期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2013
卷号：3
期号：4
出版社：S.S. Mishra
摘要：Genetic Algorithms are biologically inspired optimization algorithms. Performance of genetic algorithms mainly depends on type of genetic operators ¨C Selection, Crossover, Mutation and Replacement used in it. Crossover operators are used to bring diversity in the population. This paper studies different crossover operators and then proposes a hybrid crossover operator that incorporates knowledge based on existing population and uses the concept of Hill climbing search. Performance of the proposed hill climbing based hybrid crossover is compared with existing PMX and OX operator in genetic algorithm. Implementation is carried out in MATLAB on benchmark TSP Oliver30 problem. The results are optimistic and clearly demonstrate that the proposed hybrid crossover is better than the existing crossovers in terms of convergence towards optimal solution.
关键词：Crossover; genetic algorithm; hill climbing; memetic algorithm.
