Search

Tomato blight significantly threatened tomato yield and quality, making precise disease detection essential for modern agricultural practices. Traditional segmentation models often struggle with over-segmentation and missed segmentation, particularly in complex backgrounds and with diverse lesion morphologies. To address these challenges, we proposed Unet with Vision Mamba and ConvNeXt (VMC-Unet), an asymmetric segmentation model for quantitative analysis of tomato blight. Built on the Unet framework, VMC-Unet integrated a parallel feature-aware backbone combining ConvNeXt, Vision Mamba, and Atrous Spatial Pyramid Pooling (ASPP) modules to enhance spatial feature focusing and multi-scale information processing. During decoding, Vision Mamba was hierarchically embedded to accurately recover complex lesion morphologies through refined feature processing and efficient up-sampling. A joint loss function was designed to optimize the model’s performance. Extensive experiments on both tomato epidemic and public datasets demonstrated VMC-Unet superior performance, achieving 97.82% pixel accuracy, 87.94% F1 score, and 86.75% mIoU. These results surpassed those of classical segmentation models, underscoring the effectiveness of VMC-Unet in mitigating over-segmentation and under-segmentation while maintaining high segmentation accuracy in complex backgrounds. The consistent performance of the model across various datasets further validated its robustness and generalization potential, highlighting its applicability in broader agricultural settings.

The climatic parameters within greenhouse facilities, such as temperature, humidity, and light, exert significant influence on the growth and yield of crops, particularly seedlings. Therefore, it is crucial to establish an accurate predictive model to monitor and adjust the greenhouse microclimate for optimizing the greenhouse environment to the fullest extent. To precisely forecast the greenhouse microclimate and assess the suitability of nursery environments, this study focuses on greenhouse environmental factors. This study leveraged open-source APIs to acquire meteorological data, integrated a model based on Convolutional Neural Networks (CNN) and Long Short-Term Memory Networks (LSTM), and utilized the sparrow search algorithm to optimize model parameters, consequently developing a time series greenhouse microclimate prediction model. Furthermore, Squeeze-and-Excitation (SE) Networks were employed to enhance the model’s attention mechanism, enabling more accurate predictions of environmental factors within the greenhouse. The predictive results indicated that the optimized model achieved high precision in forecasting the greenhouse microclimate, with average errors of 0.540 °C, 0.936%, and 1.586 W/m2 for temperature, humidity, and solar radiation, respectively. The coefficients of determination (R2) reached 0.940, 0.951, and 0.936 for temperature, humidity, and solar radiation, respectively. In comparison to individual CNN or LSTM models, as well as the back-propagation (BP) neural network, the proposed model demonstrates a significant improvement in predictive accuracy. Moreover, this research was applied to the greenhouse nursery environment, demonstrating that the proposed model significantly enhanced the efficiency of greenhouse seedling cultivation and the quality of seedlings. Our study provided an effective approach for optimizing greenhouse environmental control and nursery environment suitability, contributing significantly to achieving sustainable and efficient agricultural production.

Peanut leaf spot is a worldwide disease whose prevalence poses a major threat to peanut yield and quality, and accurate prediction models are urgently needed for timely disease management. In this study, we proposed a novel peanut leaf spot prediction method based on an improved long short-term memory (LSTM) model and multi-year meteorological data combined with disease survey records. Our method employed a combination of convolutional neural networks (CNNs) and LSTMs to capture spatial–temporal patterns from the data and improve the model’s ability to recognize dynamic features of the disease. In addition, we introduced a Squeeze-and-Excitation (SE) Network attention mechanism module to enhance model performance by focusing on key features. Through several hyper-parameter optimization adjustments, we identified a peanut leaf spot disease condition index prediction model with a learning rate of 0.001, a number of cycles (Epoch) of 800, and an optimizer of Adma. The results showed that the integrated model demonstrated excellent prediction ability, obtaining an RMSE of 0.063 and an R2 of 0.951, which reduced the RMSE by 0.253 and 0.204, and raised the R2 by 0.155 and 0.122, respectively, compared to the single CNN and LSTM. Predicting the occurrence and severity of peanut leaf spot disease based on the meteorological conditions and neural networks is feasible and valuable to help growers make accurate management decisions and reduce disease impacts through optimal fungicide application timing.

Grapes are a globally popular fruit, with grape cultivation worldwide being second only to citrus. This article focuses on the low efficiency and accuracy of traditional manual grading of red grape external appearance and proposes a small-sample red grape external appearance grading model based on transfer learning with convolutional neural networks (CNNs). In the naturally growing vineyards, 195,120,135 samples of Grade I, Grade II, and Grade III red grapes were collected using a Canon EOS 550D camera, and a data set of 1800 samples was obtained using data enhancement technology. Then, the CNN transfer learning method was used to transfer the pre-trained AlexNet, VGG16, GoogleNet, InceptionV3, and ResNet50 network models on the ImageNet image dataset to the red grape image grading task. By comparing the classification performance of the CNN models of these five different network depths with fine-tuning, ResNet50 with a learning rate of 0.001 and a loop number of 10 was determined to be the best feature extractor for red grape images. Moreover, given the small number of red grape image samples in this study, different convolutional layer features output by the ResNet50 feature extractor were analyzed layer by layer to determine the effect of deep features extracted by each convolutional layer on Support Vector Machine (SVM) classification performance. This analysis helped to obtain a ResNet50 + SVM red grape external appearance grading model based on the optimal ResNet50 feature extraction strategy. Experimental data showed that the classification model constructed using the feature parameters extracted from the 10th node of the ResNet50 network achieved an accuracy rate of 95.08% for red grape grading. These research results provide a reference for the online grading of red grape clusters based on external appearance quality and have certain guiding significance for the quality and efficiency of grape industry circulation and production.

The push for greater urban sustainability has increased the urgency of the search for noise mitigation solutions that allow for natural ventilation into buildings. Although a viable active noise control (ANC) solution with up to 10 dB of global attenuation between 100 Hz and 1000 Hz was previously developed for an open window, it had limited low-frequency performance below 300 Hz, owing to the small loudspeakers used. To improve the low-frequency attenuation, four passive radiator-based speakers were affixed around the opening of a top-hung ventilation window. The active control performance between 100 Hz and 700 Hz on a single top-hung window in a full-sized mock-up apartment room was examined. Active attenuation came close to the performance of the passive insulation provided by fully closing the window for expressway traffic and motorbike passing noise types. For a jet aircraft flyby, the performance of active attenuation with the window fully opened was similar to that of passive insulation with fully closed windows. In the case of low-frequency compressor noise, active attenuation’s performance was significantly better than the passive insulation. Overall, between 8 dB and 12 dB of active attenuation was achieved directly in front of the window opening, and up to 10.5 dB of attenuation was achieved across the entire room.

Active noise control (ANC) is a re-emerging technique to mitigate noise pollution. To reduce the noise power in large spaces, multiple channels are usually required, which complicates the implementation of ANC systems. In this paper, we separate the multichannel ANC problem into two subproblems, where the subproblem of computing the control filter is usually an underdetermined problem. Therefore, we could leverage the underdetermined system to simplify the ANC system without degrading the noise reduction performance. For a single incidence, we compare the conventional fully-coupled (pseudoinverse) multichannel control with the colocated (diagonal) control method and find that they can achieve equivalent performance, but the colocated control method is less computationally intensive. Furthermore, the underdetermined system presents an opportunity to control noise from multiple incidences with one common fixed filter. Both the full-rank and the overdetermined optimal control filters are realized. The performance of these control methods was analyzed numerically with the Finite Element Method (FEM) and the results validate the feasibility of the full-rank and overdetermined optimal control methods, where the latter could even offer more robust performance in more complex noise scenarios.

Extracting accurate values for relevant unknown parameters of solar cell models is vital and necessary for performance analysis of a photovoltaic (PV) system. This paper presents an effective application of a young, yet efficient metaheuristic, named the symbiotic organisms search (SOS) algorithm, for the parameter extraction of solar cell models. SOS, inspired by the symbiotic interaction ways employed by organisms to improve their overall competitiveness in the ecosystem, possesses some noticeable merits such as being free from tuning algorithm-specific parameters, good equilibrium between exploration and exploitation, and being easy to implement. Three test cases including the single diode model, double diode model, and PV module model are served to validate the effectiveness of SOS. On one hand, the performance of SOS is evaluated by five state-of-the-art algorithms. On the other hand, it is also compared with some well-designed parameter extraction methods. Experimental results in terms of the final solution quality, convergence rate, robustness, and statistics fully indicate that SOS is very effective and competitive.

The potential of utilizing doubly-fed induction generator (DFIG)-based wind farms to improve power system damping performance and to enhance small signal stability has been proposed by many researchers. However, the simultaneous coordinated tuning of a DFIG power oscillation damper (POD) with other damping controllers is rarely involved. A simultaneous robust coordinated multiple damping controller design strategy for a power system incorporating power system stabilizer (PSS), static var compensator (SVC) POD and DFIG POD is presented in this paper. This coordinated damping control design strategy is addressed as an eigenvalue-based optimization problem to increase the damping ratios of oscillation modes. Both local and inter-area electromechanical oscillation modes are intended in the optimization design process. Wide-area phasor measurement unit (PMU) signals, selected by the joint modal controllability/ observability index, are utilized as SVC and DFIG POD feedback modulation signals to suppress inter-area oscillation modes. The robustness of the proposed coordinated design strategy is achieved by simultaneously considering multiple power flow situations and operating conditions. The recently proposed Grey Wolf optimizer (GWO) algorithm is adopted to efficiently optimize the parameter values of multiple damping controllers. The feasibility and effectiveness of the proposed coordinated design strategy are demonstrated through frequency-domain eigenvalue analysis and nonlinear time-domain simulation studies in two modified benchmark test systems. Moreover, the dynamic response simulation results also validate the robustness of the recommended coordinated multiple damping controllers under various system operating conditions.