Searching Parameter Values in Support Vector Machines Using DNA Genetic Algorithms
Searching Parameter Values in Support Vector Machines Using DNA Genetic Algorithms
复制标题
DOI：
10.1007/978-3-319-31854-7_53
复制
发表时间：
2016-01
期刊：
影响因子：
--
通讯作者：
Wenke Zang;Minghe Sun
中科院分区：
文献类型：
--
作者：
Wenke Zang;Minghe Sun
提出了一种新的DNA编码遗传算法--支持向量机-DNAGA，用于搜索支持向量机参数的最优值。该算法可以使支持向量机的训练过程快速收敛，提高支持向量机的性能。使用DNA编码将支持向量机中的参数编码到染色体中。支持向量机-DNAGA采用了选择、转基因和移码突变等DNA遗传操作。使用四个数据集进行计算实验，验证了支持向量机-DNAGA算法的有效性。与其他常用的分类器相比，支持向量机-DNAGA取得了很好的效果。
A novel DNA encoding genetic algorithm, called SVM-DNAGA, is proposed to search for optimal values for the parameters in support vector machines. With this algorithm, the training process of support vector machines can converge quickly and the performance of the support vector machines can improve. The parameters in the support vector machines are encoded into chromosomes using DNA encoding. DNA genetic operations, including selection, transgenosis and frameshift mutation, are used in SVM-DNAGA. Four datasets are used in the computational experiments to verify the effectiveness of SVM-DNAGA. Compared with other commonly used classifiers, SVM-DNAGA obtains very good results.