Symbolic and numerical regression: experiments and applications

被引：51

作者：

Davidson, JW ^{[1
]}

Savic, DA ^{[1
]}

Walters, GA ^{[1
]}

机构：

[1] Univ Exeter, Sch Engn & Comp Sci, Dept Engn, Exeter EX4 4QF, Devon, England

来源：

INFORMATION SCIENCES | 2003年 / 150卷 / 1-2期

关键词：

genetic programming; least squares; rule-based programming; stepwise regression; symbolic regression;

D O I：

10.1016/S0020-0255(02)00371-7

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper describes a new method for creating polynomial regression models. The new method is compared with stepwise regression and symbolic regression using three example problems. The first example is a polynomial equation. The two examples that follow are real-world problems, approximating the Colebrook-White equation and rainfall-runoff modelling. The three example problems illustrate the advantages of the new method. (C) 2002 Elsevier Science Inc. All rights reserved.

引用

页码：95 / 117

页数：23

共 20 条

[1] [Anonymous], 1998, Applied regression analysis, DOI 10.1002/9781118625590
[2] Babovic V, 2000, J HYDROINFORM, V2, P35, DOI DOI 10.2166/HYDRO.2000.0004
[3] COUSIN N, 1997, 9703 U EX CTR WAT SY
[4] Davidson JW, 2000, ADV SOFT COMP, P111
[5] EELES CWO, 1994, THESIS OPEN U MILTON
[6] EELES CWO, 1989, HYRROM OPERATION MAN
[7] FRANCONE FD, 1998, DISCIPULUS PRO OWNER
[8] The interpretation of Mallows's C-p-statistic
Gilmour, SG
[J]. JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES D-THE STATISTICIAN, 1996, 45 (01) : 49 - 56
[9] SELECTION OF VARIABLES FOR FITTING EQUATIONS TO DATA
GORMAN, JW
TOMAN, RJ
[J]. TECHNOMETRICS, 1966, 8 (01) : 27 - &
[10] JACQ F, 1997, 9702 U EX CTR WAT SY

← 1 2 →