2018 Fiscal Year Annual Research Report
DeepMob: Learning Deep Models from Big and Heterogeneous Data for Next-generation Urban Emergency Management
| Project/Area Number |
17H01784
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
宋 軒 東京大学, 空間情報科学研究センター, 准教授 (20600737)
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Keywords | Disaster Informatics / Big Data and Data Mining / Artificial Intelligence / Urban Computing / Internet of Things |
|---|
| Outline of Annual Research Achievements |
In the 2018 fiscal year, the research progress of this project is very good, and our research achievements can be summarized as follows:
(1)We developed an online deep ensemble learning model for predicting citywide human mobility. Our approach was evaluated using a real-world GPS-log dataset from Tokyo and Osaka and achieved a higher prediction accuracy than baseline models. (2) We proposed a deep ROI-based modeling approach for effectively predicting urban human mobility. Experimental results demonstrate that the superior performance and several real-world practices show the applicability of our approach to real-world urban computing problems.
Our research results were published in the eminent publications for computer science including ACM IMWUT 2018 and Applied Energy.
|
| Current Status of Research Progress |
Current Status of Research Progress
1: Research has progressed more than it was originally planned.
Reason
The research progress of this project is good. Firstly, we developed an online deep ensemble learning model for predicting citywide human mobility.Secondly, we proposed a deep ROI-based modeling approach for effectively predicting urban human mobility.
Our research results were published in the eminent publications for computer science including ACM IMWUT 2018 and Applied Energy.
|
| Strategy for Future Research Activity |
In the third year of this project, will focus on developing an intelligent system that is able to automatically simulate and predict population movements during the disaster or emergency events.
For evaluating our system, we will collaborate with our indusial partner. We will use the feedback we obtain from the field evaluation to refine the system models and implementations to improve our overall results.
|
