摘要
为改进传统遗传算法局部搜索能力较差、收敛速度慢等缺点,提出一种基于加权二叉树的遗传算法。通过构建遗传基因二叉树,对种群染色体进行编码,根据子代基因的适应值挑选优秀基因替换弱势基因,采用蚁群信息素对不同的遗传基因进行加权操作,依权重择优进行交叉操作,利用自适应排序选择最优解,并通过对比实验对该算法和基本遗传算法进行了全方位的比较。试验结果表明该算法大大提高了遗传算法的局部搜索能力,加快了算法的收敛速度。
In order to improve the deficiencies of the locally searching capability and slow convergence speed of traditional genetic algorithm,a novel genetic algorithm based on weighted binary tree is presented in this paper.Constructing the genetic binary tree by adopting the pheromone of ant colony to weight different genes and a new crossover strategy which chooses the outstanding individuals according to weight is introduced,finally an adaptive adjusting mechanism is adopted by the ranking selection strategy to choose the best solution.By comparing the algorithm and the basic genetic algorithm,the experimental results showed that the algorithm greatly improved the local search capability and convergence speed of the genetic algorithm.
出处
《计算机技术与发展》
2010年第11期95-99,共5页
Computer Technology and Development
基金
陕西省教育重点项目(09Z09)
关键词
加权二叉树
自适应遗传算法
蚁群算法
排序选择
weighted binary tree
adaptive genetic algorithm
ant colony algorithm
ranking selection
