Modified Genetic Algorithm with Threshold Selection
Lutfi Mohammed Omer Khanbary, Deo Prakash Vidyarthi · 2009
Genetic Algorithm (GA) is widely used for the number of optimization problems. For a large set of problems, GA provides the sub-optimal solution and thus the thrust to improve the GA for better result is on. In all the variants of the GA a selection operator guides the result towards the convergence. Selection, being a major component of the GA, attracts a good number of researchers with a new selection method. The current work introduces a variant of selection method in the GA that results in better improvement of the result. Genetic algorithm is modified by the new selection method that incorporates a problem specific knowledge in the new population generation. The GA with the new selection method is called as the Modified Genetic Algorithm (MGA). In the proposed selection method, not all the chromosomes of a generation are used for mating rather it is selected based on its goodness. Two threshold values, based on some prior knowledge, are used to classify the chromosomes. Efficacy of the proposed threshold method has been evaluated by conducting experiment and comparing the threshold method with some existing selection methods viz. sigma scaling, rank selection and tournament selection.