| Project/Area Number |
22510166
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Social systems engineering/Safety system
|
|---|
| Research Institution | Hiroshima Shudo University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KAIO Naoto 広島修道大学, 経済科学部, 教授 (80148741)
HIROMITSU Seijirou 広島修道大学, 経済科学部, 教授 (90043827)
|
|---|
| Project Period (FY) |
2010-04-01 – 2014-03-31
|
| Project Status |
Completed (Fiscal Year 2013)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2013: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2012: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2011: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2010: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
|
|---|
| Keywords | 非線形最適化 / 多点探索法 / サンプリング / 近傍構造 / 近似モデル / 低精度近似モデル / 制約付き最適化 / 差分進化 / 直接探索法 / メタヒューリスティスティクス / Differential Evolution / 関数形状推定 / Expensive Optimization / 近接グラフ / 種分化 / 高次元最適化 / ε制約法 / アーカイブ / 回転不変性 / ファジィクラスタリング / 貪欲戦略 / ランク情報 / 最適化アルゴリズム / 進化的計算 / 機械学習 / Expensive optimization |
|---|
| Research Abstract |
We proposed methods that improved the efficiency and the robustness of population-based optimization algorithms, such as differential evolution: 1. Methods that dynamically tune algorithm parameters (1)according to the landscape modality of the objective function which is estimated by sampling the objective values along a line and by using proximity graphs and neighborhood structures, (2)according to the estimated distribution of search points, (3)according to the ranking-information of points. Their advantages are shown by solving benchmark problems and comparing them with other methods. 2. Efficient constrained optimization methods that combined estimated comparison method with epsilon constrained method. The estimated comparison is a comparison using rough approximation model. By comparing with several rough models, it is shown that the potential model is the most efficient model for the estimated comparison.
|
