Search Results (533)

To tackle the challenges of detecting complex cracks on large stone slabs with noisy textures, this paper presents the first domain-optimized framework for stone slab cracks, an improved semantic segmentation model (YOLOv8-Seg) synergistically integrating U-NetV2, DSConv, and DySample. The network uses the lightweight U-NetV2 backbone combined with dynamic feature recalibration and multi-scale refinement to better capture fine crack details. The dynamic up-sampling module (DySample) helps to adaptively reconstruct curved boundaries. In addition, the dynamic snake convolution head (DSConv) improves the model’s ability to follow irregular crack shapes. Experiments on the custom-built ST stone crack dataset show that YOLOv8-Seg achieves an mAP@0.5 of 0.856 and an mAP@0.5–0.95 of 0.479. The model also reaches a mean intersection over union (MIoU) of 79.17%, outperforming both baseline and mainstream segmentation models. Ablation studies confirm the value of each module. Comparative tests and industrial validation demonstrate stable performance across different stone materials and textures and a 30% false-positive reduction in real production environments. Overall, YOLOv8-Seg greatly improves segmentation accuracy and robustness in industrial crack detection on natural stone slabs, offering a strong solution for intelligent visual inspection in real-world applications. Full article

Bruising in ‘Korla’ pears represents a prevalent phenomenon that leads to progressive fruit decay and substantial economic losses. The detection of early-stage bruising proves challenging due to the absence of visible external characteristics, and existing deep learning models have limitations in weak feature extraction under complex optical interference. To address the postharvest latent damage detection challenges in ‘Korla’ pears, this study proposes a collaborative detection framework integrating structured-illumination reflectance imaging (SIRI) with multi-order gated attention mechanisms. Initially, an SIRI optical system was constructed, employing 150 cycles·m⁻¹ spatial frequency modulation and a three-phase demodulation algorithm to extract subtle interference signal variations, thereby generating RT (Relative Transmission) images with significantly enhanced contrast in subsurface damage regions. To improve the detection accuracy of latent damage areas, the MOGA-UNet model was developed with three key innovations: 1. Integrate the lightweight VGG16 encoder structure into the feature extraction network to improve computational efficiency while retaining details. 2. Add a multi-order gated aggregation module at the end of the encoder to realize the fusion of features at different scales through a special convolution method. 3. Embed the channel attention mechanism in the decoding stage to dynamically enhance the weight of feature channels related to damage. Experimental results demonstrate that the proposed model achieves 94.38% mean Intersection over Union (mIoU) and 97.02% Dice coefficient on RT images, outperforming the baseline UNet model by 2.80% with superior segmentation accuracy and boundary localization capabilities compared with mainstream models. This approach provides an efficient and reliable technical solution for intelligent postharvest agricultural product sorting. Full article

This review comprehensively examines the application of deep learning technologies across the entire soybean production chain, encompassing areas such as disease and pest identification, weed detection, crop phenotype recognition, yield prediction, and intelligent operations. By systematically analyzing mainstream deep learning models, optimization strategies (e.g., model lightweighting, transfer learning), and sensor data fusion techniques, the review identifies their roles and performances in complex agricultural environments. It also highlights key challenges including data quality limitations, difficulties in real-world deployment, and the lack of standardized evaluation benchmarks. In response, promising directions such as reinforcement learning, self-supervised learning, interpretable AI, and multi-source data fusion are proposed. Specifically for soybean automation, future advancements are expected in areas such as high-precision disease and weed localization, real-time decision-making for variable-rate spraying and harvesting, and the integration of deep learning with robotics and edge computing to enable autonomous field operations. This review provides valuable insights and future prospects for promoting intelligent, efficient, and sustainable development in soybean production through deep learning. Full article

The accurate detection of surface defects in bamboo is critical to maintaining product quality. Traditional inspection methods rely heavily on manual labor, making the manufacturing process labor-intensive and error-prone. To overcome these limitations, TEB-YOLO is introduced in this paper, a lightweight and efficient defect detection model based on YOLOv5s. Firstly, EfficientViT replaces the original YOLOv5s backbone, reducing the computational cost while improving feature extraction. Secondly, BiFPN is adopted in place of PANet to enhance multi-scale feature fusion and preserve detailed information. Thirdly, an Efficient Local Attention (ELA) mechanism is embedded in the backbone to strengthen local feature representation. Lastly, the original CIoU loss is replaced with EIoU loss to enhance localization precision. The proposed model achieves a precision of 91.7% with only 10.5 million parameters, marking a 5.4% accuracy improvement and a 22.9% reduction in parameters compared to YOLOv5s. Compared with other mainstream models including YOLOv5n, YOLOv7, YOLOv8n, YOLOv9t, and YOLOv9s, TEB-YOLO achieves precision improvements of 11.8%, 1.66%, 2.0%, 2.8%, and 1.1%, respectively. The experiment results show that TEB-YOLO significantly improves detection precision and model lightweighting, offering a practical and effective solution for real-time bamboo surface defect detection. Full article

Frequent corn leaf diseases and pests pose serious threats to agricultural production. Traditional manual detection methods suffer from significant limitations in both performance and efficiency. To address this, the present paper proposes a novel biotic condition screening (BCS) model for the detection of corn leaf diseases and pests, called BCS_YOLO, based on the You Only Look Once version 11n (YOLOv11n). The proposed model enables accurate detection and classification of various corn leaf pathologies and pest infestations under challenging agricultural field conditions. It achieves this thanks to three key newly designed modules—a Self-Perception Coordinated Global Attention (SPCGA) module, a High/Low-Frequency Feature Enhancement (HLFFE) module, and a Local Attention Enhancement (LAE) module. The SPCGA module improves the model’s ability to perceive fine-grained targets by fusing multiple attention mechanisms. The HLFFE module adopts a frequency domain separation strategy to strengthen edge delineation and structural detail representation in affected areas. The LAE module effectively improves the model’s discrimination ability between targets and backgrounds through local importance calculation and intensity adjustment mechanisms. Conducted experiments show that BCS_YOLO achieves 78.4%, 73.7%, 76.0%, and 82.0% in $precision$, recall, $F1score$, and $mAP@50$, respectively, representing corresponding improvements of 3.0%, 3.3%, 3.2%, and 4.6% compared to the baseline model (YOLOv11n), while also outperforming the mainstream object detection models. In summary, the proposed BCS_YOLO model provides a practical and scalable solution for efficient detection of corn leaf diseases and pests in complex smart-agriculture scenarios, demonstrating significant theoretical and application value. Full article

Magnetic tiles are an important component of permanent magnet motors, and the quality of magnetic tiles directly affects the performance and service life of a motor. It is necessary to perform defect detection on magnetic tiles in industrial production and remove those with defects. The YOLOv8-AHF algorithm is proposed to improve the ability of network feature information extraction and solve the problem of missed detection or poor detection results in surface defect detection due to the small volume of permanent magnet motor tiles, which reduces the deviation between the predicted box and the true box simultaneously. Firstly, a hybrid module of a combination of atrous convolution and depthwise separable convolution (ADConv) is introduced in the backbone of the model to capture global and local features in magnet tile detection images. In the neck section, a hybrid attention module (HAM) is introduced to focus on the regions of interest in the magnetic tile surface defect images, which improves the ability of information transmission and fusion. The Focal-Enhanced Intersection over Union loss function (Focal-EIoU) is optimized to effectively achieve localization. We conducted comparative experiments, ablation experiments, and corresponding generalization experiments on the magnetic tile surface defect dataset. The experimental results show that the evaluation metrics of YOLOv8-AHF surpass mainstream single-stage object detection algorithms. Compared to the You Only Look Once version 8 (YOLOv8) algorithm, the performance of the YOLOv8-AHF algorithm was improved by 5.9%, 4.1%, 5%, 5%, and 5.8% in terms of mAP@0.5, mAP@0.5:0.95, F1-Score, precision, and recall, respectively. This algorithm achieved significant performance improvement in the task of detecting surface defects on magnetic tiles. Full article

To ensure the safety of nuclear power production, nuclear power plants deploy numerous sensors to monitor various physical indicators during production, enabling the early detection of anomalies. Efficient anomaly detection relies on complete sensor data. However, compared to conventional energy sources, the extreme physical environment of nuclear power plants is more likely to negatively impact the normal operation of sensors, compromising the integrity of the collected data. To address this issue, we propose an anomaly detection method for nuclear power data: Neural Normal Stochastic Process (NNSP). This method does not require imputing missing sensor data. Instead, it directly reads incomplete monitoring data through a sequentialization structure and encodes it as continuous latent representations in a neural network. This approach avoids additional “processing” of the raw data. Moreover, the continuity of these representations allows the decoder to specify supervisory signals at time points where data is missing or at future time points, thereby training the model to learn latent anomaly patterns in incomplete nuclear power monitoring data. Experimental results demonstrate that our model outperforms five mainstream baseline methods—ARMA, Isolation Forest, LSTM-AD, VAE, and NeutraL AD—in anomaly detection tasks on incomplete time series. On the Power Generation System (PGS) dataset with a 15% missing rate, our model achieves an F1 score of 83.72%, surpassing all baseline methods and maintaining strong performance across multiple industrial subsystems. Full article

Accurate detection of cotton pests and diseases is essential for agricultural productivity yet remains challenging due to complex field environments, the small size of pests and diseases, and significant occlusions. To address the challenges presented by these factors, a novel cotton disease and pest detection method is proposed. This method builds upon the YOLOv8 baseline model and incorporates a Multi-Scale Sliding Window Attention Module (MSFE) within the backbone architecture to enhance feature extraction capabilities specifically for small targets. Furthermore, a Depth-Separable Dilated Convolution Module (C2f-DWR) is designed to replace the existing C2f module in the neck of the network. By employing varying dilation rates, this modification effectively expands the receptive field and alleviates the loss of detailed information associated with the downsampling processes. In addition, a Multi-Head Attention Detection Head (MultiSEAMDetect) is introduced to supplant the original detection head. This new head utilizes diverse patch sizes alongside adaptive average pooling mechanisms, thereby enabling the model to adjust its responses in accordance with varying contextual scenarios, which significantly enhances its ability to manage occlusion during detection. For the purpose of experimental validation, a dedicated dataset for cotton disease and pest detection was developed. In this dataset, the improved model’s mAP50 and mAP50:95 increased from 73.4% and 46.2% to 77.2% and 48.6%, respectively, compared to the original YOLOv8 algorithm. Validation on two Kaggle datasets showed that mAP50 rose from 92.1% and 97.6% to 93.2% and 97.9%, respectively. Meanwhile, mAP50:95 improved from 86% and 92.5% to 87.1% and 93.5%. These findings provide compelling evidence of the superiority of the proposed algorithm. Compared to other advanced mainstream algorithms, it exhibits higher accuracy and recall, indicating that the improved algorithm performs better in the task of cotton pest and disease detection. Full article

As the mainstream financial modality in the digital economy era, digital finance drives industrial digitization and green transformation through capital and technological support, enabling governments to advance environmental governance with greater precision, efficiency, and sustainability. Utilizing 2012–2023 panel data from 31 Chinese provinces, this study innovatively constructs a multidimensional panel data model for the quantitative analysis of the overall impact, heterogeneous effects, and spatial spillover effects of digital finance on government environmental governance. It further examines the mediating effect and the threshold effects of new quality productive forces, and the moderated mediation effects of green technological innovation and industrial collaborative agglomeration. In this study, (1) digital finance significantly drives government environmental governance, and this finding exhibits robustness; (2) digital finance exerts heterogeneous impact on government environmental governance, with more pronounced effects in eastern and sub-developed regions; (3) digital finance generates positive spatial spillover effects on government environmental governance; (4) new quality productive forces positively mediate the relationship between digital finance and government environmental governance; (5) green technological innovation exhibits dual moderation characteristics, moderating both “digital finance → new quality productive forces” and “new quality productive forces → government environmental governance,” while industrial collaborative agglomeration shows single moderation, specifically moderating “new quality productive forces → government environmental governance”; (6) the impact of digital finance on government environmental governance presents a nonlinear feature of “increasing marginal returns.” On these accounts, this study proposes targeted recommendations from six dimensions. Full article

Technological progress in agriculture plays an essential role in enhancing productivity, sustainability, and resilience. This study conducts a bibliometric analysis of the concept of technological progress in agriculture using data extracted from the Web of Science database for the period 1979–2025. The main aim is to identify emerging trends, the structure of collaborative networks, and the influence of research on the development of smart agriculture. The methodology is based on a co-occurrence analysis of keywords, co-author networks, and institutional and international collaborations, providing a detailed insight into the dynamics of research in this field. The results show an accelerated growth of studies on the digitization of agriculture, with a particular focus on technologies such as artificial intelligence, precision agriculture, the Internet of Things, and agricultural process automation. According to the bibliometric analysis, China accounts for the largest share of publications in this field, followed by the United States and Australia. These countries also exhibit high levels of centrality in international collaboration networks, indicating their pivotal role in knowledge production and dissemination. Europe shows a fragmented but active collaborative network, while emerging countries are starting to strengthen their position through strategic partnerships. The findings suggest the need for transdisciplinary collaborations in order to mainstream technological progress in agriculture, emphasizing the importance of policies to support technology transfer and sustainable innovation. Full article

Tobacco control policies have aimed to reduce the global prevalence of smoking. Unfortunately, the recent survey data shows that about 24% of Europeans still smoke. Although combustible cigarettes remain the most used tobacco product, the tendency made evident in the prevalence of smoking-alternative nicotine-containing products increases. Studies that can objectively assess the long-term health effects of the latter products are lacking, so assessing toxic substances associated with smoking-alternative products and comparing them to substances from combustible cigarettes could inform future public health efforts. The manufacturers of these alternative products claim that the use of alternatives to combustible cigarettes reduces exposure to toxic compounds, but the reality is unclear. This study compares the concentrations of toxic substances in generated aerosols and performs calculations based on mainstream cigarette smoke and aerosols from smoking-alternative products. It summarizes the amounts of harmful and potentially harmful constituents per single puff. Alternative smoking products are undoubtedly harmful to non-smokers. Still, based on the analysis of the latest independent studies’ empirical data, the concentrations of inhaled HPHCs using heated tobacco products or e-cigarettes are reduced up to 91–98%, respectively; therefore, for those who cannot quit, these could provide a less harmful alternative. However, more well-designed studies of alternative product emissions are needed, including an analysis of the compounds that are not present in conventional tobacco products (e.g., thermal degradation products of propylene glycol, glycerol, or flavorings) to evaluate possible future health effects objectively. Full article

With the advancement of logistics technology, Automated Guided Vehicles (AGVs) have been widely adopted in manufacturing enterprises due to their high flexibility and stability, particularly in flexible and discrete manufacturing domains such as tire production and electronic assembly. However, existing studies seldom systematically consider practical constraints such as limited AGV transport resources, AGV charging requirements, and charging station capacity limitations. To address this gap, this paper proposes a flexible job shop production-logistics collaborative scheduling model that incorporates transport and charging constraints, aiming to minimize the maximum makespan. To solve this problem, an improved PPO algorithm—CRGPPO-TKL—has been developed, which integrates candidate probability ratio calculations and a dynamic clipping mechanism based on target KL divergence to enhance the exploration capability and stability during policy updates. Experimental results demonstrate that the proposed method outperforms composite dispatching rules and mainstream DRL methods across multiple scheduling scenarios, achieving an average improvement of 8.2% and 10.5% in makespan, respectively. Finally, sensitivity analysis verifies the robustness of the proposed method with respect to parameter combinations. Full article

This study investigated the spatiotemporal dynamics and driving forces governing water quality variationsin the Midstream of the Chishui River, a pivotal area for China’s iconic liquor production, focused on its mainstream and tributaries. Through monthly intensive sampling and monitoring, combined with water quality assessment methods (single-factor evaluation and the Nemerow index method) and hydrochemical analysis, the spatiotemporal patterns and driving mechanisms of the water environment were systematically analyzed. The key findings reveal three distinct patterns. 1. Spatial heterogeneity: There is a notable difference in water quality between the main stream and tributaries, with the main stream exhibiting better water quality, while some tributaries show poorer water quality during certain months. 2. Seasonal ion variability: The proportions of Mg²⁺, Cl⁻, and SO₃²⁻ peaked during winter and spring, while concentrations of cations and anions decreased in summer and autumn. 3. Driving factors: The spatial disparity between mainstream and tributary water quality was primarily controlled by anthropogenic activities, whereas temporal variations in ionic composition were jointly influenced by basin lithology and seasonal environmental-climatic changes. Enhanced tributary management and climate adaptive monitoring strategies are proposed to safeguard water resources critical for both ecosystem integrity and specialty beverage manufacturing. Full article

With the rapid development of e-commerce and the logistics industry, the importance of logistics packaging defect detection as a key link in product quality control is becoming increasingly prominent. However, existing target detection models often face the problems of difficulty in improving detection accuracy and high model complexity when dealing with small-scale targets in logistics packaging. For this reason, an improved target detection model, DScanNet, is proposed in this paper. To address the problem that the model’s detailed feature extraction for small target defects is not sufficient and thus leads to low detection accuracy, the MEFE module, the local feature extraction module (LFEM Block), and the PCR module of the multi-scale convolution and feature enhancement strategy are proposed to enhance the model’s capability of capturing defective features and focusing on specific features, and to improve the detection accuracy. To address the problem of excessive model complexity, a Mamba module incorporating a channel attention mechanism is proposed to optimize the model via its linear complexity. Through experiments on its own dataset, BIGC-LP, DScanNet achieves a high accuracy of 96.8% on the defect detection task compared with the current mainstream detection algorithms, while the number of model parameters and the computational volume are effectively controlled. Full article

Effective stored-grain insect pest detection is crucial in grain storage management to prevent economic losses and ensure food security throughout production and supply chains. Existing detection methods suffer from issues such as high labor costs, environmental interference, high equipment costs, and inconsistent performance. To address these limitations, we proposed PDA-YOLO, an improved stored-grain insect pest detection algorithm based on YOLO11n which integrates three key modules: PoolFormer_C3k2 (PF_C3k2) for efficient local feature extraction, Attention-based Intra-Scale Feature Interaction (AIFI) for enhanced global context awareness, and Dynamic Multi-scale Aware Edge (DMAE) for precise boundary detection of small targets. Trained and tested on 6200 images covering five common stored-grain insect pests (Lesser Grain Borer, Red Flour Beetle, Indian Meal Moth, Maize Weevil, and Angoumois Grain Moth), PDA-YOLO achieved an mAP@0.5 of 96.6%, mAP@0.5:0.95 of 60.4%, and F1 score of 93.5%, with a computational cost of only 6.9 G and mean detection time of 9.9 ms per image. These results demonstrate the advantages over mainstream detection algorithms, balancing accuracy, computational efficiency, and real-time performance. PDA-YOLO provides a reference for pest detection in intelligent grain storage management. Full article