Miniaturized NIRS Coupled with Machine Learning Algorithm for Noninvasively Quantifying Gluten Quality in Wheat Flour

This research implemented a miniaturized near-infrared spectroscopy (NIRS) system integrated with machine learning approaches for the quantitative evaluation of dry gluten content (DGC), wet gluten content (WGC), and the gluten index (GI) in wheat flour in a noninvasive manner. Five different algori...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuling Wang, Chen Zhang, Xinhua Li, Longzhu Xing, Mengchao Lv, Hongju He, Leiqing Pan, Xingqi Ou
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Foods
Subjects:
Online Access:https://www.mdpi.com/2304-8158/14/13/2393
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849428880400580608
author Yuling Wang
Chen Zhang
Xinhua Li
Longzhu Xing
Mengchao Lv
Hongju He
Leiqing Pan
Xingqi Ou
author_facet Yuling Wang
Chen Zhang
Xinhua Li
Longzhu Xing
Mengchao Lv
Hongju He
Leiqing Pan
Xingqi Ou
author_sort Yuling Wang
collection DOAJ
description This research implemented a miniaturized near-infrared spectroscopy (NIRS) system integrated with machine learning approaches for the quantitative evaluation of dry gluten content (DGC), wet gluten content (WGC), and the gluten index (GI) in wheat flour in a noninvasive manner. Five different algorithms were employed to mine the relationship between the full-range spectra (900–1700 nm) and three parameters, with support vector regression (SVR) demonstrating the best prediction performance for all gluten parameters (R<sub>P</sub> = 0.9370–0.9430, RMSEP = 0.3450–0.4043%, and RPD = 3.1348–3.4998). Through a comparative evaluation of five wavelength selection techniques, 25–30 optimal wavelengths were identified, enabling the development of optimized SVR models. The improved whale optimization algorithm iWOA-based SVR (iWOA-SVR) model exhibited the strongest predictive capability among the five optimal wavelengths-based models, achieving comparable accuracy to the full-range spectra SVR for all gluten parameters (R<sub>P</sub> = 0.9190–0.9385, RMSEP = 0.3927–0.5743%, and RPD = 3.0424–3.2509). The model’s robustness was confirmed through external validation and statistical analyses (<i>p</i> > 0.05 for F-test and <i>t</i>-test). The results highlight the effectiveness of micro-NIRS combined with iWOA-SVR for the nondestructive gluten quality assessment of wheat flour, providing a more valuable reference for expanding the use of NIRS technology and developing portable specialized NIRS equipment for industrial-level applications in the future.
format Article
id doaj-art-7130a56cf9d241cf85ba27601d6e351b
institution Kabale University
issn 2304-8158
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Foods
spelling doaj-art-7130a56cf9d241cf85ba27601d6e351b2025-08-20T03:28:32ZengMDPI AGFoods2304-81582025-07-011413239310.3390/foods14132393Miniaturized NIRS Coupled with Machine Learning Algorithm for Noninvasively Quantifying Gluten Quality in Wheat FlourYuling Wang0Chen Zhang1Xinhua Li2Longzhu Xing3Mengchao Lv4Hongju He5Leiqing Pan6Xingqi Ou7School of Agriculture, Henan Institute of Science and Technology, Xinxiang 453003, ChinaSchool of Information Engineering, Xinxiang Institute of Engineering, Xinxiang 453700, ChinaSchool of Agriculture, Henan Institute of Science and Technology, Xinxiang 453003, ChinaSchool of Food Science, Henan Institute of Science and Technology, Xinxiang 453003, ChinaSchool of Food Science, Henan Institute of Science and Technology, Xinxiang 453003, ChinaSchool of Food Science, Henan Institute of Science and Technology, Xinxiang 453003, ChinaCollege of Food Science and Technology, Nanjing Agricultural University, Nanjing 210095, ChinaSchool of Agriculture, Henan Institute of Science and Technology, Xinxiang 453003, ChinaThis research implemented a miniaturized near-infrared spectroscopy (NIRS) system integrated with machine learning approaches for the quantitative evaluation of dry gluten content (DGC), wet gluten content (WGC), and the gluten index (GI) in wheat flour in a noninvasive manner. Five different algorithms were employed to mine the relationship between the full-range spectra (900–1700 nm) and three parameters, with support vector regression (SVR) demonstrating the best prediction performance for all gluten parameters (R<sub>P</sub> = 0.9370–0.9430, RMSEP = 0.3450–0.4043%, and RPD = 3.1348–3.4998). Through a comparative evaluation of five wavelength selection techniques, 25–30 optimal wavelengths were identified, enabling the development of optimized SVR models. The improved whale optimization algorithm iWOA-based SVR (iWOA-SVR) model exhibited the strongest predictive capability among the five optimal wavelengths-based models, achieving comparable accuracy to the full-range spectra SVR for all gluten parameters (R<sub>P</sub> = 0.9190–0.9385, RMSEP = 0.3927–0.5743%, and RPD = 3.0424–3.2509). The model’s robustness was confirmed through external validation and statistical analyses (<i>p</i> > 0.05 for F-test and <i>t</i>-test). The results highlight the effectiveness of micro-NIRS combined with iWOA-SVR for the nondestructive gluten quality assessment of wheat flour, providing a more valuable reference for expanding the use of NIRS technology and developing portable specialized NIRS equipment for industrial-level applications in the future.https://www.mdpi.com/2304-8158/14/13/2393wheat flourNIRSchemometricsglutenmachine learning
spellingShingle Yuling Wang
Chen Zhang
Xinhua Li
Longzhu Xing
Mengchao Lv
Hongju He
Leiqing Pan
Xingqi Ou
Miniaturized NIRS Coupled with Machine Learning Algorithm for Noninvasively Quantifying Gluten Quality in Wheat Flour
Foods
wheat flour
NIRS
chemometrics
gluten
machine learning
title Miniaturized NIRS Coupled with Machine Learning Algorithm for Noninvasively Quantifying Gluten Quality in Wheat Flour
title_full Miniaturized NIRS Coupled with Machine Learning Algorithm for Noninvasively Quantifying Gluten Quality in Wheat Flour
title_fullStr Miniaturized NIRS Coupled with Machine Learning Algorithm for Noninvasively Quantifying Gluten Quality in Wheat Flour
title_full_unstemmed Miniaturized NIRS Coupled with Machine Learning Algorithm for Noninvasively Quantifying Gluten Quality in Wheat Flour
title_short Miniaturized NIRS Coupled with Machine Learning Algorithm for Noninvasively Quantifying Gluten Quality in Wheat Flour
title_sort miniaturized nirs coupled with machine learning algorithm for noninvasively quantifying gluten quality in wheat flour
topic wheat flour
NIRS
chemometrics
gluten
machine learning
url https://www.mdpi.com/2304-8158/14/13/2393
work_keys_str_mv AT yulingwang miniaturizednirscoupledwithmachinelearningalgorithmfornoninvasivelyquantifyingglutenqualityinwheatflour
AT chenzhang miniaturizednirscoupledwithmachinelearningalgorithmfornoninvasivelyquantifyingglutenqualityinwheatflour
AT xinhuali miniaturizednirscoupledwithmachinelearningalgorithmfornoninvasivelyquantifyingglutenqualityinwheatflour
AT longzhuxing miniaturizednirscoupledwithmachinelearningalgorithmfornoninvasivelyquantifyingglutenqualityinwheatflour
AT mengchaolv miniaturizednirscoupledwithmachinelearningalgorithmfornoninvasivelyquantifyingglutenqualityinwheatflour
AT hongjuhe miniaturizednirscoupledwithmachinelearningalgorithmfornoninvasivelyquantifyingglutenqualityinwheatflour
AT leiqingpan miniaturizednirscoupledwithmachinelearningalgorithmfornoninvasivelyquantifyingglutenqualityinwheatflour
AT xingqiou miniaturizednirscoupledwithmachinelearningalgorithmfornoninvasivelyquantifyingglutenqualityinwheatflour