|
|||||
|
|
| 基于最小二乘支持向量机的声速空间变化模型构建 | |
| 引用本文： | 魏碧辉,刘翀,周青,黄贤源,陆秀平,吴太旗.基于最小二乘支持向量机的声速空间变化模型构建[J].海洋测绘,2013,33(4):12-15. |
| 作者姓名： | 魏碧辉 刘翀 周青 黄贤源 陆秀平 吴太旗 |
| 作者单位： | 1. 91561部队,广东广州,510320 2. 92292部队,山东胶南,266405 3. 海军海洋测绘研究所,天津,300061 |
| 基金项目： | 国家863计划项目，国家自然科学基金项目 |
| 摘 要： | 建立声速空间变化模型是解决声速剖面代表性误差的有效方法。在对不同声速剖面进行标准化处理的基础上,通过声速训练样本及核函数的选取,提出并实现了一种基于最小二乘支持向量机算法的声速空间变化模型构建方法。为了检验该方法的有效性,选取实测的声速剖面数据进行验证,结果表明该方法能有效地构建声速空间变化模型,从而消除或最大限度地削弱声速剖面代表性误差。 |
| 关 键 词： | 声速剖面代表性误差 最小二乘支持向量机(LS-SVM) 声速空间变化模型 |
Construction of the Spatial Model for Sound Velocity by the Least Square Support Vector Machine |
|
| WEI Bihui,LIU Chong,ZHOU Qing,HUANG Xianyuan,LU Xiuping,WU Taiqi.Construction of the Spatial Model for Sound Velocity by the Least Square Support Vector Machine[J].Hydrographic Surveying and Charting,2013,33(4):12-15. | |
| Authors: | WEI Bihui LIU Chong ZHOU Qing HUANG Xianyuan LU Xiuping WU Taiqi |
| Institution: | 1. 91561 Troops, Guangzhou 510320, China; 2. 92292 Troops, Jiaonan 266405, China; 3. Naval Institute of Hydrographic Surveying and Charting, Tianjin 300061, China) |
| Abstract: | The influence of the representative error of sound velocity profile could be weaken by constructing spatial model of sound velocity. On the basis of sound velocity profile standardization, a new method, which is used for constructing spatial model of sound velocity by the least square support vector machine, is presented. In order to illuminate the correctness and rationality so an example is given. The results show that the effect of the representative error of sound velocity profile could be weaken by this method. |
| Keywords: | representative error of SVP LS-SVM spatial model of sound velocity |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |
| 点击此处可从《海洋测绘》浏览原始摘要信息 | |
| 点击此处可从《海洋测绘》下载免费的PDF全文 | |