期刊
OPTIK
卷 170, 期 -, 页码 17-29出版社
ELSEVIER GMBH, URBAN & FISCHER VERLAG
DOI: 10.1016/j.ijleo.2018.05.096
关键词
Color difference classification; Grey wolf optimization; Differential evolution; Support vector machine
类别
资金
- NSFC-Zhejiang Joint Fund for the Integration of Industrialization and Informatization [U1609205]
- Zhejiang Provincial Natural Science Foundation of China [LY18F030018, LZ15F020004]
- Natural Science Foundation of China [51376055, 61272311]
- 521 Plan of Zhejiang Sci-Tech University
In order to establish the color difference classification model of printing and dyeing products, a grey wolf algorithm optimization support vector machine based on differential evolution (DE) model is proposed in this paper. First of all, the performance of the support vector machine (SVM)model is mainly affected by the penalty parameter C and the RBF kernel width y, and the method uses the good global search capability of grey wolf optimization (GWO) algorithm iteratively optimization to compute the best parameter combination of support vector machines. At the same time, because the initial population of grey wolf algorithm has a greater influence on the solution speed and quality of the algorithm, the DE algorithm is used to generate a more suitable initial population for grey wolf algorithm, which makes the grey wolf population have better solution ability. Finally, through the optimization to the penalty factor and the kernel width parameter, the printing and dyeing products classification model of SVM with strong generalization ability is constructed. The experimental results show that the proposed method achieves high classification accuracy, and have good stability and generalization ability, when it is compared with the color difference classification method of printing and dyeing product based on SVM and GWO-SVM algorithm.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据