A method for near-infrared spectral calibration of complex plant samples with wavelet transform and elimination of uninformative variables

被引：80

作者：

Shao, XG ^{[1
]}

Wang, F ^{[1
]}

Chen, D ^{[1
]}

Su, QD ^{[1
]}

机构：

[1] Univ Sci & Technol China, Dept Chem, Hefei 230026, Anhui, Peoples R China

来源：

ANALYTICAL AND BIOANALYTICAL CHEMISTRY | 2004年 / 378卷 / 05期

关键词：

wavelet transform; uninformative variable elimination (UVE); partial least squares (PLS); near-infrared spectrum;

D O I：

10.1007/s00216-003-2397-9

中图分类号：

Q5 [生物化学];

学科分类号：

071010 ; 081704 ;

摘要：

An algorithm is proposed for extracting relevant information from near-infrared (NIR) spectra for multivariate calibration of routine components in complex plant samples. The algorithm is a combination of wavelet transform (WT) data compression and a procedure for uninformative variable elimination (UVE). After compression of the NIR spectra by WT, the UVE approach is used to eliminate the irrelevant wavelet coefficients. Finally, a calibration model is built from the retained wavelet coefficients to enable prediction. Because irrelevant information can be removed from the spectra used for multivariate calibration, the model based on the extracted relevant features is better than those obtained with full-spectrum data. Both prediction precision and calculation speed are improved.

引用

页码：1382 / 1387

页数：6

共 17 条

[1] Variable selection in wavelet regression models
Alsberg, BK
Woodward, AM
Winson, MK
Rowland, JJ
Kell, DB
[J]. ANALYTICA CHIMICA ACTA, 1998, 368 (1-2) : 29 - 44
[2] The successive projections algorithm for variable selection in spectroscopic multicomponent analysis
Araújo, MCU
Saldanha, TCB
Galvao, RKH
Yoneyama, T
Chame, HC
Visani, V
[J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2001, 57 (02) : 65 - 73
[3] NTR calibration in non-linear systems:: different PLS approaches and artificial neural networks
Blanco, M
Coello, J
Iturriaga, H
Maspoch, S
Pagès, J
[J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2000, 50 (01) : 75 - 82
[4] NIR spectroscopy, mineral nitrogen analysis and soil incubations for the prediction of crop uptake of nitrogen during the growing season
Börjesson, T
Stenberg, B
Lindén, B
Jonsson, A
[J]. PLANT AND SOIL, 1999, 214 (1-2) : 75 - 83
[5] Use of near infrared reflectance spectroscopy (NIRS) for the prediction of the chemical composition and nutritional attributes of green crop cereals
Bruno-Soares, AM
Murray, I
Paterson, RM
Abreu, JMF
[J]. ANIMAL FEED SCIENCE AND TECHNOLOGY, 1998, 75 (01) : 15 - 25
[6] Elimination of uninformative variables for multivariate calibration
Centner, V
Massart, DL
deNoord, OE
deJong, S
Vandeginste, BM
Sterna, C
[J]. ANALYTICAL CHEMISTRY, 1996, 68 (21) : 3851 - 3858
[7] Selection of variables for interpreting multivariate gas sensor data
Eklöv, T
Mårtensson, P
Lundström, I
[J]. ANALYTICA CHIMICA ACTA, 1999, 381 (2-3) : 221 - 232
[8] Galvao RKH, 2001, ANAL CHIM ACTA, V443, P107
[9] Variable and subset selection in PLS regression
Höskuldsson, A
[J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2001, 55 (1-2) : 23 - 38
[10] Application of wavelet transform to extract the relevant component from spectral data for multivariate calibration
JouanRimbaud, D
Walczak, B
Poppi, RJ
deNoord, OE
Massart, DL
[J]. ANALYTICAL CHEMISTRY, 1997, 69 (21) : 4317 - 4323

← 1 2 →