Genetic algorithms are one of the most efficient meta-heuristics. The base of genetic algorithms is a set of candidate optimal solutions called population. The initial population usually is randomly generated. Optimization goes in epochs of new generations. New generations are produced after crossover and mutation. Mating between individuals is done after the selection of the better-fitted individuals. The fitness value of each individual is calculated by supplying the candidate solution to the optimized target function. The efficiency of the genetic algorithms is tightly related to the fast calculation of the fitness value. When the target function is a very timeconsuming one the efficiency of the genetic algorithms falls dramatically. This study proposes target function replacement by approximation function based on curve fitting.

No abstract

No abstract