A Novel Selection Circuit Based on Rough Comparison Method for Genetic Algorithms Hardware

  • Hiratsuka Tomokazu
    Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology
  • Tamukoh Hakaru
    Institute of Symbiotic and Technology, Tokyo University of Agriculture and Technology
  • Horio Keiichi
    Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology
  • Yamakawa Takeshi
    Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology

Search this article

Abstract

Genetic algorithms (GAs) are search algorithms based on the mechanics of natural selection and natural evolution. Due to cost reasons, hardware accelerators for GAs are required to reduce its execution time. In the hardware implementation of GAs, a circuit design of roulette wheel selection influences the performance of the GAs hardware. In this paper, we propose a new selection circuit based on Rough Comparison Method (RCM), and evaluate effects of the proposed circuit in terms of execution time and circuit size. The RCM is a parallel processing circuit. Therefore, the execution time is constant regardless of the increase of number in individuals, and the circuit size of the RCM is reduced than the ordinary parallel roulette selection circuits.

Journal

Citations (1)*help

See more

References(30)*help

See more

Details 詳細情報について

Report a problem

Back to top