| Project/Area Number |
18H03287
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 61030:Intelligent informatics-related
|
|---|
| Research Institution | Kyushu University (2019-2021)
Osaka University (2018) |
|---|
Principal Investigator |
Kawahara Yoshinobu 九州大学, マス・フォア・インダストリ研究所, 教授 (00514796)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
中尾 裕也 東京工業大学, 工学院, 教授 (40344048)
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Project Status |
Completed (Fiscal Year 2021)
|
| Budget Amount *help |
¥16,770,000 (Direct Cost: ¥12,900,000、Indirect Cost: ¥3,870,000)
Fiscal Year 2021: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2020: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2019: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2018: ¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
|
|---|
| Keywords | 非線形ダイナミクス / 作用素論的解析 / 機械学習 / 統計的機械学習 / データ科学 / 非線形動力学 / 位相縮約 / データ駆動科学 |
|---|
| Outline of Final Research Achievements |
With the development of measurement technology and information infrastructure, the extraction of scientific knowledge by data-driven approaches using observation / measurement data has been recognized as an important issue in various fields. In this study, we worked on the development of machine learning algorithms for extracting from data dynamic characteristics (dynamics) that complicated phenomena follow. In particular, we have developed methods for extracting information on complex systems and evaluating their validities by expanding the operator-theoretic analysis, including Koopman analysis, which is attracting attention in the field of physics recently, based on the framework of machine learning. We also developed machine learning algorithms to use extracted information for prediction. Finally, we conducted applied research in collaboration with researchers in multiple scientific fields to verify its usefulness.
|
| Academic Significance and Societal Importance of the Research Achievements |
データ駆動による科学的知識の抽出は，近年様々な領域においてますます重要となっている．本研究では，データ駆動により複雑現象に関する動的特性の情報抽出を行い，そしてそれを更に予測へ用いるための新たな機械学習に基づく理論・アルゴリズムの構築を進めた．また，脳波解析や集団運動をはじめとしたいくつかの科学領域におけるデータ解析に対して適用し，その有用性を確認した．このような課題は広く科学領域において重要となるものであり，本研究で得られた成果は，本研究でも取り組んだ分野に限らず今後広く他分野へと波及する技術的要素となることが期待できる．
|
