Bacteria Cooperative Optimization Applying Individual's Speed for Performance Improvements

성능향상을 위하여 개체속력을 적용한 박테리아 협동 최적화

  • Jung, Sung-Hoon (Department of Information & Communications Engineering, Hansung University)
  • 정성훈 (한성대학교 정보통신공학과)
  • Received : 2010.04.05
  • Accepted : 2010.04.30
  • Published : 2010.05.25

Abstract

This paper proposes a bacteria cooperative optimization (BCO) method applying individuals's speed for the performance improvements. All individuals in existing BCO methods move the same length at the same time because their speeds are constant. These methods had the problem that the individuals couldn't find the global optimum effectively because good individuals and bad individuals had same speeds. In order to overcome this problem, we applied the speed concept to the BCO algorithm that individuals moved different lengths according to their speeds assigned by the ranks of individuals according to the fitness of individuals. That is to say, we provide high speeds to bad individuals with low fitness in order to fast move to the areas with high fitness and provide low speeds to good individuals with high fitness because they may be near global optimum. It was found from experimental results of four function optimization problems that the proposed method outperformed the existing methods. Our method showed better performances even than the rank replacement method. This means that applying speed concepts to the individuals for BCO is very effective and efficient.

본 논문에서는 성능향상을 위하여 개체속력 개념을 적용한 박테리아 협동 최적화 방법을 제안한다. 기존의 박테리아 협동 최적화 방법에서는 개체별로 속력이 일정해 모든 개체가 같은 시간에 똑 같은 거리를 움직인다. 이러한 방법은 개체의 적합도가 좋은 개체나 나쁜 개체가 같은 속력으로 움직임으로서 효과적으로 최적 해를 찾아가지 못하는 문제점이 있었다. 이러한 문제점을 개선하고자 개체의 적합도를 이용하여 개체별 등급을 매기고 등급에 따라서 한 번에 이동할 수 있는 거리를 다르게 하는 속력 개념을 적용하였다. 즉 적합도가 낮은 개체는 적합도가 높은 영역으로 빨리 이동하기위하여 속력을 높이고 적합도가 높은 개체는 주변에 최적 해가 있을 가능성이 있으므로 속력을 낮게 유지하였다. 4개의 함수 최적화 문제에 적용해본 결과 속력개념을 적용하지 않은 방법에 대하여 상당한 성능향상이 있음을 보았다. 특히 성능향상을 위하여 기존에 도입했던 등급별 교체방법보다도 더 좋은 성능을 보였다. 이는 박테리아 협동 최적화의 성능을 향상시키기 위한 방법으로 속력개념을 적용하는 것이 매우 유용함을 보여준다.

Keywords

References

  1. D. Goldberg, "Genetic Algorithms in Search, Optimization and Machine Learning," Addison-Wesley, 1989.
  2. M. Srinivas and L. M. Patnaik, "Genetic Algorithms: A Survey," IEEE Computer Magazine, pp. 17-26, June 1994.
  3. R. C. Eberhart, Y. Shi, and J. Kennedy, "Swarm Intelligence," Morgan Kaufmann, 2001.
  4. E. Bonabeau, M. Dorigo, and G. Theraulaz, "Swarm Intelligence: From Natural to Artificial Systems," Oxford University Press, 1999.
  5. M. Dorigo and T. Stutzle, "Ant Colony Optimization," The MIT Press, 2004.
  6. M. Clerc, "Particle Swarm Optimization," ISTE Publishing Company, 2006.
  7. L. N. de Castro and J. Timmis, "Artificial Immune Systems: A New Computational Intelligence Approach," Oxford University Press, 2002.
  8. H. C. Berg and D. A. Brown, "Chemotaxis in escheichia coli analysed by three-dimensional tracking," Nature, vol. 239, pp. 500-504, 1972. https://doi.org/10.1038/239500a0
  9. M. Kim, S. Baek, S. H. Jung, and K.-H. Cho, "Dynamical characteristics of bacteria clustering by self-generated attractants," Computational Biology and Chemistry, vol. 31, pp. 328-334, Oct. 2007. https://doi.org/10.1016/j.compbiolchem.2007.07.002
  10. T.-H. Kim, S. H. Jung, and K.-H. Cho, "Investigations into the design principles in the chemotactic behavior of Escherichia coli," BioSystems, vol. 91, pp. 171-182, Jan. 2008. https://doi.org/10.1016/j.biosystems.2007.08.009
  11. S. H. Jung and T.-G. Kim, "A Novel Optimization Algorithm Inspired by Bacteria Behavior Patterns," Journal of Korean Institute of Intelligent Systems, vol. 18, pp. 392-400, June 2008.
  12. S. H. Jung, "Simple Bacteria Cooperative Optimization with Rank Replacement," Journal of Korean Institute of Intelligent Systems, vol. 19, pp. 432-436, June 2009. https://doi.org/10.5391/JKIIS.2009.19.3.432