Application of NIR Spectral Standardization Based on Principal Component Score Evaluation in Wheat Flour Crude Protein Model Sharing

In order to explore spectral standardization methods for spectra collected by different NIR spectrometers, to reduce spectral differences, and to realize model sharing among different instruments, the crude protein content of 154 wheat flour samples was measured using one grating and three Fabry-Per...

Full description

Saved in:
Bibliographic Details
Main Authors: Jing Tian, Xinyu Chen, Zhennan Liang, Wenliang Qi, Xiaohuan Zheng, Daoli Lu, Bin Chen
Format: Article
Language:English
Published: Wiley 2022-01-01
Series:Journal of Food Quality
Online Access:http://dx.doi.org/10.1155/2022/9009756
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850166082714730496
author Jing Tian
Xinyu Chen
Zhennan Liang
Wenliang Qi
Xiaohuan Zheng
Daoli Lu
Bin Chen
author_facet Jing Tian
Xinyu Chen
Zhennan Liang
Wenliang Qi
Xiaohuan Zheng
Daoli Lu
Bin Chen
author_sort Jing Tian
collection DOAJ
description In order to explore spectral standardization methods for spectra collected by different NIR spectrometers, to reduce spectral differences, and to realize model sharing among different instruments, the crude protein content of 154 wheat flour samples was measured using one grating and three Fabry-Perot tunable filter NIR spectrometers in wavelength. At the same wavelength range and wavelength interval, three algorithms, namely, direct standardization (DS), piecewise direct standardization (PDS), and simple linear regression direct standardization (SLRDS), were used to standardize spectra collected by different instruments from the same samples. Spectral standardization error rate (SSER), principal component score error rate (PCSER), and other indicators were employed to analyze the spectral differences between the master and the target spectra, and the effect of model sharing was evaluated using parameters including prediction correlation coefficient (Rp), root mean square error of prediction (RMSEP), and relative prediction deviation (RPD). The results show the following: (1) The difference between spectra can be quantitatively evaluated through analyzing SSER and PCSER. (2) After standardization by the three algorithms, the spectral difference between the three target and the master spectrometers is significantly reduced and the prediction effect of the master model is greatly improved. (3) Among the three algorithms, DS algorithm had the smallest error rate in standardizing spectra from three target spectrometers. After standardization by the DS algorithm, the master model had the best effect. Its prediction accuracy was greatly improved compared with that before standardization. (4) The standard model established based on the S450 spectrometer can be applied to the same spectrometer as the N500 spectrometer with the same resolution and different wavelength ranges, so as to achieve model sharing. Therefore, DS, PDS, and SLRDS algorithms can effectively reduce the spectral differences between different instruments and realize the sharing of NIR calibration models for wheat flour crude protein measurement.
format Article
id doaj-art-e42e48f0a79b467eb3cfdef4bbd1d853
institution OA Journals
issn 1745-4557
language English
publishDate 2022-01-01
publisher Wiley
record_format Article
series Journal of Food Quality
spelling doaj-art-e42e48f0a79b467eb3cfdef4bbd1d8532025-08-20T02:21:34ZengWileyJournal of Food Quality1745-45572022-01-01202210.1155/2022/9009756Application of NIR Spectral Standardization Based on Principal Component Score Evaluation in Wheat Flour Crude Protein Model SharingJing Tian0Xinyu Chen1Zhennan Liang2Wenliang Qi3Xiaohuan Zheng4Daoli Lu5Bin Chen6School of Food and Biological EngineeringDepartment of Physical ChemistrySchool of Mechanical EngineeringSchool of Food and Biological EngineeringSchool of Food and Biological EngineeringSchool of Food and Biological EngineeringSchool of Food and Biological EngineeringIn order to explore spectral standardization methods for spectra collected by different NIR spectrometers, to reduce spectral differences, and to realize model sharing among different instruments, the crude protein content of 154 wheat flour samples was measured using one grating and three Fabry-Perot tunable filter NIR spectrometers in wavelength. At the same wavelength range and wavelength interval, three algorithms, namely, direct standardization (DS), piecewise direct standardization (PDS), and simple linear regression direct standardization (SLRDS), were used to standardize spectra collected by different instruments from the same samples. Spectral standardization error rate (SSER), principal component score error rate (PCSER), and other indicators were employed to analyze the spectral differences between the master and the target spectra, and the effect of model sharing was evaluated using parameters including prediction correlation coefficient (Rp), root mean square error of prediction (RMSEP), and relative prediction deviation (RPD). The results show the following: (1) The difference between spectra can be quantitatively evaluated through analyzing SSER and PCSER. (2) After standardization by the three algorithms, the spectral difference between the three target and the master spectrometers is significantly reduced and the prediction effect of the master model is greatly improved. (3) Among the three algorithms, DS algorithm had the smallest error rate in standardizing spectra from three target spectrometers. After standardization by the DS algorithm, the master model had the best effect. Its prediction accuracy was greatly improved compared with that before standardization. (4) The standard model established based on the S450 spectrometer can be applied to the same spectrometer as the N500 spectrometer with the same resolution and different wavelength ranges, so as to achieve model sharing. Therefore, DS, PDS, and SLRDS algorithms can effectively reduce the spectral differences between different instruments and realize the sharing of NIR calibration models for wheat flour crude protein measurement.http://dx.doi.org/10.1155/2022/9009756
spellingShingle Jing Tian
Xinyu Chen
Zhennan Liang
Wenliang Qi
Xiaohuan Zheng
Daoli Lu
Bin Chen
Application of NIR Spectral Standardization Based on Principal Component Score Evaluation in Wheat Flour Crude Protein Model Sharing
Journal of Food Quality
title Application of NIR Spectral Standardization Based on Principal Component Score Evaluation in Wheat Flour Crude Protein Model Sharing
title_full Application of NIR Spectral Standardization Based on Principal Component Score Evaluation in Wheat Flour Crude Protein Model Sharing
title_fullStr Application of NIR Spectral Standardization Based on Principal Component Score Evaluation in Wheat Flour Crude Protein Model Sharing
title_full_unstemmed Application of NIR Spectral Standardization Based on Principal Component Score Evaluation in Wheat Flour Crude Protein Model Sharing
title_short Application of NIR Spectral Standardization Based on Principal Component Score Evaluation in Wheat Flour Crude Protein Model Sharing
title_sort application of nir spectral standardization based on principal component score evaluation in wheat flour crude protein model sharing
url http://dx.doi.org/10.1155/2022/9009756
work_keys_str_mv AT jingtian applicationofnirspectralstandardizationbasedonprincipalcomponentscoreevaluationinwheatflourcrudeproteinmodelsharing
AT xinyuchen applicationofnirspectralstandardizationbasedonprincipalcomponentscoreevaluationinwheatflourcrudeproteinmodelsharing
AT zhennanliang applicationofnirspectralstandardizationbasedonprincipalcomponentscoreevaluationinwheatflourcrudeproteinmodelsharing
AT wenliangqi applicationofnirspectralstandardizationbasedonprincipalcomponentscoreevaluationinwheatflourcrudeproteinmodelsharing
AT xiaohuanzheng applicationofnirspectralstandardizationbasedonprincipalcomponentscoreevaluationinwheatflourcrudeproteinmodelsharing
AT daolilu applicationofnirspectralstandardizationbasedonprincipalcomponentscoreevaluationinwheatflourcrudeproteinmodelsharing
AT binchen applicationofnirspectralstandardizationbasedonprincipalcomponentscoreevaluationinwheatflourcrudeproteinmodelsharing