Development of an extraction method of interaction patterns from heterogeneous time series datasets and its evaluation
| Project/Area Number |
18K18108
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 61030:Intelligent informatics-related
|
|---|
| Research Institution | Nara Institute of Science and Technology |
|---|
Principal Investigator |
Kubo Takatomi 奈良先端科学技術大学院大学, 先端科学技術研究科, 特任准教授 (20631550)
|
|---|
| Project Period (FY) |
2018-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2019: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2018: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | 時系列分節化 / 相互作用 / ノンパラメトリックベイズ法 / 階層構造 |
|---|
| Outline of Final Research Achievements |
In this study, we developed a method that extract interaction patterns from heterogeneous time series datasets and an evaluation method for the interaction. In our method, we used Beta Process Auto-Regressive Hidden Markov Model to extract primitive patterns and NPYLM to identify complex patterns based on primitive one. Our method can extract interaction patterns from datasets recorded under the situation where controlling experimental conditions are difficult.We presented this study in several international workshops (Briones et al., 2018, etc.) and submitted a manuscript to an international journal.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究では，時間的に変化する未知の相互作用のパターンを複数の時系列データセットから自動検出し，かつ相互作用の定量的評価を可能とする手法の開発を行った．環境統制が困難な状況下で計測された時系列データに対しても相互作用パターンを抽出できるため，広く応用可能な手法であると言える．人と人の関わりをはじめ，動物間・非生物間までも含め，対象を問わずに相互作用分析への応用が可能である．幅広く，様々な科学的分析での応用が期待される．
|
Report
(3 results)
Research Products
(10 results)
