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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |