Analysis of Nutritional Content in Rice Seeds Based on Near-Infrared Spectroscopy

The nutritional quality of rice seeds is mainly determined by the content of key components such as protein, fat, and starch. Traditional chemical detection methods are time-consuming, labor-intensive, inefficient, and harmful to the environment. To overcome these limitations, this study developed a...

Full description

Saved in:
Bibliographic Details
Main Authors: Hengyuan Kong, Jianing Wang, Guanyu Lin, Jianbo Chen, Zhitao Xie
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Photonics
Subjects:
Online Access:https://www.mdpi.com/2304-6732/12/5/481
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849711270785187840
author Hengyuan Kong
Jianing Wang
Guanyu Lin
Jianbo Chen
Zhitao Xie
author_facet Hengyuan Kong
Jianing Wang
Guanyu Lin
Jianbo Chen
Zhitao Xie
author_sort Hengyuan Kong
collection DOAJ
description The nutritional quality of rice seeds is mainly determined by the content of key components such as protein, fat, and starch. Traditional chemical detection methods are time-consuming, labor-intensive, inefficient, and harmful to the environment. To overcome these limitations, this study developed a non-destructive detection method using near-infrared spectroscopy (1000–2200 nm) combined with linear regression modeling to achieve efficient and simultaneous multi-component analysis through the principle of anharmonic molecular vibration. By combining nutrient data from chemical analysis with spectroscopic measurements, we established a comprehensive rice seed composition dataset. After preprocessing with Gaussian denoising, first-order derivative transformation, SPA wavelength selection, and multiplicative scatter correction (MSC), we constructed partial least squares regression (PLS) and orthogonal partial least squares (OPLS), as well as artificial neural network (ANN) models. The OPLS model performed well in fat prediction (R<sup>2</sup> = 0.971, Q<sup>2</sup> = 0.926, RMSE = 0.175, RMSECV = 0.186), followed by starch (R<sup>2</sup> = 0.956, Q<sup>2</sup> = 0.907, RMSE = 0.159, RMSECV = 0.146) and protein (R<sup>2</sup> = 0.967, Q<sup>2</sup> = 0.936, RMSE = 0.164, RMSECV = 0.156). Our results confirm that the combination of the moving average, first order derivative, SPA, and MSC preprocessing of the OPLS model significantly improves the prediction. The developed non-destructive testing equipment provides a practical solution for automated, high-precision sorting of rice seeds based on nutrient composition.
format Article
id doaj-art-6e16e84d12b1440da2f14e04096287e1
institution DOAJ
issn 2304-6732
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Photonics
spelling doaj-art-6e16e84d12b1440da2f14e04096287e12025-08-20T03:14:39ZengMDPI AGPhotonics2304-67322025-05-0112548110.3390/photonics12050481Analysis of Nutritional Content in Rice Seeds Based on Near-Infrared SpectroscopyHengyuan Kong0Jianing Wang1Guanyu Lin2Jianbo Chen3Zhitao Xie4Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaCollege of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaThe nutritional quality of rice seeds is mainly determined by the content of key components such as protein, fat, and starch. Traditional chemical detection methods are time-consuming, labor-intensive, inefficient, and harmful to the environment. To overcome these limitations, this study developed a non-destructive detection method using near-infrared spectroscopy (1000–2200 nm) combined with linear regression modeling to achieve efficient and simultaneous multi-component analysis through the principle of anharmonic molecular vibration. By combining nutrient data from chemical analysis with spectroscopic measurements, we established a comprehensive rice seed composition dataset. After preprocessing with Gaussian denoising, first-order derivative transformation, SPA wavelength selection, and multiplicative scatter correction (MSC), we constructed partial least squares regression (PLS) and orthogonal partial least squares (OPLS), as well as artificial neural network (ANN) models. The OPLS model performed well in fat prediction (R<sup>2</sup> = 0.971, Q<sup>2</sup> = 0.926, RMSE = 0.175, RMSECV = 0.186), followed by starch (R<sup>2</sup> = 0.956, Q<sup>2</sup> = 0.907, RMSE = 0.159, RMSECV = 0.146) and protein (R<sup>2</sup> = 0.967, Q<sup>2</sup> = 0.936, RMSE = 0.164, RMSECV = 0.156). Our results confirm that the combination of the moving average, first order derivative, SPA, and MSC preprocessing of the OPLS model significantly improves the prediction. The developed non-destructive testing equipment provides a practical solution for automated, high-precision sorting of rice seeds based on nutrient composition.https://www.mdpi.com/2304-6732/12/5/481near infraredseedsspectral analysis
spellingShingle Hengyuan Kong
Jianing Wang
Guanyu Lin
Jianbo Chen
Zhitao Xie
Analysis of Nutritional Content in Rice Seeds Based on Near-Infrared Spectroscopy
Photonics
near infrared
seeds
spectral analysis
title Analysis of Nutritional Content in Rice Seeds Based on Near-Infrared Spectroscopy
title_full Analysis of Nutritional Content in Rice Seeds Based on Near-Infrared Spectroscopy
title_fullStr Analysis of Nutritional Content in Rice Seeds Based on Near-Infrared Spectroscopy
title_full_unstemmed Analysis of Nutritional Content in Rice Seeds Based on Near-Infrared Spectroscopy
title_short Analysis of Nutritional Content in Rice Seeds Based on Near-Infrared Spectroscopy
title_sort analysis of nutritional content in rice seeds based on near infrared spectroscopy
topic near infrared
seeds
spectral analysis
url https://www.mdpi.com/2304-6732/12/5/481
work_keys_str_mv AT hengyuankong analysisofnutritionalcontentinriceseedsbasedonnearinfraredspectroscopy
AT jianingwang analysisofnutritionalcontentinriceseedsbasedonnearinfraredspectroscopy
AT guanyulin analysisofnutritionalcontentinriceseedsbasedonnearinfraredspectroscopy
AT jianbochen analysisofnutritionalcontentinriceseedsbasedonnearinfraredspectroscopy
AT zhitaoxie analysisofnutritionalcontentinriceseedsbasedonnearinfraredspectroscopy