| Project/Area Number |
24700234
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | Kansai University |
|---|
Principal Investigator |
HANADA Yoshiko 関西大学, システム理工学部, 助教 (30511711)
|
|---|
| 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: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2012: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
|
|---|
| Keywords | 進化計算 / 遺伝的プログラミング / 交叉 / 木構造 / 局所探索 / 近傍 |
|---|
| Research Abstract |
In this study, a multistep crossover which can generate offspring keeping parents' good characteristics without inducing a bloat was developed for genetic programming. This crossover performs successively local search along the path connecting the parents. We considered the largest common sub-graph observed between parents as the characteristic that should not be destroyed, and defined the neighborhood structure and the corresponding pair-wise distance based on it to develop the local search.
It was shown that the proposed method works very well on several symbolic regression problems, an artificial ant problem, and a design problem of stack filters for digital images.
|
