The rapid detection of chestnut quality is a critical aspect of chestnut processing. However, traditional imaging methods pose a challenge for chestnut-quality detection due to the absence of visible epidermis symptoms. This study aims to develop a quick and efficient detection method using hyperspectral imaging (HSI, 935–1720 nm) and deep learning modeling for qualitative and quantitative identification of chestnut quality. Firstly, we used principal component analysis (PCA) to visualize the qualitative analysis of chestnut quality, followed by the application of three pre-processing methods to the spectra. To compare the accuracy of different models for chestnut-quality detection, traditional machine learning models and deep learning models were constructed. Results showed that deep learning models were more accurate, with FD-LSTM achieving the highest accuracy of 99.72%. Moreover, the study identified important wavelengths for chestnut-quality detection at around 1000, 1400 and 1600 nm, to improve the efficiency of the model. The FD-UVE-CNN model achieved the highest accuracy of 97.33% after incorporating the important wavelength identification process. By using the important wavelengths as input for the deep learning network model, recognition time decreased on average by 39 s. After a comprehensive analysis, FD-UVE-CNN was deter-mined to be the most effective model for chestnut-quality detection. This study suggests that deep learning combined with HSI has potential for chestnut-quality detection, and the results are encouraging.

Accurate identification of rice diseases is crucial for improving rice yield and ensuring food security. In this study, we constructed an image dataset containing six classes of rice diseases captured under real field conditions to address challenges such as complex backgrounds, varying lighting, and symptom similarities. Based on the MobileViT-XXS architecture, we proposed an enhanced model named MobileViT-DAP, which integrates Channel Attention (CA), Efficient Channel Attention (ECA), and PoolFormer blocks to achieve precise classification of rice diseases. The experimental results demonstrated that the improved model achieved superior performance with 0.75 M Params and 0.23 G FLOPs, ensuring computational efficiency while maintaining high classification accuracy. On the testing set, the model achieved an accuracy of 99.61%, a precision of 99.64%, a recall of 99.59%, and a specificity of 99.92%. Compared to traditional lightweight models, MobileViT-DAP showed significant improvements in model complexity, computational efficiency, and classification performance, effectively balancing lightweight design with high accuracy. Furthermore, visualization analysis confirmed that the model’s decision-making process primarily relies on lesion-related features, enhancing its interpretability and reliability. This study provides a novel perspective for optimizing plant disease recognition tasks and contributes to improving plant protection strategies, offering a solution for accurate and efficient disease monitoring in agricultural applications.

The cold storage time of salmon has a significant impact on its freshness, which is an important factor for consumers to evaluate the quality of salmon. The efficient, accurate, and convenient protocol is urgent to appraise the freshness for quality checking. In this paper, the ability of visible/near-infrared (VIS/NIR) spectroscopy was evaluated to predict the cold storage time of salmon meat and skin, which were stored at low-temperature box for 0~12 days. Meanwhile, a double-layer stacked denoising autoencoder neural network (SDAE-NN) algorithm was introduced to establish the prediction model without spectral pre-preprocessing. The results showed that, compared with the common methods such as partial least squares regression (PLSR) and back propagation neural network (BP-NN), the SDAE-NN method had a better performance due to its high efficiency in decreasing noise and optimizing the initial weights. The determination coefficient of test sets (R²_test) and root mean square error of test sets (RMSEP) have been calculated based on SDAE-NN, for the salmon meat (skin), the R²_test can reach 0.98 (0.92), and the RMSEP can reach 0.93 (1.75), respectively. It is highlighted that the algorithm is efficient and accurate and that the salmon meat would be more suitable for predicting freshness than the salmon skin. VIS/NIR spectroscopy combined with the SDAE-NN algorithm can be widely used to predict the freshness of various agricultural products.