Locus Oriented Adaptive Genetic Algorithm: Application to the Zero/One Knapsack Problem

The biological observation of the difference in the mutation rates of allele on different loci is implemented in genetic algorithm so that the mutation rate is both time and locus dependent. The performance of this new locus oriented adaptive genetic algorithm (LOAGA) is evaluated on the test problem of zero/one knapsack for various sizes. It is found that LOAGA can solve the single constraint zero/one knapsack with high speed, high success rate, and small memory requirement. A heuristic argument is given to show how the statistical information inside the population can be used to tune the mutation rate at individual locus, resulting in higher overall performance