Shiitake mushrooms are an important edible fungus, and their nutrient content is related to their quality. With the acceleration of urbanization, there has been a serious loss of population and shortage of labor in rural areas. The problem of harvesting agricultural products after maturity is becoming more and more prominent. In recent years, deep learning techniques have performed well in classification tasks using image data. These techniques can replace the manual labor needed to classify the quality of shiitake mushrooms quickly and accurately. Therefore, in this paper, a MobileNetV3_large deep convolutional network is improved, and a mushroom quality classification model using images with complex backgrounds is proposed. First, captured image data of shiitake mushrooms are divided into three categories based on the appearance characteristics related to shiitake quality. By constructing a hybrid data set, the model’s focus on shiitake mushrooms in images with complex backgrounds is improved. And the constructed data set is expanded using data enhancement methods to improve the generalization ability of the model. The total number of images after expansion is 10,991. Among them, the number of primary mushroom images is 3758, the number of secondary mushroom images is 3678, and the number of tertiary mushroom images is 3555. Subsequently, the SE module in MobileNetV3_large network is improved and processed to enhance the model recognition accuracy while reducing the network size. Finally, PolyFocalLoss and migration learning strategies are introduced to train the model and accelerate model convergence. In this paper, the recognition performance of the improved MobileNetV3_large model is evaluated by using the confusion matrix evaluation tool. It is also compared with other deep convolutional network models such as VGG16, GoogLeNet, ResNet50, MobileNet, ShuffleNet, and EfficientNet using the same experimental conditions. The results show that the improved MobileNetV3_large network has a recognition accuracy of 99.91%, a model size of 11.9 M, and a recognition error rate of 0.09% by the above methods. Compared to the original model, the recognition accuracy of the improved model is increased by 18.81% and the size is reduced by 26.54%. The improved MobileNetV3_large network model in this paper has better comprehensive performance, and it can provide a reference for the development of quality recognition and classification technologies for shiitake mushrooms cultivated in greenhouse environments.

To reveal the impact of cadmium stress on the physiological mechanism of lettuce, simultaneous determination and correlation analyses of chlorophyll content and photosynthetic function were conducted using lettuce seedlings as the research subject. The changes in relative chlorophyll content, rapid chlorophyll fluorescence induction kinetics curve, and related chlorophyll fluorescence parameters of lettuce seedling leaves under cadmium stress were detected and analyzed. Furthermore, a model for estimating relative chlorophyll content was established. The results showed that cadmium stress at 1 mg/kg and 5 mg/kg had a promoting effect on the relative chlorophyll content, while cadmium stress at 10 mg/kg and 20 mg/kg had an inhibitory effect on the relative chlorophyll content. Moreover, with the extension of time, the inhibitory effect became more pronounced. Cadmium stress affects both the donor and acceptor sides of photosystem II in lettuce seedling leaves, damaging the electron transfer chain and reducing energy transfer in the photosynthetic system. It also inhibits water photolysis and decreases electron transfer efficiency, leading to a decline in photosynthesis. However, lettuce seedling leaves can mitigate photosystem II damage caused by cadmium stress through increased thermal dissipation. The model established based on the energy captured by a reaction center for electron transfer can effectively estimate the relative chlorophyll content of leaves. This study demonstrates that chlorophyll fluorescence techniques have great potential in elucidating the physiological mechanism of cadmium stress in lettuce, as well as in achieving synchronized determination and correlation analyses of chlorophyll content and photosynthetic function.

To address the issue of automated apple harvesting in orchards, we propose a YOLOv5-RACF algorithm for identifying apples and calculating apple diameters. This algorithm employs the robot operating dystem (ROS) to control the robot’s locomotion system, Lidar mapping, and navigation, as well as the robotic arm’s posture and grasping operations, achieving automated apple harvesting and placement. The tests were conducted in an actual orchard environment. The algorithm model achieved an average apple detection accuracy (mAP@0.5) of 98.748% and a (mAP@0.5:0.95) of 90.02%. The time to calculate the diameter of one apple was 0.13 s, with a measurement accuracy within an error range of 1–3 mm. The robot takes an average of 9 s to pick an apple and return to the initial pose. These results demonstrate the system’s efficiency and reliability in real agricultural environments.

Olives are a crucial woody oil crop, the harvesting of which predominantly relies on manual labor, which is characterized by high costs, low efficiency, and challenges in ensuring optimal harvesting timing. The development of an automated ripeness-detection system with high recognition accuracy is of paramount importance for advancing automated olive-harvesting technologies. Traditional detection methods are constrained by susceptibility to environmental interference, limited robustness, and inadequate generalization capabilities. Concurrently, existing deep learning-based detection models face issues such as insufficient feature extraction for small targets and difficulties in deployment due to their need for large numbers of parameters. To address these limitations, this study proposes a lightweight algorithm for detection and grading of olive ripeness based on an Improved YOLOv11n framework. The proposed approach employs YOLOv11n as the baseline model, replaces its backbone network with EfficientNet-B0, and integrates the Large-Scale Kernel Attention (LSKA) mechanism and the Bidirectional Feature Pyramid Network (BiFPN). Experimental validation demonstrated that the enhanced model achieved detection accuracy comparable to that of the original model, attaining a mean average precision (mAP) of 0.918. Furthermore, the model size was reduced to 3.7 MB, a 39.3% reduction, while the computational complexity (GFLOPs) was decreased by 2.4 and the inference time per image was reduced by 0.2 ms. The proposed model exhibits significant advantages in terms of lightweight design and improved detection efficiency, demonstrating substantial potential for practical deployment. This study provides a valuable reference for the development of automated olive-harvesting technologies.

The internal temperature of the pigsty has a great impact on the pigs. Keeping the temperature in the pigsty within a certain range is a pressing problem in environmental control. The current pigsty temperature regulation method is based mainly on manual and simple automatic control. There is rarely intelligent control, and such direct methods have problems such as low control accuracy, high energy consumption and untimeliness, which can easily lead to the occurrence of heat stress conditions. Therefore, this paper proposed an improved sparrow search algorithm (ISSA) based on a multi-strategy improvement to optimize the least squares support vector machine (LSSVM) to form a pigsty temperature prediction model. In the optimization process of the sparrow search algorithm (SSA), the initial position of the sparrow population was first generated by using the reverse good point set; secondly, the population number update formula was proposed to automatically adjust the number of discoverers and followers based on the number of iterations to improve the search ability of the algorithm; finally, the adaptive t-distribution was applied to the discoverer position variation to refine the discoverer population and further improve the search ability of the algorithm. Tests were conducted using 23 benchmark functions, and the results showed that ISSA outperformed SSA. By comparing it with the LSSVM models optimized by four standard algorithms, the prediction effect of the ISSA-LSSVM model was tested. In the end, the ISSA-LSSVM temperature prediction model had MSE of 0.0766, MAE of 0.2105, and R² of 0.9818. The results showed that the proposed prediction model had the best prediction performance and prediction accuracy, and can provide accurate data support for the prediction and control of the internal temperature of the pigsty.

To build a DEM model of Cyperus esculentus seed particles, the shape and size of the Cyperus esculentus seed particles were measured and analyzed. The results showed that the dispersity in size had a normal distribution. Additionally, a certain functional relationship between the primary dimension and secondary dimensions was determined. The width of the seed was the primary dimension, and the other secondary dimensions (length and thickness) were calculated based on their relationships with the primary dimension. On this basis, an approach for modeling Cyperus esculentus seed particles based on the multi-sphere (MS) method was proposed. The discrete element analysis models of three varieties of Cyperus esculentus seeds were established with different numbers of filing spheres. Moreover, to obtain more accurate simulation parameters, first, a range of values of the simulation parameters was obtained by the experimental method. Second, the Plackett–Burman (PB) test and the path of steepest ascent method were both adopted to correct and calibrate the simulation parameters, which were difficult to obtain through experiments, and simulation of the direct shear test was used for calibration. All of the methods guaranteed that the selected parameters were reasonable. The test results showed that the static friction coefficient of seed–seed had a significant effect on the simulation results. Finally, piling tests and the bulk density test were used for modeling verification. By comparing the simulated results and experimental results in the piling tests and bulk density test, when the number of filing spheres increased, the simulated results were close to those obtained experimentally. Therefore, the feasibility and validity of the modeling method for Cyperus esculentus seed particles that we proposed and the simulation parameters that were obtained were verified.