Performance of Arithmetic Crossover and Heuristic Crossover in Genetic Algorithm Based on Alpha Parameter

Genetic algorithm (GA) is a heuristic search algorithm based on the idea of natural selection that occurs in the process of evolution and genetic operations. One of the critical stages in the genetic algorithm is a crossover process. In the crossover, phase occurs the gene mix between the parent that it will determine the diversity in the population. This paper will describe the effects of the alpha parameter in the crossover process which includes arithmetic crossover and heuristic crossover. The Case studies that used in this study is the Traveling Salesman Problem (TSP). The influence of parameters on the performance of genetic algorithm alpha is associated with gene diversity resulting from the crossover. The results showed that in the arithmetic crossover, the best alpha value is 0.5, becoming the best alpha value because of a balanced genes combination from both parents. On Heuristic Crossover obtained different results where the alpha value which gives the best performance is 0.9. This method slightly different from the Arithmetic Crossover caused on Heuristic Crossover; the alpha parameter used as multiplier factor after the subtraction process of genes from both parents