Current Affiliation Organization 【 display / non-display 】

Current Affiliation Organization 【 display / non-display 】

Academic degree 【 display / non-display 】

Academic degree 【 display / non-display 】

External Career 【 display / non-display 】

External Career 【 display / non-display 】

Research Interests 【 display / non-display 】

Research Interests 【 display / non-display 】

Research Areas 【 display / non-display 】

Research Areas 【 display / non-display 】

Published Papers 【 display / non-display 】

Published Papers 【 display / non-display 】

• Proposal of a Data Augmentation Method Using ChatGPT for Japanese Imbalanced Data

  Natsuki Sawasaki and Satoshi Endo

  ICIC Express Letters, Part B: Applicatiions ( ICIC International )  15 ( 10 ) 999 - 1007   2024.10 [ Peer Review Accepted ]

  Type of publication: Research paper (scientific journal)

  　View Summary

  As the exploitation of large-scale data advances, numerous classification issues are being effectively addressed. However, significant challenges persist when dealing with imbalanced data. In cases of data imbalance, ideally, new data would be annotated for the underrepresented categories. Nonetheless, in practical terms, data augmentation strategies are often employed to generate analogous data for these minor categories. While there are numerous issues associated with data augmentation techniques within the realm of natural language processing, no definitive methods have been established until the efficacy of ChatGPT for English data augmentation was demonstrated. However, it is known that its performance decreases for languages other than English, and there has been limited validation in Japanese. Consequently, in this research, we sought to annotate and augment the Livedoor News Corpus using ChatGPT, and through a comparative analysis of accuracy changes, we validated the effectiveness of ChatGPT for Japanese imbalanced data.

  • Access this article

    DOI

• Classification of Rainfall Intensity and Cloud Type from Dash Cam Images Using Feature Removal by Masking

  Kodai Suemitsu,Satoshi Endo, Shunsuke Sato

  Climate ( MDPI )  12 ( 5 )   2024.05 [ Peer Review Accepted ]

  Type of publication: Research paper (scientific journal)

  • Access this article

    DOI Repository

• 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.

  • Access this article

    DOI Repository

• 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)

display all >>

Books 【 display / non-display 】

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

Presentations 【 display / non-display 】

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 

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

  遠藤　聡志

  第77回全国大会  2015  -  2015 

• 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 

display all >>

Grant-in-Aid for Scientific Research 【 display / non-display 】

Grant-in-Aid for Scientific Research 【 display / non-display 】

• Grant-in-Aid for Young Scientists(B)

  Project Year: 2001.04  -  2003.03 

  Direct: 2,100,000 (YEN)  Overheads: 630,000 (YEN)  Total: 2,730,000 (YEN)

SDGs 【 display / non-display 】

SDGs 【 display / non-display 】