Partial Least Square Analysis of Lysozyme Near-Infrared Spectra

2000 ◽  
Vol 87 (3) ◽  
pp. 153-164 ◽  
Author(s):  
Shih-Yao B. Hu ◽  
Amy Lillquist ◽  
Mark A. Arnold ◽  
John M. Wiencek
Keyword(s):  
Infrared Spectra ◽  
Near Infrared ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Analysis ◽  
Near Infrared Spectra

Rapid Determining Contents of the Rhubarb Anthraquinones Compounds by Support Vector Machines Modeling based on Near Infrared Spectra

2020 ◽  
Vol 16 ◽  
Author(s):  
Linqi Liu ◽  
JInhua Luo ◽  
Chenxi Zhao ◽  
Bingxue Zhang ◽  
Wei Fan ◽  
...  
Keyword(s):  
Infrared Spectra ◽  
Near Infrared ◽  
Mean Squared Error ◽  
Rapid Determination ◽  
Partial Least Square ◽  
Least Square ◽  
Support Vector ◽  
Near Infrared Spectra ◽  
Aloe Emodin ◽  
Relative Differences

BACKGROUND: Measuring medicinal compounds to evaluate their quality and efficacy has been recognized as a useful approach in treatment. Rhubarb anthraquinones compounds (mainly including aloe-emodin, rhein, emodin, chrysophanol and physcion) are its main effective components as purgating drug. In the current Chinese Pharmacopoeia, the total anthraquinones content is designated as its quantitative quality and control index while the content of each compound has not been specified. METHODS: On the basis of forty rhubarb samples, the correlation models between the near infrared spectra and UPLC analysis data were constructed using support vector machine (SVM) and partial least square (PLS) methods according to Kennard and Stone algorithm for dividing the calibration/prediction datasets. Good models mean they have high correlation coefficients (R2) and low root mean squared error of prediction (RMSEP) values. RESULTS: The models constructed by SVM have much better performance than those by PLS methods. The SVM models have high R2 of 0.8951, 0.9738, 0.9849, 0.9779, 0.9411 and 0.9862 that correspond to aloe-emodin, rhein, emodin, chrysophanol, physcion and total anthraquinones contents, respectively. The corresponding RMSEPs are 0.3592, 0.4182, 0.4508, 0.7121, 0.8365 and 1.7910, respectively. 75% of the predicted results have relative differences being lower than 10%. As for rhein and total anthraquinones, all of the predicted results have relative differences being lower than 10%. CONCLUSION: The nonlinear models constructed by SVM showed good performances with predicted values close to the experimental values. This can perform the rapid determination of the main medicinal ingredients in rhubarb medicinal materials.

Using consensus interval partial least square in near infrared spectra analysis

2015 ◽  
Vol 144 ◽  
pp. 56-62 ◽  
Author(s):  
Guoli Ji ◽  
Guangzao Huang ◽  
Zijiang Yang ◽  
Xiaohui Wu ◽  
Xiaojing Chen ◽  
...  
Keyword(s):  
Infrared Spectra ◽  
Near Infrared ◽  
Partial Least Square ◽  
Least Square ◽  
Spectra Analysis ◽  
Near Infrared Spectra

Application of Wavelet Transform in the Prediction of Chemical Composition of Sunflower Seeds by Near Infrared Reflectance Spectroscopy

2011 ◽  
Vol 460-461 ◽  
pp. 599-604
Author(s):  
Rui Zhen Han ◽  
Shu Xi Cheng ◽  
Yong He
Keyword(s):  
Wavelet Transform ◽  
Chemical Composition ◽  
Infrared Spectra ◽  
Crude Protein ◽  
Near Infrared ◽  
Partial Least Square ◽  
Least Square ◽  
Sunflower Seeds ◽  
Near Infrared Reflectance ◽  
Near Infrared Spectra

In this paper, a method based on wavelet transform, which is used to analyze near infrared spectra, is discussed with the purpose of prediction of the content of oil, crude protein(CP) and moisture in sunflower seeds. By using different decomposing levels of Daubechies 2 wavelet transform, the near infrared spectra signals obtained from 105 intact sunflower seed samples were de-noised. Calibration equations were developed by partial least square regression (PLS) using the reconstructed spectra data with internal cross validation. It was indicated that the prediction effects varied when different wavelet decomposing level were employed. At the wavelet decomposing level 5, the best prediction effect was obtained, with the coefficient of correlation(R)and root mean square error prediction (RMSEP) being 0.953 and 0.466% for moisture;0.963 and 1.259% for crude protein; 0.801 and 1.874% for oil on a dry weight basis. It was concluded that the near infrared spectral model de-noised by means of wavelet transform can be used for the prediction of chemical composition in sunflower seeds for rapid pre-screening of quality characteristics on breeding programs.

Influence of spectral acquisition technique and wood anisotropy on the statistics of predictive near infrared–based models for wood density

2018 ◽  
Vol 26 (2) ◽  
pp. 106-116 ◽  
Author(s):  
Emylle Veloso Santos Costa ◽  
Maria Fernanda Vieira Rocha ◽  
Paulo Ricardo Gherardi Hein ◽  
Evelize Aparecida Amaral ◽  
Luana Maria dos Santos ◽  
...  
Keyword(s):  
Wood Density ◽  
Infrared Spectra ◽  
Near Infrared ◽  
Partial Least Square ◽  
Least Square ◽  
Integrating Sphere ◽  
Fiber Optic Probe ◽  
Near Infrared Spectra ◽  
Optic Probe ◽  
Acquisition Technique

Wood density is an important criterion for material classification, as it is directly related to quality of wood for structural use. Several studies have shown promising results for the estimation of wood density by near infrared spectroscopy. However, the optimal conditions for spectral acquisition need to be investigated in order to develop predictive models and to understand how anisotropy and surface roughness affect the statistics of predictive partial least square regression models. The aim of this study was to evaluate how the spectral acquisition technique, wood surface, and the surface quality influence the ability of partial least square–based models to estimate wood density. Near infrared spectra were recorded using an integrating sphere and fiber-optic probe on the tangential, radial, and transverse surfaces machined by circular and band saws in 278 wood specimens of six-year-old Eucalyptus hybrids. The basic density values determined by the conventional method were then correlated with near infrared spectra acquired using an integrating sphere and fiber-optic probe on the wood surfaces by means of partial least square regressions. The most promising models for predicting wood density were generated from near infrared spectra obtained from the transverse surface machined by the bandsaw, via an integrating sphere ([Formula: see text], RMSEP = 23 kg m−3 and RPD = 3.0) as well as for the optic fiber ([Formula: see text], RMSEP = 35 kg m−3 and RPD = 2.1). Surface quality affected the spectral information and robustness of predictive models with a rougher surface, caused by band sawing, showing better results.

Determination of Proteins in Human Serum by Near-Infrared Spectroscopy with Partial Least Square Analysis

2016 ◽  
Vol 49 (18) ◽  
pp. 2964-2976 ◽  
Author(s):  
Huixian Guo ◽  
Furong Huang ◽  
Yuanpeng Li ◽  
Tao Fang ◽  
Siqi Zhu ◽  
...  
Keyword(s):  
Infrared Spectroscopy ◽  
Human Serum ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Analysis
Sign in / Sign up

Export Citation Format

Share Document