2022 Fiscal Year Final Research Report
Fundamental research for analysis of mesh location data
| Project/Area Number |
20K11720
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 60030:Statistical science-related
|
|---|
| Research Institution | Doshisha University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2020-04-01 – 2023-03-31
|
| Keywords | 位置情報データ / 時空間データ解析 / オンライン学習 / 異常検知 / メッシュ統計学 / 人流データ |
|---|
| Outline of Final Research Achievements |
In this study, we conducted fundamental research on methodologies for analyzing location data. Specifically, we focused on the disparity between "normal" and "abnormal" conditions and developed a method to clarify the factors contributing to this discrepancy. We devised a technique to improve the stability of location prediction and an approach for online learning-based anomaly detection. Additionally, we performed anomaly detection on a mesh using GPS-acquired people flow data, which accurately reflected variations in people flow during real disasters. The methodology developed in this study is applicable not only to mesh-based data but also to location data represented by geographic coordinates.
|
| Free Research Field |
統計科学
|
| Academic Significance and Societal Importance of the Research Achievements |
位置情報データは，その取得容易性から収集できるデータ自体は大きいもののそれを活用することは未だ困難な点が多いのが現状である．本研究では，異常検知の観点から位置情報データの分析手法の開発を行い，実際の位置情報データを用いて異常を検知できることを確認した．
本研究で提案した手法により，災害や大規模イベント発生時など，「平常」とされる状態とは異なる事態が発生した際にいち早くその状態を検出することが可能になり，二次災害を防ぐことや災害発生時のリスクマネジメントに役立つことが期待される．
|
