Linkage Identification by Nonlinearity Check for Real-Coded Genetic Algorithms
Linkage Identification by Nonlinearity Check for Real-Coded Genetic Algorithms
复制标题
DOI：
10.1007/978-3-540-24855-2_20
复制
发表时间：
2004-06
期刊：
影响因子：
--
通讯作者：
M. Tezuka;M. Munetomo;K. Akama
中科院分区：
文献类型：
--
作者：
M. Tezuka;M. Munetomo;K. Akama
链接识别是一种识别可分解或准可分解子问题的技术。准确的连锁识别提高了遗传算法的搜索能力。我们引入了一种新的实数编码 GA 连锁识别方法，称为 LINC-R（实数编码 GA 的非线性检查连锁识别）。它通过实值域中每个轨迹的随机扰动来测试非线性。对于域中非线性区域所占比例较小的问题，需要更多的扰动才能确保LINC-R成功检测非线性。如果已知该比例，就可以计算出保证LINC-R一定成功率的群体规模。基准问题的计算实验表明，使用 LINC-R 的 GA 优于传统的实编码 GA 和通过相关模型进行连锁识别的 GA。
Linkage identification is a technique to recognize decomposable or quasi-decomposable sub-problems. Accurate linkage identification improves GA’s search capability. We introduce a new linkage identification method for Real-Coded GAs called LINC-R (Linkage Identification by Nonlinearity Check for Real-Coded GAs). It tests nonlinearity by random perturbations on each locus in a real value domain. For the problem on which the proportion of nonlinear region in the domain is smaller, more perturbations are required to ensure LINC-R to detect nonlinearity successfully. If the proportion is known, the population size which ensures a certain success rate of LINC-R can be calculated. Computational experiments on benchmark problems showed that the GA with LINC-R outperforms conventional Real-Coded GAs and those with linkage identification by a correlation model.