Improvement of Evolutionary Computation of Genetic Algorithm using SVM

  • Cho, Byung-Sun (Department of Control and Instrumentation Engineering, Korea University) ;
  • Han, So-Hee (Department of Control and Instrumentation Engineering, Korea University) ;
  • Son, Sung-Han (Department of Control and Instrumentation Engineering, Korea University) ;
  • Kim, Jin-Su (Department of Control and Instrumentation Engineering, Korea University) ;
  • Park, Kang-Bak (Department of Control and Instrumentation Engineering, Korea University)
  • Published : 2003.10.22

Abstract

Genetic algorithm is well known as a stochastic searching method. In this paper, a modified genetic algorithm using 'Suppor Vector Machines (SVM)' is proposed. SVM is used to reduce the number of calling the objective function which in turn accelerate the searching speed compared to the conventional GA.