Prediction of Key Quality Parameters in Hot Air-Dried Jujubes Based on Hyperspectral Imaging

Traditional biochemical analysis methods are not only resource-intensive and time-consuming, but are increasingly inadequate for meeting the demands of modern production and quality testing. In recent years, hyperspectral imaging (HSI) technology has been widely applied as a non-destructive detectio...

Full description

Saved in:
Bibliographic Details
Main Authors: Quancheng Liu, Chunzhan Yu, Yuxuan Ma, Hongwei Zhang, Lei Yan, Shuxiang Fan
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Foods
Subjects:
Online Access:https://www.mdpi.com/2304-8158/14/11/1855
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330649647808512
author Quancheng Liu
Chunzhan Yu
Yuxuan Ma
Hongwei Zhang
Lei Yan
Shuxiang Fan
author_facet Quancheng Liu
Chunzhan Yu
Yuxuan Ma
Hongwei Zhang
Lei Yan
Shuxiang Fan
author_sort Quancheng Liu
collection DOAJ
description Traditional biochemical analysis methods are not only resource-intensive and time-consuming, but are increasingly inadequate for meeting the demands of modern production and quality testing. In recent years, hyperspectral imaging (HSI) technology has been widely applied as a non-destructive detection method for fruit and vegetable quality assessment. This study, based on HSI technology, systematically investigates the distribution patterns of jujube quality parameters under various drying temperature conditions. It focuses on analyzing six key quality indicators: <i>L</i>*, <i>a</i>*, <i>b</i>*, soluble solid content (SSC), hardness, and moisture content. HSI was used to acquire reflectance (R), absorbance (A), and Kubelka–Munk (K-M) spectral data of jujubes at various drying temperatures, followed by several spectral preprocessing methods, including standard normal variate (SNV), baseline correction (baseline), and Savitzky–Golay first derivative (SG1st). Subsequently, a nonlinear support vector regression (SVR) model was used to perform regression modeling for the six quality parameters. The results demonstrate that the SG1st preprocessing method significantly enhanced the predictive capability of the model. For the predictions of <i>L</i>*, <i>a</i>*, <i>b</i>*, SSC, hardness, and moisture content, the best inversion models achieved coefficients of determination <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>R</mi><mi>p</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> of 0.9972, 0.9970, 0.9857, and 0.9972, respectively. To further enhance modeling accuracy, deep learning models such as bidirectional long short-term memory (BiLSTM), bidirectional gated recurrent unit (BiGRU), and convolutional neural network–bidirectional gated recurrent unit (CNN-BiGRU) were introduced and compared comprehensively under the optimal spectral preprocessing conditions. The results demonstrate that deep learning models significantly improved modeling accuracy, with the CNN-BiGRU model performing particularly well. Compared to the SVR model, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>R</mi><mi>p</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> values for <i>L</i>*, <i>a</i>*, <i>b</i>*, SSC, hardness, and moisture increased by 0.005, 0.007, 0.008, 0.011, 0.007, and 0.006, respectively; the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>R</mi><mi>P</mi><mi>D</mi></mrow></semantics></math></inline-formula> values increased by 0.036, 0.04, 0.26, 0.462, 0.428, and 0.216. This study provides important insights into the further application of HSI technology in the quality monitoring and optimization of the jujube drying process.
format Article
id doaj-art-44ea32eecab34bbbac92ac8f494a4b93
institution Kabale University
issn 2304-8158
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Foods
spelling doaj-art-44ea32eecab34bbbac92ac8f494a4b932025-08-20T03:46:50ZengMDPI AGFoods2304-81582025-05-011411185510.3390/foods14111855Prediction of Key Quality Parameters in Hot Air-Dried Jujubes Based on Hyperspectral ImagingQuancheng Liu0Chunzhan Yu1Yuxuan Ma2Hongwei Zhang3Lei Yan4Shuxiang Fan5School of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaTraditional biochemical analysis methods are not only resource-intensive and time-consuming, but are increasingly inadequate for meeting the demands of modern production and quality testing. In recent years, hyperspectral imaging (HSI) technology has been widely applied as a non-destructive detection method for fruit and vegetable quality assessment. This study, based on HSI technology, systematically investigates the distribution patterns of jujube quality parameters under various drying temperature conditions. It focuses on analyzing six key quality indicators: <i>L</i>*, <i>a</i>*, <i>b</i>*, soluble solid content (SSC), hardness, and moisture content. HSI was used to acquire reflectance (R), absorbance (A), and Kubelka–Munk (K-M) spectral data of jujubes at various drying temperatures, followed by several spectral preprocessing methods, including standard normal variate (SNV), baseline correction (baseline), and Savitzky–Golay first derivative (SG1st). Subsequently, a nonlinear support vector regression (SVR) model was used to perform regression modeling for the six quality parameters. The results demonstrate that the SG1st preprocessing method significantly enhanced the predictive capability of the model. For the predictions of <i>L</i>*, <i>a</i>*, <i>b</i>*, SSC, hardness, and moisture content, the best inversion models achieved coefficients of determination <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>R</mi><mi>p</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> of 0.9972, 0.9970, 0.9857, and 0.9972, respectively. To further enhance modeling accuracy, deep learning models such as bidirectional long short-term memory (BiLSTM), bidirectional gated recurrent unit (BiGRU), and convolutional neural network–bidirectional gated recurrent unit (CNN-BiGRU) were introduced and compared comprehensively under the optimal spectral preprocessing conditions. The results demonstrate that deep learning models significantly improved modeling accuracy, with the CNN-BiGRU model performing particularly well. Compared to the SVR model, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msubsup><mi>R</mi><mi>p</mi><mn>2</mn></msubsup></mrow></semantics></math></inline-formula> values for <i>L</i>*, <i>a</i>*, <i>b</i>*, SSC, hardness, and moisture increased by 0.005, 0.007, 0.008, 0.011, 0.007, and 0.006, respectively; the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>R</mi><mi>P</mi><mi>D</mi></mrow></semantics></math></inline-formula> values increased by 0.036, 0.04, 0.26, 0.462, 0.428, and 0.216. This study provides important insights into the further application of HSI technology in the quality monitoring and optimization of the jujube drying process.https://www.mdpi.com/2304-8158/14/11/1855dried jujubeshyperspectral imagingmachine learningdeep learningquality parameters
spellingShingle Quancheng Liu
Chunzhan Yu
Yuxuan Ma
Hongwei Zhang
Lei Yan
Shuxiang Fan
Prediction of Key Quality Parameters in Hot Air-Dried Jujubes Based on Hyperspectral Imaging
Foods
dried jujubes
hyperspectral imaging
machine learning
deep learning
quality parameters
title Prediction of Key Quality Parameters in Hot Air-Dried Jujubes Based on Hyperspectral Imaging
title_full Prediction of Key Quality Parameters in Hot Air-Dried Jujubes Based on Hyperspectral Imaging
title_fullStr Prediction of Key Quality Parameters in Hot Air-Dried Jujubes Based on Hyperspectral Imaging
title_full_unstemmed Prediction of Key Quality Parameters in Hot Air-Dried Jujubes Based on Hyperspectral Imaging
title_short Prediction of Key Quality Parameters in Hot Air-Dried Jujubes Based on Hyperspectral Imaging
title_sort prediction of key quality parameters in hot air dried jujubes based on hyperspectral imaging
topic dried jujubes
hyperspectral imaging
machine learning
deep learning
quality parameters
url https://www.mdpi.com/2304-8158/14/11/1855
work_keys_str_mv AT quanchengliu predictionofkeyqualityparametersinhotairdriedjujubesbasedonhyperspectralimaging
AT chunzhanyu predictionofkeyqualityparametersinhotairdriedjujubesbasedonhyperspectralimaging
AT yuxuanma predictionofkeyqualityparametersinhotairdriedjujubesbasedonhyperspectralimaging
AT hongweizhang predictionofkeyqualityparametersinhotairdriedjujubesbasedonhyperspectralimaging
AT leiyan predictionofkeyqualityparametersinhotairdriedjujubesbasedonhyperspectralimaging
AT shuxiangfan predictionofkeyqualityparametersinhotairdriedjujubesbasedonhyperspectralimaging