| Project/Area Number |
17K00141
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Information network
|
|---|
| Research Institution | Chiba Institute of Technology |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2019: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2018: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2017: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
|
|---|
| Keywords | 人の移動 / 確率モデル / 強化学習 / ネットワーク科学 / 社会ネットワーク / 人の移動パターン / 移動モデル / ブロックチェーン / ヒューマンモビリティ / データ科学 / 移動体通信 / 統計数学 / 非常時通信 |
|---|
| Outline of Final Research Achievements |
Mathematical models that reproduce the statistical properties of human mobility and encounter patterns have been studied. Some researches have also been undertaken to assimilate human mobility data and human mobility models. But, it is necessary to consider a method to assimilate the data and the model even when the amount of data itself is very small and sufficient learning cannot be performed. Reinforcement learning is known as one of machine learning methods, but a method of generating a human mobility model using reinforcement learning has not been sufficiently studied. In this study, I studied a method to automatically generate a human mobility model by learning human mobility data by reinforcement learning. As a result, it was found that the method tends to generate a returner's mobility model.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究成果より，災害時の人の移動のように，学習するデータが非常に少ない状況における人の移動モデルの自動生成を行う為の土台となる枠組みを構築できた．これに加えて人の移動から報酬モデルを自動生成する枠組みを構築することにより，現実の人の移動パターンに近い移動モデルを生成することができ，これを用いた様々な社会シミュレーションを行うことが可能になると期待できる．
|
