Identification of Maize with Different Moldy Levels Based on Catalase Activity and Data Fusion of Hyperspectral Images

Research on nondestructive detection of sweet-waxy corn seed varieties and mildew based on stacked ensemble learning and hyperspectral feature fusion technology

The variety and quality of corn seeds are crucial factors affecting crop yield and farmers' economic benefits. This study adopts an innovative method based on a hyperspectral imaging system combined with stacked ensemble learning, aiming to achieve varieties classification and mildew detection of sweet-waxy corn seeds. First, data interference is eliminated by extracting the spectral and texture information of each corn sample and preprocessing the data. Secondly, a stacked ensemble learning model (Stack) was constructed by stacking base models and meta-models. Its results were compared with those of the base models, including Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Random Forest (RF).Finally, the overall performance of the model is improved through the information fusion strategy of hyperspectral data and texture information. The research results indicate that the GBDT-Stack model, which integrates spectral and texture data, demonstrated optimal performance in the comprehensive classification of both corn seed varieties and mold detection. On the test set, the model achieved an average prediction accuracy of 97.01%. Specifically, the model achieved a test set accuracy ranging from 94.49% to 97.58% for different corn seed varieties and a test set accuracy of 98.89% for mildew detection. This model not only classifies corn seed varieties but also accurately detects mildew, demonstrating its wide applicability. The method has huge potential and is of great significance for improving crop yield and quality.

Detection of Maize Mold Based on a Nanocomposite Colorimetric Sensor Array under Different Substrates

This study developed a novel nanocomposite colorimetric sensor array (CSA) to distinguish between fresh and moldy maize. First, the headspace solid-phase microextraction gas chromatography-mass spectrometry (HS-SPME-GC/MS) method was used to analyze volatile organic compounds (VOCs) in fresh and moldy maize samples. Then, principal component analysis and orthogonal partial least-squares discriminant analysis (OPLS-DA) were used to identify 2-methylbutyric acid and undecane as key VOCs associated with moldy maize. Furthermore, colorimetric sensitive dyes modified with different nanoparticles were employed to enhance the dye properties used in the nanocomposite CSA analysis of key VOCs. This study focused on synthesizing four types of nanoparticles: polystyrene acrylic (PSA), porous silica nanospheres (PSNs), zeolitic imidazolate framework-8 (ZIF-8), and ZIF-8 after etching. Additionally, three types of substrates, qualitative filter paper, polyvinylidene fluoride film, and thin-layer chromatography silica gel, were comparatively used to fabricate nanocomposite CSA combining with linear discriminant analysis (LDA) and K-nearest neighbor (KNN) models for real sample detection. All moldy maize samples were correctly identified and prepared to characterize the properties of the CSA. Through initial testing and nanoenhancement of the chosen dyes, four nanocomposite colorimetric sensitive dyes were confirmed. The accuracy rates for LDA and KNN models in this study reached 100%. This work shows great potential for grain quality control using CSA methods.

Fast Nondestructive Detection Technology and Equipment for Food Quality and Safety

Fast nondestructive detection technology in food quality and safety evaluation is a powerful support tool that fosters informatization and intelligence in the food industry, characterized by its rapid processing, convenient operation, and seamless online inspection [...].

Non-destructive detection of single-seed viability in maize using hyperspectral imaging technology and multi-scale 3D convolutional neural network

The viability of Zea mays seed plays a critical role in determining the yield of corn. Therefore, developing a fast and non-destructive method is essential for rapid and large-scale seed viability detection and is of great significance for agriculture, breeding, and germplasm preservation. In this study, hyperspectral imaging (HSI) technology was used to obtain images and spectral information of maize seeds with different aging stages. To reduce data input and improve model detection speed while obtaining more stable prediction results, successive projections algorithm (SPA) was used to extract key wavelengths that characterize seed viability, then key wavelength images of maize seed were divided into small blocks with 5 pixels ×5 pixels and fed into a multi-scale 3D convolutional neural network (3DCNN) for further optimizing the discrimination possibility of single-seed viability. The final discriminant result of single-seed viability was determined by comprehensively evaluating the result of all small blocks belonging to the same seed with the voting algorithm. The results showed that the multi-scale 3DCNN model achieved an accuracy of 90.67% for the discrimination of single-seed viability on the test set. Furthermore, an effort to reduce labor and avoid the misclassification caused by human subjective factors, a YOLOv7 model and a Mask R-CNN model were constructed respectively for germination judgment and bud length detection in this study, the result showed that mean average precision (mAP) of YOLOv7 model could reach 99.7%, and the determination coefficient of Mask R-CNN model was 0.98. Overall, this study provided a feasible solution for detecting maize seed viability using HSI technology and multi-scale 3DCNN, which was crucial for large-scale screening of viable seeds. This study provided theoretical support for improving planting quality and crop yield.

Combination of hyperspectral imaging and entropy weight method for the comprehensive assessment of antioxidant enzyme activity in Tan mutton

The antioxidant enzymes play the crucial role in inhibiting mutton spoilage. In this study, visible near-infrared (Vis-NIR) hyperspectral imaging (HSI) combined with entropy weight method (EWM) was developed for the first time to evaluate the antioxidant properties of Tan mutton. The comprehensive index of antioxidant enzymes (AECI) consisting of peroxidase (49.34%), catalase (37.97%) and superoxidase (12.69%) was constructed by the EWM. Partial least squares regression, least squares support vector machine and artificial neural networks (ANN) were developed based on characteristic wavelengths extracted by successful projections algorithm, uninformative variable selection, iteratively retains informative variables (IRIV), regression coefficient and competitive adaptive reweighted sampling (CARS). The textural features (TF) were extracted by the gray level co-occurrence matrix and fused with the spectral data to establish models. Visualization of the changes in antioxidant enzyme activity was constructed from the optimal model. In addition, two-dimensional correlation spectra (2D-COS) with AECI as a perturbation variable was used to identify spectral features, revealing chemical bond changes order under the characteristic peaks at 612-799-473-708-559 nm. The results showed that the IRIV-CARS-TF-ANN model performed the best, with prediction set coefficient of determination (R_P²) of 0.8813, which improved 2.12%, 1.11% and 2.77% over the R_P² of full band, IRIV and IRIV-CARS, respectively. It was suggested that fusion data of HSI may effectively predict the activity of antioxidant enzymes in Tan mutton.