Research work · 2007
Adaptive genetic algorithm based on superiority inheritance
Wanyu Liu
Ha'erbin gongye daxue xuebao
Abstract
To solve the premature problem of genetic algorithm,after studying adaptive genetic algorithm,a new viewpoint is presented.It is greatly efficient to create new superiority individual and trap out local optimum that makes the crossover probability higher to individual with high fitness and make the mutation probability higher to individual with low fitness at the same time.It is unsuitable to make average fitness approach to maximum fitness too quickly.So a new adaptive genetic algorithm is presented which varies crossover and mutation probability with individual's fitness in course of evolution using superiority inheritance principle.To a certain extent,this algorithm is very good for solving the premature question.The experiments demonstrate that this algorithm can improve the performance of searching global optimum efficiently, and has high robust.