Zhengguang Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Zhengguang Chen has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
Jin-Ming Liu
College of Information and Electrical Engineering, Heilongjiang Bayi Agricultural University, Daqing 163319, China
4 shared publicationsShuo Liu
4 shared publicationsFeng Jiao
College of Agriculture, Heilongjiang Bayi Agricultural University, Daqing 163319, China
3 shared publications- Shuo Liu
College of Information and Electrical Engineering, Heilongjiang Bayi Agricultural University, Daqing, Heilongjiang, China
3 shared publications Xiao-Wen Zhang
Heilongjiang Bayi Agr Univ, Coll Informat & Elect Engn, Daqing 163319, Peoples R China
3 shared publicationsJinming Liu
College of Information and Electrical Engineering, Heilongjiang Bayi Agricultural University, Daqing, 163319, China
2 shared publications
Latest Publications
- Open Access
- 2 July 2026
- Published by MDPI AG in Agriculture
- Vol. 16 (13) , 1447
Kernel-Independent Component Analysis for Near-Infrared Spectroscopic Prediction of Tannin Content in Sorghum Grains
To eliminate the complex nonlinear mixing relationships among spectral features in near-infrared (NIR) quantitative analysis, and to overcome the limitations of principal component analysis (PCA), which relies solely on covariance structure and linear assumptions and is therefore incapable of effectively handling nonlinear signals, this study employs kernel-independent component analysis (KICA), for nonlinear feature extraction from NIR spectra, combined with a regression model to achieve rapid detection of tannin content in sorghum grains. KICA effectively separates nonlinearly mixed source signals by mapping spectral data into a high-dimensional feature space via the kernel trick. The prediction model built on KICA-extracted features and support vector regression (SVR) consistently delivered the highest test-set prediction accuracy and exhibited the smallest training-to-test R2 gap among all evaluated models across repeated random splits, confirming its superiority over PCA-based feature extraction methods and standalone SVR, and its competitive performance relative to ICA-based methods, in both predictive accuracy and generalization capability. Additionally, KICA yielded a lower reconstruction error for the original spectra, indicating its ability to more completely retain the nonlinear informative content of the spectral data. By calculating the mean absolute coefficient of each independent component, it was found that the component with the highest contribution was strongly correlated with the wavelength range near the characteristic absorption peaks of tannin, thereby enhancing the chemical interpretability of the features. On a publicly available corn NIR dataset, the proposed method also achieved superior prediction results compared with benchmark methods, validating its generalization capability across different sample types and quality attributes. This study confirms the feasibility of introducing nonlinear blind source separation via KICA into NIR quantitative analysis, offering a promising approach for spectral feature extraction in the rapid quality assessment of agricultural products with complex matrices.
- 2 July 2026
- Published by MDPI AG in Agriculture
- Vol. 16 (13) , 1447
Open AccessKernel-Independent Component Analysis for Near-Infrared Spectroscopic Prediction of Tannin Content in Sorghum Grains
To eliminate the complex nonlinear mixing relationships among spectral features in near-infrared (NIR) quantitative analysis, and to overcome the limitations of principal component analysis (PCA), which relies solely on covariance structure and linear assumptions and is therefore incapable of effectively handling nonlinear signals, this study employs kernel-independent component analysis (KICA), for nonlinear feature extraction from NIR spectra, combined with a regression model to achieve rapid detection of tannin content in sorghum grains. KICA effectively separates nonlinearly mixed source signals by mapping spectral data into a high-dimensional feature space via the kernel trick. The prediction model built on KICA-extracted features and support vector regression (SVR) consistently delivered the highest test-set prediction accuracy and exhibited the smallest training-to-test R2 gap among all evaluated models across repeated random splits, confirming its superiority over PCA-based feature extraction methods and standalone SVR, and its competitive performance relative to ICA-based methods, in both predictive accuracy and generalization capability. Additionally, KICA yielded a lower reconstruction error for the original spectra, indicating its ability to more completely retain the nonlinear informative content of the spectral data. By calculating the mean absolute coefficient of each independent component, it was found that the component with the highest contribution was strongly correlated with the wavelength range near the characteristic absorption peaks of tannin, thereby enhancing the chemical interpretability of the features. On a publicly available corn NIR dataset, the proposed method also achieved superior prediction results compared with benchmark methods, validating its generalization capability across different sample types and quality attributes. This study confirms the feasibility of introducing nonlinear blind source separation via KICA into NIR quantitative analysis, offering a promising approach for spectral feature extraction in the rapid quality assessment of agricultural products with complex matrices.
- Open Access
- 22 February 2026
- Published by MDPI AG in Agriculture
- Vol. 16 (4) , 485
Multi-Output Gaussian Process Regression for Rapid Multi-Nutrient Prediction in Soil Using Near-Infrared Spectroscopy
The concentrations of nitrogen (N), phosphorus (P), potassium (K), organic matter (OM), and pH in soil are critical markers of fertility that influence crop growth and yield. Traditional wet-chemical analyses are labor-intensive, time-consuming, and costly, thereby constraining timely soil information acquisition for precision agriculture. This study evaluates whether multi-output Gaussian process regression (MOGPR) can enhance the prediction accuracy of multiple soil nutrients by exploiting their intrinsic correlations, in comparison with single-output Gaussian process regression (SOGPR). Near-infrared (NIR) spectroscopy was applied to 622 typical black soil samples collected from the Farm 855 (45°43′ N, 131°35′ E), Heilongjiang Province, China. Corresponding MOGPR and SOGPR models were developed for systematic performance comparison. Results indicated that MOGPR significantly outperformed SOGPR for nutrients exhibiting moderate-to-strong intercorrelations (N, P, K, and OM), yielding R2 improvements of 0.070.28 and RPD increases of 16–40%, whereas only limited gains were observed for pH due to its weak correlations with other nutrients. These findings indicate that combining NIR spectroscopy with MOGPR offers significant potential for rapid, nondestructive assessment of multiple soil nutrients. This study further establishes a correlation-aware multi-output modeling framework that links shared spectral responses with an inter-nutrient dependency structure, providing methodological guidance for multi-nutrient soil prediction.
- 22 February 2026
- Published by MDPI AG in Agriculture
- Vol. 16 (4) , 485
Open AccessMulti-Output Gaussian Process Regression for Rapid Multi-Nutrient Prediction in Soil Using Near-Infrared Spectroscopy
The concentrations of nitrogen (N), phosphorus (P), potassium (K), organic matter (OM), and pH in soil are critical markers of fertility that influence crop growth and yield. Traditional wet-chemical analyses are labor-intensive, time-consuming, and costly, thereby constraining timely soil information acquisition for precision agriculture. This study evaluates whether multi-output Gaussian process regression (MOGPR) can enhance the prediction accuracy of multiple soil nutrients by exploiting their intrinsic correlations, in comparison with single-output Gaussian process regression (SOGPR). Near-infrared (NIR) spectroscopy was applied to 622 typical black soil samples collected from the Farm 855 (45°43′ N, 131°35′ E), Heilongjiang Province, China. Corresponding MOGPR and SOGPR models were developed for systematic performance comparison. Results indicated that MOGPR significantly outperformed SOGPR for nutrients exhibiting moderate-to-strong intercorrelations (N, P, K, and OM), yielding R2 improvements of 0.070.28 and RPD increases of 16–40%, whereas only limited gains were observed for pH due to its weak correlations with other nutrients. These findings indicate that combining NIR spectroscopy with MOGPR offers significant potential for rapid, nondestructive assessment of multiple soil nutrients. This study further establishes a correlation-aware multi-output modeling framework that links shared spectral responses with an inter-nutrient dependency structure, providing methodological guidance for multi-nutrient soil prediction.
- Open Access
- 20 January 2026
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 16, 1726266
Rapid detection method of soybean seed germination potential based on the PLSR-MLP fusion model
In order to realize the rapid detection of soybean seed germination potential, this study designed a fusion model to solve the problem that the single model was insufficient in spectral feature analysis and the prediction performance was limited. The model combines the advantages of the Partial Least Squares Regression (PLSR) and the Multilayer Perceptron (MLP), and utilizing principal components extracted by PLSR as the input features for MLP to construct a soybean seed germination potential prediction model with both linear and nonlinear modeling capabilities. The PLSR module accurately extracts the linear features of the spectrum, and the MLP network further captures the nonlinear relationship between the spectral data and the target variable, which significantly improves the generalization ability of the model. The experimental results show that the prediction performance of the proposed PLSR-MLP fusion model (R p 2 = 0.9534, RMSEP = 7.3821) is significantly improved compared with the single PLSR model (R p 2 = 0.7284, RMSEP = 17.8154) and the single MLP model (R p 2 = 0.7935, RMSEP = 15.5335). In the prediction of soybean germination potential, the PLSR-MLP model also outperforms other single models (Support Vector Machine, SVM; Random Forest, RF) and other fusion models such as PLSR-SVM and PLSR-RF. The PLSR-MLP fusion model effectively addresses the limitations of a single model’s performance enhancement potential and the susceptibility to overfitting. It provides a new method for the efficient evaluation of seed germination potential. It also has practical application value for precision seed selection in agriculture and offers a new idea for near-infrared spectrum modeling.
- 20 January 2026
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 16, 1726266
Open AccessRapid detection method of soybean seed germination potential based on the PLSR-MLP fusion model
In order to realize the rapid detection of soybean seed germination potential, this study designed a fusion model to solve the problem that the single model was insufficient in spectral feature analysis and the prediction performance was limited. The model combines the advantages of the Partial Least Squares Regression (PLSR) and the Multilayer Perceptron (MLP), and utilizing principal components extracted by PLSR as the input features for MLP to construct a soybean seed germination potential prediction model with both linear and nonlinear modeling capabilities. The PLSR module accurately extracts the linear features of the spectrum, and the MLP network further captures the nonlinear relationship between the spectral data and the target variable, which significantly improves the generalization ability of the model. The experimental results show that the prediction performance of the proposed PLSR-MLP fusion model (R p 2 = 0.9534, RMSEP = 7.3821) is significantly improved compared with the single PLSR model (R p 2 = 0.7284, RMSEP = 17.8154) and the single MLP model (R p 2 = 0.7935, RMSEP = 15.5335). In the prediction of soybean germination potential, the PLSR-MLP model also outperforms other single models (Support Vector Machine, SVM; Random Forest, RF) and other fusion models such as PLSR-SVM and PLSR-RF. The PLSR-MLP fusion model effectively addresses the limitations of a single model’s performance enhancement potential and the susceptibility to overfitting. It provides a new method for the efficient evaluation of seed germination potential. It also has practical application value for precision seed selection in agriculture and offers a new idea for near-infrared spectrum modeling.
- 16 December 2025
- Published by Elsevier in Food Chemistry
- Vol. 501, 147614
Application of K-means ant colony optimization wavelength selection method combining similarity measures for soybean crude fat content detection
- 16 December 2025
- Published by Elsevier in Food Chemistry
- Vol. 501, 147614
Application of K-means ant colony optimization wavelength selection method combining similarity measures for soybean crude fat content detection
- 10 December 2025
- Published by Wiley in Journal of Chemometrics
- Vol. 39 (12)
Application of an ECAM‐ConvNeXt Model With Multichannel Spectrogram Based on Vis–NIR for Soil Property Prediction
Vis–NIR spectroscopy is increasingly widely used for soil property analysis due to its rapid, cost‐effective, and nondestructive advantages. In particular, deep learning models perform very well when working with large sample data. In this study, we propose a deep learning model based on three‐channel ECAM‐ConvNeXt. Firstly, the method applies three window functions, Bartlett, Gaussian, and Blackman, in the short‐time Fourier transform to convert a one‐dimensional spectral sequence signal into three different two‐dimensional spectrograms. Next, we perform multichannel feature fusion and use the resulting triple‐channel spectrograms as model inputs. This method fully preserves the temporal information and spectral characteristics of the spectral sequence, thereby improving the performance of the model. Secondly, this study introduces the Efficient Channel Attention Module in the ConvNeXt model. This module combines the advantages of the Convolutional Block Attention Module and Efficient Channel Attention Network, further enhancing the expressive ability of the network by highlighting useful information and suppressing irrelevant information. Finally, we also validate the effectiveness of multichannel inputs by deep learning models (AlexNet18, ResNet50, MobileNet‐V3, EfficientNet, VIT) and compare them with existing techniques reported in the literature. The results indicate that the root‐mean‐square error (RMSE) of the TriCH‐ECAM‐ConvNeXt model in predicting soil nitrogen content (N (g/kg)), organic carbon content (OC (g/kg)), cation exchange capacity (CEC (cmol(+)/kg)), pH, clay content (%), and sand content (%) was reduced to 0.9847, 19.7347, 6.3380, 0.3812, 5.1537, and 12.9706, respectively, and the coefficient of determination ( R 2 ) increased to 0.9307, 0.9544, 0.7999, 0.9206, 0.8493, and 0.7526, respectively.
- 10 December 2025
- Published by Wiley in Journal of Chemometrics
- Vol. 39 (12)
Application of an ECAM‐ConvNeXt Model With Multichannel Spectrogram Based on Vis–NIR for Soil Property Prediction
Vis–NIR spectroscopy is increasingly widely used for soil property analysis due to its rapid, cost‐effective, and nondestructive advantages. In particular, deep learning models perform very well when working with large sample data. In this study, we propose a deep learning model based on three‐channel ECAM‐ConvNeXt. Firstly, the method applies three window functions, Bartlett, Gaussian, and Blackman, in the short‐time Fourier transform to convert a one‐dimensional spectral sequence signal into three different two‐dimensional spectrograms. Next, we perform multichannel feature fusion and use the resulting triple‐channel spectrograms as model inputs. This method fully preserves the temporal information and spectral characteristics of the spectral sequence, thereby improving the performance of the model. Secondly, this study introduces the Efficient Channel Attention Module in the ConvNeXt model. This module combines the advantages of the Convolutional Block Attention Module and Efficient Channel Attention Network, further enhancing the expressive ability of the network by highlighting useful information and suppressing irrelevant information. Finally, we also validate the effectiveness of multichannel inputs by deep learning models (AlexNet18, ResNet50, MobileNet‐V3, EfficientNet, VIT) and compare them with existing techniques reported in the literature. The results indicate that the root‐mean‐square error (RMSE) of the TriCH‐ECAM‐ConvNeXt model in predicting soil nitrogen content (N (g/kg)), organic carbon content (OC (g/kg)), cation exchange capacity (CEC (cmol(+)/kg)), pH, clay content (%), and sand content (%) was reduced to 0.9847, 19.7347, 6.3380, 0.3812, 5.1537, and 12.9706, respectively, and the coefficient of determination ( R 2 ) increased to 0.9307, 0.9544, 0.7999, 0.9206, 0.8493, and 0.7526, respectively.
- 23 June 2025
- Published by Oxford University Press (OUP) in Journal of AOAC INTERNATIONAL
- Vol. 108 (6) , 818-827
Outlier Identification Method Based on Multi-Model Weighted Consensus in Conjunction With Monte Carlo Cross-Validation
Background: The accurate identification and removal of outliers are fundamental to the development of a robust model. Objective: Exclusively relying on a single model for outlier detection may be insufficient for the proper identification of all outliers. This study examines the identification of anomalous data using the multi-model consensus technique to address issues of false positives, false negatives, and model reliance inherent in the identification process using a singular model. Methods: This study introduces a method called Monte Carlo cross-validation in conjunction with multiple models of Weighted Consensus for outlier identification (MCWC, Monte Carlo Weighted Consensus). The proposed method integrates Monte Carlo random sampling with three distinct modeling methods: Partial Least-Squares Regression (PLSR), Gaussian process regression (GPR), and support vector regression (SVR). This integration allows for the amalgamation of predictions from each model, facilitating the identification of outliers effectively. Results: This study employed a dataset comprising 305 sorghum samples as the experimental foundation. The predictive model for sorghum protein was built using the data after removing outliers using the single model method and the MCWC method, respectively. The experimental results indicate that the dataset, which was obtained by removing outliers using a single modeling method, is appropriate for further modeling with the same method. However, it is not suitable for modeling with other methods due to issues related to model dependence. After applying the MCWC method to remove outliers, the average R2 of the model prediction set was found to be 0.8525. In contrast, the average R2 of the model prediction set, obtained by applying the Monte Carlo method combined exclusively with PLSR for outlier removal, is 0.8037. Conclusions: The MCWC method exhibits superior accuracy in identifying outliers and effectively addresses challenges such as false positive, false negative, and model dependence in the process of identifying near-infrared spectral outliers. This enhances the overall predictive performance of the calibration model for spectral quantitative analysis. Highlights: A multi-model dynamic weighted consensus outlier identification for near-infrared spectroscopy (NIRS) data is proposed. This dynamic weighting method effectively addresses the biases that can occur with simple averaging. The data after removing outliers using consensus methods is more suitable for modeling with a wider range of models.
- 23 June 2025
- Published by Oxford University Press (OUP) in Journal of AOAC INTERNATIONAL
- Vol. 108 (6) , 818-827
Outlier Identification Method Based on Multi-Model Weighted Consensus in Conjunction With Monte Carlo Cross-Validation
Background: The accurate identification and removal of outliers are fundamental to the development of a robust model. Objective: Exclusively relying on a single model for outlier detection may be insufficient for the proper identification of all outliers. This study examines the identification of anomalous data using the multi-model consensus technique to address issues of false positives, false negatives, and model reliance inherent in the identification process using a singular model. Methods: This study introduces a method called Monte Carlo cross-validation in conjunction with multiple models of Weighted Consensus for outlier identification (MCWC, Monte Carlo Weighted Consensus). The proposed method integrates Monte Carlo random sampling with three distinct modeling methods: Partial Least-Squares Regression (PLSR), Gaussian process regression (GPR), and support vector regression (SVR). This integration allows for the amalgamation of predictions from each model, facilitating the identification of outliers effectively. Results: This study employed a dataset comprising 305 sorghum samples as the experimental foundation. The predictive model for sorghum protein was built using the data after removing outliers using the single model method and the MCWC method, respectively. The experimental results indicate that the dataset, which was obtained by removing outliers using a single modeling method, is appropriate for further modeling with the same method. However, it is not suitable for modeling with other methods due to issues related to model dependence. After applying the MCWC method to remove outliers, the average R2 of the model prediction set was found to be 0.8525. In contrast, the average R2 of the model prediction set, obtained by applying the Monte Carlo method combined exclusively with PLSR for outlier removal, is 0.8037. Conclusions: The MCWC method exhibits superior accuracy in identifying outliers and effectively addresses challenges such as false positive, false negative, and model dependence in the process of identifying near-infrared spectral outliers. This enhances the overall predictive performance of the calibration model for spectral quantitative analysis. Highlights: A multi-model dynamic weighted consensus outlier identification for near-infrared spectroscopy (NIRS) data is proposed. This dynamic weighting method effectively addresses the biases that can occur with simple averaging. The data after removing outliers using consensus methods is more suitable for modeling with a wider range of models.
- 20 June 2025
- Published by Elsevier in Food Chemistry
- Vol. 491, 145254
Rapid detection of maize seed germination using near-infrared spectroscopy combined with Gaussian process regression
- 20 June 2025
- Published by Elsevier in Food Chemistry
- Vol. 491, 145254
Rapid detection of maize seed germination using near-infrared spectroscopy combined with Gaussian process regression
- Open Access
- 13 December 2024
- Published by Atlantis Press SARL
- p. 60-67
Research on Teaching Methods of Big Data Major Courses Under the Background of “Four New Disciplines” Construction
- 13 December 2024
- Published by Atlantis Press SARL
- p. 60-67
Open AccessResearch on Teaching Methods of Big Data Major Courses Under the Background of “Four New Disciplines” Construction