Final Stage Disaster Prediction at the Disaster Warning Stage
Project/Area Number |
24310121
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Partial Multi-year Fund |
Section | 一般 |
Research Field |
Social systems engineering/Safety system
|
Research Institution | Kyushu Institute of Technology |
Principal Investigator |
HIROSE Hideo 九州工業大学, 大学院情報工学研究院, 教授 (60275401)
|
Project Period (FY) |
2012-04-01 – 2015-03-31
|
Project Status |
Completed (Fiscal Year 2014)
|
Budget Amount *help |
¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2014: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2013: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2012: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
Keywords | リスク予測 / 微分方程式 / SIR / マトリクス分解 / PoP / 最適試験法 / 寿命推定法 / アンサンブル法 / マトリクス分解法 / 信頼性工学 / パンデミック |
Outline of Final Research Achievements |
In the risk analysis methods, such as pandemic, final stage disaster prediction at the disaster warning stage becomes extremely important. Since a use of single approach alone cannot provide a good prediction accuracy, we developed the ensemble method, called PoP (prediction on predictions), consisting of statistical methods, the agent model, differential equation model, and the machine learning method. Applying the method to SARS, Ebola, Dengue, influenza cases, we obtained superior prediction results at early stage than the use of single approach. For seasonal disasters, the matrix decomposition method, used in recommendation systems, is found to be useful. In addition, we proposed a new mathematical model for electric insulation deterioration, and introduced it to IEC committee.
|
Report
(4 results)
Research Products
(79 results)