Increase Performance Genetic Algorithm in Matching System by Setting GA Parameter

Abstract

Matching system is a system that finding an object base on what we are looking for. In this research, the object is a paragraph. Paragraph matching is a process of finding a paragraph which is inputted as a target paragraph. The previous worked on this filed is that focus on finding a sentence. It shows that it took 490 generations or iterations in order to find the sentence, which mean it is not so fast or takes more times. This paper intends to bring into expand research which means from sentence matching into paragraph matching. It means that there are two points to bring about that is paragraph matching and increase performance. On this research used genetic algorithm to get best speed of finding the sentence through several genetic algorithm components that is population, selection, crossover, and mutation. In implementation side, it sets the parameter value of genetic algorithm that is chromosome = 10, 20, 50, crossover probability=0.5 and mutation probability=0.05. The outcome of this research is to give a better approach of finding a paragraph accurately and also faster in term of speed. The final result is that the generation or iterations is 144.