文章基本信息

标题：USING A LEAST SQUARES SUPPORT VECTOR MACHINE TO ESTIMATE A LOCAL GEOMETRIC GEOID MODEL
本地全文：下载
作者：SZU-PYNG KAO KAO ; CHAO-NAN CHEN ; HUI-CHI HUANG 等
期刊名称：Boletim de Ciências Geodésicas
印刷版ISSN：1982-2170
出版年度：2014
卷号：20
期号：2
语种：English
出版社：Universidade Federal do Paraná-UFPR
摘要：In this study, test-region global positioning system (GPS) control points exhibiting known first-order orthometric heights were employed to obtain the points of plane coordinates and ellipsoidal heights by using the real-time GPS kinematic measurement method. Plane-fitting, second-order curve-surface fitting, back- propagation (BP) neural networks, and least-squares support vector machine (LS- SVM) calculation methods were employed. The study includes a discussion on data integrity and localization, changing reference-point quantities and distributions to obtain an optimal solution. Furthermore, the LS-SVM was combined with local geoidal-undulation models that were established by researching and analyzing3 kernel functions. The results indicated that the overall precision of the local geometric geoidal-undulation values calculated using the radial basis function (RBF) and third-order polynomial kernel function was optimal and the root mean square error (RMSE) was approximately ± 1.5 cm. These findings demonstrated that the LS-SVM provides a rapid and practical method for determining orthometric heights and should serve as a valuable academic reference regarding local geoid models.
关键词：Least Squares Support Vector Machine (LS-SVM);Kernel Function; Local Geoid Model