|本期目录/Table of Contents|

[1]向先全,陶建华.基于GA-SVM的渤海湾富营养化模型[J].天津大学学报(自然科学版),2011,(03):215-220.
 XIANG Xian-quan,TAO Jian-hua.Eutrophication Model of Bohai Bay Based on GA-SVM[J].Journal of Tianjin University,2011,(03):215-220.
点击复制

基于GA-SVM的渤海湾富营养化模型()
分享到:

《天津大学学报(自然科学版)》[ISSN:0493-2137/CN:12-1127/N]

卷:
期数:
2011年03
页码:
215-220
栏目:
出版日期:
2011-03-15

文章信息/Info

Title:
Eutrophication Model of Bohai Bay Based on GA-SVM
作者:
向先全1陶建华2
(1.天津大学环境科学与工程学院,天津 300072;2.天津大学机械工程学院,天津 300072)
Author(s):
XIANG Xian-quan TAO Jian-hua
(1. School of Environmental Science and Engineering,Tianjin University,Tianjin 300072,China; 2. School of Mechanical Engineering,Tianjin University,Tianjin 300072,China)
关键词:
富营养化模型支持向量机遗传算法参数寻优特征选择渤海湾
Keywords:
eutrophication modelsupport vector machinegenetic algorithmparameters optimizationfeature selectionBohai Bay
分类号:
X171;TP181
文献标志码:
A
摘要:
为了更好地模拟和认知渤海湾富营养化的复杂行为,通过研究遗传算法(GA)和支持向量机(SVM)的结合形式,即参数寻优和特征选择,以渤海湾水质实测资料为依据,叶绿素a的质量浓度为输出,建立了GA-SVM的富营养化模型.无特征选择时,用遗传算法对支持向量机的参数(惩罚参数和核参数)进行自适应地优选,预测模型的均方误差可达到1.831 μg/L,具有较好的认知、泛化能力.再利用遗传算法二进制编码及启发式寻优的优点,对所建模型的输入空间进行特征选择,提取出代表性的特征变量:DO%、pH值、水温、COD、盐度以及氨氮.特征提取后预测模型的均方误差可达到1.363 μg/L,模型性能有了很大提高.分析表明,COD、盐度及氨氮可作为人为控制的首要指标.
Abstract:
For better simulating and cognizing the complex eutrophication behaviors of Bohai Bay,the combining forms of genetic algorithm and support vector machine (parameter optimization and feature selection) have been re-searched to establish GA-SVM eutrophication model for Bohai Bay based on the field measured data,and chloro-phyll_a content has been selected as the model output. Firstly, with GA self-adaptive optimizing for penalty parameter and kernel parameter, the root mean square error (RMSE) of SVM test model was 1.831 ?g/L,indicating preferable generalization performance. Then,with GA-based feature selection for the established SVM model,RMSE of SVM test model was 1.363 ?g/L,showing great improvement for model performance. The representative features were ex-tracted such as DO%,pH,water temperature,COD,salinity,and ammonia-nitrogen,the latter three of which could be considered as prior indexes for artificial control of eutrophication based on further analysis.

相似文献/References:

[1]万柏坤,刘延刚,明 东,等.基于脑电特征的多模式想象动作识别[J].天津大学学报(自然科学版),2010,(10):895.
 WAN Bai-kun,LIU Yan-gang,MING Dong,et al.Multi-Pattern Motor Imagery Recognition Based on EEG Features[J].Journal of Tianjin University,2010,(03):895.
[2]曲志刚,封皓,靳世久,等.基于支持向量机的油气管道安全监测信号识别方法[J].天津大学学报(自然科学版),2009,(05):465.
 QU Zhi-gang,FENG Hao,JIN Shi-jiu,et al.An SVM-Based Recognition Method for Safety Monitoring Signals of Oil and Gas Pipeline[J].Journal of Tianjin University,2009,(03):465.
[3]王国锋,李启铭,秦旭达,等.支持向量机在刀具磨损多状态监测中的应用[J].天津大学学报(自然科学版),2011,(01):35.
 WANG Guo-feng,LI Qi-ming,QIN Xu-da,et al.Application of Support-Vector-Machine in Tool Wear of Multi-Stage Monitoring[J].Journal of Tianjin University,2011,(03):35.
[4]薛召军,李佳,明东,等.基于支持向量机的步态识别新方法[J].天津大学学报(自然科学版),2007,(01):78.
[5]路志英,李艳英,陆洁,等.粒子群算法优化RBF-SVM沙尘暴预报模型参数[J].天津大学学报(自然科学版),2008,(04):413.
[6]张宏伟,岳琳,王亮.基于径向基函数的城市日用水量预测方法[J].天津大学学报(自然科学版),2006,(04):486.
[7]崔庆安,何桢,车建国.一种基于支持向量机的非参数双响应曲面法[J].天津大学学报(自然科学版),2006,(08):1008.
[8]路志英,张启孟,赵智超.基于SVM的沙尘暴预测模型[J].天津大学学报(自然科学版),2006,(09):1110.
[9]曹玉珍,李广,范增飞.基于小波变换特征提取的支持向量机心搏分类研究[J].天津大学学报(自然科学版),2007,(07):811.
[10]冯为嘉,张宝峰,曹作良. 基于鱼眼镜头的全方位视觉参数标定与畸变矫正[J].天津大学学报(自然科学版),2011,(05):417.
 FENG Wei-jia,ZHANG Bao-feng,CAO Zuo-liang. Omni-Directional Vision Parameter Calibration and Rectification Based on Fish-Eye Lens[J].Journal of Tianjin University,2011,(03):417.

备注/Memo

备注/Memo:
通讯作者:陶建华,jhtao@tju.edu.cn.
更新日期/Last Update: 2011-03-15