| 基于PCA特征提取的SVR地下水位动态预测方法 |
| |
| 引用本文： | 刘成忠,黄高宝,韩建民. 基于PCA特征提取的SVR地下水位动态预测方法[J]. 工程勘察, 2011, 0(3): 36-39 |
| |
| 作者姓名： | 刘成忠 黄高宝 韩建民 |
| |
| 作者单位： | 甘肃农业大学信息科学技术学院;甘肃省干旱生境作物学重点实验室;甘肃农业大学人文学院; |
| |
| 基金项目： | 甘肃省自然科学基金(096RJZA004); 甘肃省教育厅科研基金(0902-04); 甘肃省科技支撑计划(1011NKCA058) |
| |
| 摘 要： | 本文提出了一种基于PCA特征提取的SVR地下水位动态预测方法.PCA用来对地下水位样本值进行相关性分析和特征提取,将得到的最佳特征向量子集输入SVR模型,并通过网格搜索的方法进行SVR参数寻优,进行地下水位预测.通过地下水位的实例分析和UCI标准数据集对模型的有效性进行验证,结果表明该方法不仅降低了预测所需的计算工作量...
|
| 关 键 词： | 主成分分析 特征提取 支持向量机 地下水位 |
SVR method for the dynamic prediction of groundwater level based on PCA feature extraction |
| |
| Liu Chengzhong,Huang Gaobao,Han Jianmin. SVR method for the dynamic prediction of groundwater level based on PCA feature extraction[J]. Geotechnical Investigation & Surveying, 2011, 0(3): 36-39 |
| |
| Authors: | Liu Chengzhong Huang Gaobao Han Jianmin |
| |
| Affiliation: | Liu Chengzhong1,2,Huang Gaobao2,Han Jianmin3(1.College of Information Science & Technology,Gansu Agricultural University,Lanzhou 730070,China,2.Gansu Provincial Key Laboratory of Aridland Crop Science,3.College of Humanities,China) |
| |
| Abstract: | The method for the dynamic prediction of groundwater level which combines the support vector regression(SVR) and the principal component analysis(PCA) feature extraction is presented.The PCA is used to analyze the correlation of the groundwater samples and to extract the features from them,and the optimal feature vector set is input to the SVR for the groundwater level prediction.Kernel parameters of SVR are determined by using the grid search method.The efficiency of the method is illustrated through analy... |
| |
| Keywords: | principal component analysis(PCA) feature extraction support vector machine groundwater level |
| 本文献已被 CNKI 维普 等数据库收录！ |
