Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Guilin University of Technology》 2009-03
Add to Favorite Get Latest Update

Effect of Error Distribution on PCA for Detecting Gross Errors in DEM

HUANG Shi-bin1,ZHOU Guo-en1,LIANG Xin1,YANG Xiao-yun1,2(1.Department of Civil Engineering,Guangxi University of Technology,Liuzhou 545006,China;2.School of Civil Engineering,Southwest Jiaotong University,Chengdu 610031,China)  
Two error models are built in the test:spike-like error model;pyramid-like error model,which are simulated in MATLAB.Principal component analysis is used to detect the two gross errors.The result shows that the space correlation of error reduces the efficiency of the PCA.Some data polluted by error can not be found,which results in the distortion of original data.
【Fund】: 国家自然科学基金资助项目(40271092);; 广西教育厅科研项目(200808LX348);; 广西工学院院管基金项目(500634)
【CateGory Index】: P207
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
【Citations】
Chinese Journal Full-text Database 1 Hits
1 YANG Xiao-yun1,CEN Min-yi2,3,LIANG Xin1(1.Department of Civil Construction Engineering,Guangxi University of Technology,Liuzhou 545006,China;2.School of Civil Engineering,Southwest Jiaotong University,Chengdu 610031,China;3.Department of Land Surveying and Geo-Informatics,Hongkong Polytechnic University,Hongkong);Application of Detecting Gross Errors in Railway DEM[J];Journal of Guilin University of Technology;2007-04
【Secondary Citations】
Chinese Journal Full-text Database 1 Hits
1 YANG Xiao-yun~1,GU Li-ya~1,CEN Min-yi~(1,2),LI Zhi-lin~2(1. School of Civil Engineering, Southwest Jiaotong University, Chengdu 610031, China; 2. Dept. of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Kowloon, Hong Kong,China);A Method Based Fitting of Moving Quadric Surface with Variable Windows for Detecting Gross Errors in Irregular DEM[J];Acta Geodaetica Et Cartographic Sinica;2005-02
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved