摘要:
|
提出了利用支持向量回归机算法(SVR)建立海水叶绿素-a 浓度的软测量方法, 采用灰色关联分析法获取叶绿素-a 软测量模型的主要辅助测量变量。将基于支持向量回归机的叶绿素-a 软测量结果与BP神经网络和T-S 模糊神经网络方法进行了对比, 结果表明, 这种基于支持向量回归机的软测量方法能够有效测量海水叶绿素-a的浓度。 |
A soft sensing method of measuring the concentration of chlorophyll-a in seawater based on Support Vector Regression (SVR) is proposed. The method of Grey Correlation Analysis is used for obtaining the key secondary variables of soft sensing model of chlorophyll-a. The result of soft sensing based on SVR has been compared with the result from BP neural network and T-S fuzzy neural network. The testing result indicates that this soft sensing method based on SVR can effectively estimate the concentration of chlorophyll-a in seawater. |
参考文献:
|
[1] 王冬云, 黄焱歆. 海水富营养化评价的人工神经网络方法[J]. 河 北建筑科技学院学报, 2001, 18(4): 27-29. [2] 张丽旭, 张小伟. 用于海洋环境科学的一种新方法—影响因子分 析法[J]. 海洋科学进展, 2004, 22(1):33-36. [3] Lee J H W, Huang Y, Dickman M. et al. Neural network modelling of coastal algal blooms [J]. Ecological Modelling, 2003, 159(2): 179-201. [4] Melesse A M, Krishnaswamy J, Zhang K Q. Modeling Coastal Eutrophication at Florida Bay using Neural Networks[J]. Journal of Coastal Research, 2008, 24(2): 190-196. [5] 郑丙辉, 张远, 富国, 等. 三峡水库营养状态评价标准研究[J]. 环 境科学学报, 2006, 26(6): 1022-1030. [6] 李雪, 刘长发, 朱学慧, 等. 基于BP 人工神经网络的海水水质综 合评价[J]. 海洋通报, 2010, 29(2): 225-230. [7] Vapnik V, Chapelle O. Bounds on error expectation for support vector machines[J]. Neural Computation, 2000, 12(9): 2013-2036. [8] Abe S, Inoue T. Fuzzy support vector machines for multiclass problems[C]. ESANN’2002 Proceedings- European Symposiumon Artificial Neural Networks, Bruges, Belgium, 2002: 113-118. [9] Zaiwen L, WANG X, Lifeng C, et al. Research on Water Bloom Prediction Based on Least Squares Support Vector Machine[A]. 2009 World Congress on Computer Science and Information Engineering[C]. LosAngeles, 2009: 764-768. [10] 李琳, 张晓龙. 基于RBF 核的SVM学习算法的优化计算[J]. 计 算机工程与应用, 2006, 29: 190-192, 204. [11] 王红瑞, 闫五玖. 环境质量的模糊综合评判—灰色关联分析复 合模型及实例分析[J]. 北京师范大学学报, 1997, 20(4): 39-43. |
服务与反馈:
|
【文章下载】【发表评论】【查看评论】【加入收藏】
|
|
|