Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Science of Surveying and Mapping》 2019-01
Add to Favorite Get Latest Update

An algorithm of the outer point fastest drop for the parameter of nonlinear trend model

LIU Cuizhi;WU Tong;YANG Hengzan;School of Resources and Civil Engineering,Northeastern University;College of Electrical and Electronic Engineering,Nanyang Technological University;  
Aiming to the problem of solving nonlinear trend models,this paper proposed a new generalpurpose algorithm:an algorithm of the outer point fastest drop,this algorithm is based on the theory of constrained optimization method,using the outer point method and the fastest descent method,transformed the problem of parameter solution into constrained nonlinear programming problem.Taking the settlement prediction as an example,through the trial calculation of 3 typical nonlinear trend models,shown that the prediction accuracy of this algorithm is generally high.At the same time,the prediction mean absolute error is used as the precision index,the value can be calculated beforehand under this algorithm,and then the prediction accuracy can be estimated roughly.After that,the formula of obtaining higher precision parameters is given,and the method of selecting points is further optimized through analysis.
【CateGory Index】: TU196.2
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