scholarly journals The Application of Discrete Wavelet Transform with Improved Partial Least-Squares Method for the Estimation of Soil Properties with Visible and Near-Infrared Spectral Data

2018 ◽  
Vol 10 (6) ◽  
pp. 867 ◽  
Author(s):  
Guoqiang Wang ◽  
Wei Wang ◽  
Qingqing Fang ◽  
Hong Jiang ◽  
Qinchuan Xin ◽  
...  
Keyword(s):  
Wavelet Transform ◽  
Soil Properties ◽  
Least Squares ◽  
Discrete Wavelet Transform ◽  
Spectral Data ◽  
Near Infrared ◽  
Least Squares Method ◽  
Discrete Wavelet ◽  
Infrared Spectral ◽  
Partial Least Squares Method

N-way partial least squares combined with new self-construction strategy—A promising approach of using near infrared spectral data for quantitative determination of multiple compounds

2019 ◽  
Vol 28 (2) ◽  
pp. 113-121
Author(s):  
Xiang-Zhi Zhang ◽  
Ai-Jun Ma ◽  
Na Feng ◽  
Bao Qiong Li
Keyword(s):  
Quantitative Analysis ◽  
Least Squares ◽  
Partial Least Squares ◽  
Near Infrared ◽  
Least Squares Method ◽  
Three Dimensional ◽  
Near Infrared Spectra ◽  
Infrared Spectral ◽  
Construction Strategy ◽  
Partial Least Squares Method

Because of the complexity of near infrared spectral data, effective strategies are necessary proposed for accurate quantitative analysis purpose. This work explores a new self-construction strategy for the arrangement of conventional near infrared two-dimensional spectra into new self-constructed three-dimensional spectra, and investigate the feasibility of N-way partial least squares combined with the new self-constructed three-dimensional near infrared spectra for obtaining accurate quantitative determination results. A proof-of-concept model system, the quantitative analysis of four components (moisture, oil, protein, and starch) in corn samples, was applied to evaluate the performance of the proposed strategy. The ability of the newly proposed approach to predict the target compounds was checked with test samples. The established models have good predictive power for the target compounds with acceptable values of Rp (range from 0.82 to 0.997) and RMSEP (range from 0.03 to 0.47). Compared with partial least squares method on pretreated near infrared spectra and N-way partial least squares method on the basis of near infrared self-constructed three-dimensional spectra, the proposed method is competitive.

Pre-Processing Influence on Near-Infrared Spectra for Determination of Volatile in Lignite Coal Samples

2014 ◽  
Vol 898 ◽  
pp. 831-834 ◽  
Author(s):  
Xiao Li Yang ◽  
Fan Wang
Keyword(s):  
Wavelet Transform ◽  
Least Squares ◽  
Discrete Wavelet Transform ◽  
Partial Least Squares ◽  
Partial Least Squares Regression ◽  
Near Infrared ◽  
Discrete Wavelet ◽  
Least Squares Regression ◽  
Lignite Coal

We studied volatile determination in lignite coal samples using near-infrared (NIR) spectra. Firstly, spectra were pre-processed to eliminate useless information. Then, determination model was constructed by partial least squares regression. To study the influence of pre-processing on determination of volatile for NIR analysis of lignite coal samples, we applied four techniques to pre-process spectra, including normalization, standardization, centralization, derivative and discrete wavelet transform. Comparison of the mean absolute percentage error (MAPE) and root mean square error of prediction (RMSEP) of the models show that the models constructed with spectra pre-processed by discrete wavelet transform gave the best results. Through parameters optimization, the results show that discrete wavelet transform and partial least squares regression can obtain satisfactory performance for moisture and volatile determination in coal samples.

Discrete Wavelet Transform on Near-Infrared Spectra Analysis for Moisture Determination in Lignitic Coal Samples

2014 ◽  
Vol 513-517 ◽  
pp. 319-322
Author(s):  
Xiao Li Yang ◽  
Neng Bang Hou ◽  
Jun You Shi ◽  
Yan Fang Li
Keyword(s):  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Near Infrared ◽  
Processing Method ◽  
Discrete Wavelet ◽  
Moisture Determination ◽  
Least Squares Regression ◽  
Spectra Analysis ◽  
Near Infrared Spectra ◽  
Compressed Data

We studied moisture determination in lignitic coal samples through near-infrared (NIR) technique. This research was developed by applying partical least squares regression (PLS) and discrete wavelet transform (DWT). Firstly, the NIR spectra were pre-processed by DWT for fitting and compression. Then, the compressed data were used to build regression model with PLS for moisture determination in coal samples. Three type DWTs were investigated.Determination performance at different resolution scales was studied. The results show that DWT is a very efficient pre-processing method for NIR spectra analysis.

Pre-Processing Influence on Identification of Optimal Path Length for NIR Analysis of Tea Polyphenols

2013 ◽  
Vol 791-793 ◽  
pp. 265-268
Author(s):  
Xiao Li Yang ◽  
Qiong He ◽  
Li Liu ◽  
Tong Yang
Keyword(s):  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Path Length ◽  
Near Infrared ◽  
Optimal Path ◽  
Tea Polyphenols ◽  
Percentage Error ◽  
Discrete Wavelet ◽  
Least Squares Regression ◽  
Path Lengths

We investigated the optical path length to tea polyphenols (TP) determination in Puer tea by near infrared (NIR) spectroscopy. The NIR spectra samples include three path lengths (1mm, 2mm and 5mm). Firstly, spectra were pre-processed to eliminate useless information. Then, determination model was constructed by partial least squares regression. To study the influence of pre-processing on identification of optimal path for NIR analysis of tea polyphenols, we applied five techniques to pre-process spectra, including normalization, standardization, centralization, derivative and discrete wavelet transform. Comparison of the mean absolute percentage error (MAPE) of the models with different path lengths show that the models constructed with spectra collected in 2mm path length gave the best results. 1mm path length gained the uncorrected determination results. Normalization, centralization and derivative are better than standardization or discrete wavelet transform for pre-processing.

Sign in / Sign up

Export Citation Format

Share Document