Learning Probabilistic Simulation Models for Rare Event/Condition Occurrence
| Project/Area Number |
24650069
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
WASHIO Takashi 大阪大学, 産業科学研究所, 教授 (00192815)
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
IBA Yutaka 統計数理研究所, モデリング研究系, 准教授 (30213200)
SHIMIZU Shohei 大阪大学, 産業科学研究所, 准教授 (10509871)
KAWAHARA Yoshinobu 大阪大学, 産業科学研究所, 准教授 (00514796)
|
|---|
| Project Period (FY) |
2012-04-01 – 2014-03-31
|
| Project Status |
Completed (Fiscal Year 2013)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2013: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2012: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Keywords | 知識発見 / データマイニング / 確率モデル / 機械学習 / 希少事象 / 災害 / 希少事象解析 / 希少事象シミュレーション / マルコフチェインモンテカルロ / 統計的推定 / 確率的シミュレーション / 希少シナリオ / 大規模洪水 / 河川水流モデル / 降雨確率モデル |
|---|
| Research Abstract |
Various approaches for learning probabilistic models from given data and background knowledge have been studied in the past, however, studies on the probabilistic model learning for rare/special conditions have been very limited. In this study, we developed an efficient and accurate approach to learn probabilistic simulation models for the rare/special conditions by using a given data set and its associated background knowledge. Moreover, we demonstrated a novel framework for the probabilistic estimation and prediction of rare/special events and scenarios through its applications to a rare and large scale natural disaster.
|
Report
(3 results)
Research Products
(16 results)
-
-
-
-
-
-
-
-
-
-
[Presentation] Bootstrap confidence intervals in DirectLiNGAM2012
Author(s)
Kittitat Thamvitayakul, Shohei Shimizu, Tsuyoshi Ueno, Takashi Washio and Tatsuya Tashiro
Organizer
RIKD: Workshop on Reliability Issues in Knowledge Discovery, ICDM 2012. The IEEE International Conference on Data Mining
Place of Presentation
Brussels, Belgium
Related Report
-
-
-
-
-
-
