### 抄録

The rapid increase of computer power enabled us to solve many real world problems using optimization algorithms. However, the recent novel metaheuristic algorithms do not stand on concrete ground like traditional algorithms did. Therefore, there should be many rooms to improve those algorithms, and one of the way is to alter the formula of an algorithm. In this study, we define algorithm designing as an optimization problem, and use genetic programming to find new mutation schemes for differential evolution. In addition, we evaluate the generated mutation schemes using several benchmarks to verify that the proposed methods and the generated algorithms are effective ones.

元の言語 | English |
---|---|

ホスト出版物のタイトル | Proceedings of the SICE Annual Conference |

ページ | 1548-1549 |

ページ数 | 2 |

出版物ステータス | Published - 2013 |

イベント | 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013 - Nagoya, Japan 継続期間: 2013 9 14 → 2013 9 17 |

### Other

Other | 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013 |
---|---|

国 | Japan |

市 | Nagoya |

期間 | 13/9/14 → 13/9/17 |

### Fingerprint

### ASJC Scopus subject areas

- Electrical and Electronic Engineering
- Control and Systems Engineering
- Computer Science Applications

### これを引用

*Proceedings of the SICE Annual Conference*(pp. 1548-1549)

**Designing optimal updating rule for differential evolution using genetic programming.** / Kanemasa, Minoru; Aiyoshi, Eitaro.

研究成果: Conference contribution

*Proceedings of the SICE Annual Conference.*pp. 1548-1549, 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013, Nagoya, Japan, 13/9/14.

}

TY - GEN

T1 - Designing optimal updating rule for differential evolution using genetic programming

AU - Kanemasa, Minoru

AU - Aiyoshi, Eitaro

PY - 2013

Y1 - 2013

N2 - The rapid increase of computer power enabled us to solve many real world problems using optimization algorithms. However, the recent novel metaheuristic algorithms do not stand on concrete ground like traditional algorithms did. Therefore, there should be many rooms to improve those algorithms, and one of the way is to alter the formula of an algorithm. In this study, we define algorithm designing as an optimization problem, and use genetic programming to find new mutation schemes for differential evolution. In addition, we evaluate the generated mutation schemes using several benchmarks to verify that the proposed methods and the generated algorithms are effective ones.

AB - The rapid increase of computer power enabled us to solve many real world problems using optimization algorithms. However, the recent novel metaheuristic algorithms do not stand on concrete ground like traditional algorithms did. Therefore, there should be many rooms to improve those algorithms, and one of the way is to alter the formula of an algorithm. In this study, we define algorithm designing as an optimization problem, and use genetic programming to find new mutation schemes for differential evolution. In addition, we evaluate the generated mutation schemes using several benchmarks to verify that the proposed methods and the generated algorithms are effective ones.

KW - Differential evolution

KW - Evolutionary algorithm designing

KW - Genetic programming

UR - http://www.scopus.com/inward/record.url?scp=84888586419&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84888586419&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84888586419

SP - 1548

EP - 1549

BT - Proceedings of the SICE Annual Conference

ER -