A novel genetic algorithm with different structure selection for circuit design optimization

Zhiguo Bao, Takahiro Watanabe

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In the traditional GA, the tournament selection for crossover and mutation is based on the fitness of individuals. This can make convergence easy, but some useful genes may be lost. In selection, as well as fitness, we consider the different structure of each individual compared with an elite one. Some individuals are selected with many different structures, and then crossover and mutation are performed from these to generate new individuals. In this way, the GA can increase diversification into search spaces so that it can find a better solution. One promising application of GA is evolvable hardware (EHW), which is a new research field to synthesize an optimal circuit. We propose an optimal circuit design by using a GA with a different structure selection (GAdss), and with a fitness function composed of circuit complexity, power, and signal delay. Its effectiveness is shown by simulations. From the results, we can see that the best elite fitness, the average fitness value of correct circuits, and the number of correct circuits with GAdss are better than with GA. The best case of optimal circuits generated by GAdss is 8.1% better in evaluation value than that by traditional GA.

Original languageEnglish
Pages (from-to)266-270
Number of pages5
JournalArtificial Life and Robotics
Volume14
Issue number2
DOIs
Publication statusPublished - 2009 Nov

Fingerprint

Genetic algorithms
Mutation
Networks (circuits)
Research
Genes
Design optimization
Hardware

Keywords

  • Circuit design optimization
  • Evolutionary algorithm
  • Evolvable hardware
  • Genetic algorithm

ASJC Scopus subject areas

  • Artificial Intelligence
  • Biochemistry, Genetics and Molecular Biology(all)

Cite this

A novel genetic algorithm with different structure selection for circuit design optimization. / Bao, Zhiguo; Watanabe, Takahiro.

In: Artificial Life and Robotics, Vol. 14, No. 2, 11.2009, p. 266-270.

Research output: Contribution to journalArticle

@article{8dfb6e02d4ce44cb88952a6449ad1eb2,
title = "A novel genetic algorithm with different structure selection for circuit design optimization",
abstract = "In the traditional GA, the tournament selection for crossover and mutation is based on the fitness of individuals. This can make convergence easy, but some useful genes may be lost. In selection, as well as fitness, we consider the different structure of each individual compared with an elite one. Some individuals are selected with many different structures, and then crossover and mutation are performed from these to generate new individuals. In this way, the GA can increase diversification into search spaces so that it can find a better solution. One promising application of GA is evolvable hardware (EHW), which is a new research field to synthesize an optimal circuit. We propose an optimal circuit design by using a GA with a different structure selection (GAdss), and with a fitness function composed of circuit complexity, power, and signal delay. Its effectiveness is shown by simulations. From the results, we can see that the best elite fitness, the average fitness value of correct circuits, and the number of correct circuits with GAdss are better than with GA. The best case of optimal circuits generated by GAdss is 8.1{\%} better in evaluation value than that by traditional GA.",
keywords = "Circuit design optimization, Evolutionary algorithm, Evolvable hardware, Genetic algorithm",
author = "Zhiguo Bao and Takahiro Watanabe",
year = "2009",
month = "11",
doi = "10.1007/s10015-009-0668-z",
language = "English",
volume = "14",
pages = "266--270",
journal = "Artificial Life and Robotics",
issn = "1433-5298",
publisher = "Springer Japan",
number = "2",

}

TY - JOUR

T1 - A novel genetic algorithm with different structure selection for circuit design optimization

AU - Bao, Zhiguo

AU - Watanabe, Takahiro

PY - 2009/11

Y1 - 2009/11

N2 - In the traditional GA, the tournament selection for crossover and mutation is based on the fitness of individuals. This can make convergence easy, but some useful genes may be lost. In selection, as well as fitness, we consider the different structure of each individual compared with an elite one. Some individuals are selected with many different structures, and then crossover and mutation are performed from these to generate new individuals. In this way, the GA can increase diversification into search spaces so that it can find a better solution. One promising application of GA is evolvable hardware (EHW), which is a new research field to synthesize an optimal circuit. We propose an optimal circuit design by using a GA with a different structure selection (GAdss), and with a fitness function composed of circuit complexity, power, and signal delay. Its effectiveness is shown by simulations. From the results, we can see that the best elite fitness, the average fitness value of correct circuits, and the number of correct circuits with GAdss are better than with GA. The best case of optimal circuits generated by GAdss is 8.1% better in evaluation value than that by traditional GA.

AB - In the traditional GA, the tournament selection for crossover and mutation is based on the fitness of individuals. This can make convergence easy, but some useful genes may be lost. In selection, as well as fitness, we consider the different structure of each individual compared with an elite one. Some individuals are selected with many different structures, and then crossover and mutation are performed from these to generate new individuals. In this way, the GA can increase diversification into search spaces so that it can find a better solution. One promising application of GA is evolvable hardware (EHW), which is a new research field to synthesize an optimal circuit. We propose an optimal circuit design by using a GA with a different structure selection (GAdss), and with a fitness function composed of circuit complexity, power, and signal delay. Its effectiveness is shown by simulations. From the results, we can see that the best elite fitness, the average fitness value of correct circuits, and the number of correct circuits with GAdss are better than with GA. The best case of optimal circuits generated by GAdss is 8.1% better in evaluation value than that by traditional GA.

KW - Circuit design optimization

KW - Evolutionary algorithm

KW - Evolvable hardware

KW - Genetic algorithm

UR - http://www.scopus.com/inward/record.url?scp=72449178491&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72449178491&partnerID=8YFLogxK

U2 - 10.1007/s10015-009-0668-z

DO - 10.1007/s10015-009-0668-z

M3 - Article

VL - 14

SP - 266

EP - 270

JO - Artificial Life and Robotics

JF - Artificial Life and Robotics

SN - 1433-5298

IS - 2

ER -