤　聡志

    2015年度 人工知能学会全国大会  2015  -  2015 

display all >>

To the head of this page.▲

SDGs 【 display / non-display 】

  • 単眼カメラ画像による深度推定（他　深層学習関連の研究テーマ複数）

To the head of this page.▲