Mung bean seeds are very important in agricultural production and food processing, but due to their variety and similar appearance, traditional classification methods are challenging, to address this problem this study proposes a deep learning-based approach. In this study, based on the deep learning model MobileNetV2, a DMS block is proposed for mung bean seeds, and by introducing the ECA block and Mish activation function, a high-precision network model, i.e., HPMobileNet, is proposed, which is explored to be applied in the field of image recognition for the fast and accurate classification of different varieties of mung bean seeds. In this study, eight different varieties of mung bean seeds were collected and a total of 34,890 images were obtained by threshold segmentation and image enhancement techniques. HPMobileNet was used as the main network model, and by training and fine-tuning on a large-scale mung bean seed image dataset, efficient feature extraction classification and recognition capabilities were achieved. The experimental results show that HPMobileNet exhibits excellent performance in the mung bean seed grain classification task, with the accuracy improving from 87.40% to 94.01% on the test set, and compared with other classical network models, the results show that HPMobileNet achieves the best results. In addition, this study analyzes the impact of the learning rate dynamic adjustment strategy on the model and explores the potential for further optimization and application in the future. Therefore, this study provides a useful reference and empirical basis for the development of mung bean seed classification and smart agriculture technology.

Introduction: The diversity of edible fungus species and the extent of mycological knowledge pose significant challenges to the research, cultivation, and popularization of edible fungus. To tackle this challenge, there is an urgent need for a rapid and accurate method of acquiring relevant information. The emergence of question and answer (Q&A) systems has the potential to solve this problem. Named entity recognition (NER) provides the basis for building an intelligent Q&A system for edible fungus. In the field of edible fungus, there is a lack of a publicly available Chinese corpus suitable for use in NER, and conventional methods struggle to capture long-distance dependencies in the NER process.Methods: This paper describes the establishment of a Chinese corpus in the field of edible fungus and introduces an NER method for edible fungus information based on XLNet and conditional random fields (CRFs). Our approach combines an iterated dilated convolutional neural network (IDCNN) with a CRF. First, leveraging the XLNet model as the foundation, an IDCNN layer is introduced. This layer addresses the limited capacity to capture features across utterances by extending the receptive field of the convolutional kernel. The output of the IDCNN layer is input to the CRF layer, which mitigates any labeling logic errors, resulting in the globally optimal labels for the NER task relating to edible fungus.Results: Experimental results show that the precision achieved by the proposed model reaches 0.971, with a recall of 0.986 and an F1-score of 0.979.Discussion: The proposed model outperforms existing approaches in terms of these evaluation metrics, effectively recognizing entities related to edible fungus information and offering methodological support for the construction of knowledge graphs.

Seed vigor directly affects emergence rate, early emergence capacity, and seedling uniformity in ginseng. This study integrated pre-sowing laser treatment with hyperspectral prediction for rapid evaluation of ginseng seed vigor. Cracked-stage Mountain Cultivated Ginseng Seeds and American Ginseng Seeds were treated with four semiconductor laser conditions, including red light, blue light, red–blue 3:1, and red–blue 6:1, for 5, 15, and 30 min. Emergence rate, emergence energy, and emergence index were evaluated, and 350–2500 nm hyperspectral reflectance data were collected. Different preprocessing, feature selection, and machine learning methods were compared to construct an optimized support vector regression model for emergence rate prediction. The results showed that laser effects were seed-type-specific and parameter-dependent. Mountain Cultivated Ginseng Seeds responded strongly, with 5 min blue light treatment producing the best performance, achieving a 100.0% emergence rate, 40.4 percentage points higher than the control, with significantly higher emergence energy and emergence index. In American Ginseng Seeds, no treatment differed significantly from the control, although the 30 min red light treatment showed the highest emergence rate trend. Savitzky–Golay smoothing combined with the second derivative was the optimal preprocessing method. The Caterpillar Fungus Optimizer-based support vector regression (CFO-SVR) joint optimization model achieved the best prediction performance, with ${\mathrm{R}}_{\mathrm{p}}^2$ of 0.9517, ${\mathrm{R}\mathrm{M}\mathrm{S}\mathrm{E}}_{\mathrm{P}}$ of 2.4766, and ${\mathrm{M}\mathrm{A}\mathrm{E}}_{\mathrm{P}}$ of 1.0730. These results provide a feasible technical reference for pre-sowing treatment of ginseng seeds and rapid, non-destructive evaluation of emergence vigor.