| 基于藤结构pair—copula分解法的分布估计算法 |
| |
| 引用本文： | 王位,王筱萍. 基于藤结构pair—copula分解法的分布估计算法[J]. 嘉兴学院学报, 2013, 0(6): 29-34 |
| |
| 作者姓名： | 王位 王筱萍 |
| |
| 作者单位： | [1]太原科技大学电子信息工程学院,山西太原030024 [2]嘉兴学院商学院,浙江嘉兴314001 |
| |
| 基金项目： | 山西省自然科学基金项目（2009011011-3）;山西省回国留学人员科研资助项目（2011-078）;山西省软科学项目（2011041001-02） |
| |
| 摘 要： | 借鉴copula研究中藤结构在高维相关关系上的构建能力，提出了基于藤结构pair—copula分解法的分布估计算法，给出了新算法的模型框架，研究了相应的概率模型的采样算法，并对C藤、D藤两种特殊的藤进行了仿真实验，结果表明，该算法不仅可行，寻优能力也大大提高．
|
| 关 键 词： | 藤 pair—copula分解法 分布估计算法 |
Estimation of Distribution Algorithm Based on Pair-Copula Decomposition Method |
| |
| Affiliation: | WANG Wei , WANG Xiao--ping (1. School of Electronics and Information Engineering,Taiyuan University of Science and Technology, Taiyuan,Shanxi 030024; 2. School of Business, Jiaxing University, Jiaxing, Zhejiang 314001) |
| |
| Abstract: | In this paper, by taking advantage of the ability of vine in high-dimensional correlation construction, a novelty algorithm is proposed, called Estimation Distribution Algorithms based on pair-copula decomposition method （vine-EDAs）. The architecture of vine-EDAs is provided, and sampling method of the probability model is discussed, the simulation results based on two different vine, namely C-vine and D-vine, show that the proposed algorithm is not only feasible, but also perform very well. |
| |
| Keywords: | vines pair-copula decomposition method estimation of distribution algorithm |
| 本文献已被 维普 等数据库收录！ |
|
