Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Engineering of Surveying and Mapping》 2008-05
Add to Favorite Get Latest Update

Least squares support vector machine method of area quasi-geoid determination

FAN Qian1,2,ZHANG Ning3(1.Research Center for Hazard Monitoring and Prevention,Wuhan University,Wuhan430079,China;2.School of Geodesy and Geomatics,Wuhan University,Wuhan430079,China;3.Departm ent of Physics and Electronic Information Engineering,Minjing University,Fuzhou 350108,China)  
Support vector machine(SVM) is a novel machine learning method,which is powerful for the problem characterized by small sample,nonlinearity,high dimension and local minima,and has high generalization.In this paper,its continuation algorithm-least squares support vector machine(LSSVM) is studied,then LSSVM algorithm is applied to determining large area complex quasi-geoid.Through taking an example and comparing with neural network model and conicoid polynomial fitting model,the availability of LSSVM method of area quasi-geoid determination is validated.
【Fund】: 国家自然科学基金资助项目(40474003)
【CateGory Index】: P223.0
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved