Search Results (714)

Rice, a dietary staple for over half of the global population, is highly susceptible to bacterial and fungal diseases such as bacterial blight, brown spot, and leaf smut, which can severely reduce yields. Traditional manual detection is labor-intensive and often results in delayed intervention and excessive chemical use. Although deep learning models like convolutional neural networks (CNNs) achieve high accuracy, their computational demands hinder deployment in resource-limited agricultural settings. We propose MCP-X, an ultra-compact CNN with only 0.21 million parameters for real-time, on-device rice disease classification. MCP-X integrates a shallow encoder, multi-branch expert routing, a bi-level recurrent simulation encoder–decoder (BRSE), an efficient channel attention (ECA) module, and a lightweight classifier. Trained from scratch, MCP-X achieves 98.93% accuracy on PlantVillage and 96.59% on the Rice Disease Detection Dataset, without external pretraining. Mechanistically, expert routing diversifies feature branches, ECA enhances channel-wise signal relevance, and BRSE captures lesion-scale and texture cues—yielding complementary, stage-wise gains confirmed through ablation studies. Despite slightly higher FLOPs than MobileNetV2, MCP-X prioritizes a minimal memory footprint (~1.01 MB) and deployability over raw speed, running at 53.83 FPS (2.42 GFLOPs) on an RTX A5000. It achieves 16.7×, 287×, 420×, and 659× fewer parameters than MobileNetV2, ResNet152V2, ViT-Base, and VGG-16, respectively. When integrated into a multi-resolution ensemble, MCP-X attains 99.85% accuracy, demonstrating exceptional robustness across controlled and field datasets while maintaining efficiency for real-world agricultural applications. Full article

Grinding surface texture is random and feature information is weak, so it is difficult to extract effective features by deep learning network. In addition, the existing deep learning methods mostly adopt a large parameter model in grinding surface roughness recognition task, and the cost of deployment in embedded end is high. In order to solve these problems, a new lightweight network model GE-MobileNet (Ghost-ECA-MobileNetV3) is proposed. Based on MobileNetV3, a feature extractor is introduced into the shallow network part of the model to enhance the ability of the network to extract and suppress the surface texture feature and noise. At the same time, SE (Squeeze-and-Excitation) attention mechanism is replaced with ECA (Efficient Channel) attention mechanism with stronger performance. Finally, the deep network layer is removed to reduce the model size. The experimental results show that the accuracy of GE-MobileNet-based grinding surface roughness measurement model on test set is 94.97%, which is better than other networks. This study proves the effectiveness of the roughness measurement method based on GE-MobileNet. Full article

Accurate and rapid acquisition of soil texture information is crucial to evaluating soil quality, formulating soil and water conservation strategies, and guiding agricultural resource management. Compared with traditional machine learning methods, convolutional neural networks (CNNs) demonstrate superior accuracy in soil texture prediction. To overcome the limitations of existing lightweight models in spectral modeling, such as insufficient single-scale feature representation, limited channel utilization, and branch redundancy, and to meet the demand for lightweight architectures, we propose a novel dynamic feature modeling approach: Multi-scale Routing Attention Network (MSRA-Net). MSRA-Net integrates grouped multi-scale convolutions with an intra-group Efficient Channel Attention (gECA) mechanism, combined with a multi-scale weighting strategy based on a Branch Routing Attention (BRA) mechanism, thereby enhancing inter-channel feature interaction and improving the model’s ability to capture complex spectral patterns. Furthermore, we introduce a multi-task learning variant, MSRA-MT, which employs uncertainty dynamic weighting to balance gradients magnitude across tasks, thereby improving both stability and predictive accuracy. Experimental results on the LUCAS and ICRAF datasets demonstrate that the MSRA-MT model consistently outperforms baseline models in terms of performance and robustness ($RMS{E}_{mean}$ = 9.190 and $RMS{E}_{mean}$ = 8.189 for ICRAF and LUCAS, respectively). Prior knowledge-based soft constraints may hinder optimization by amplifying intrinsic noise, rather than improving learning effectiveness. Full article

The rapid expansion of the goose farming industry creates a growing need for real-time flock counting and individual-level behavior monitoring. To meet this challenge, this study proposes an improved YOLOv8-based model, termed DAEF-YOLO (DualConv-augmented C2f, ADown down-sampling, Efficient Channel Attention integrated into SPPF, and FocalerIoU regression loss), designed for simultaneous recognition of Sanhua goose individuals and their diverse behaviors. The model incorporates three targeted architectural improvements: (1) a C2f-Dual module that enhances multi-scale feature extraction and fusion, (2) ECA embedded in the SPPF module to refine channel interaction with minimal parameter cost and (3) an ADown down-sampling module that preserves cross-channel information continuity while reducing information loss. Additionally, the adoption of the FocalerIoU loss function enhances bounding-box regression accuracy in complex detection scenarios. Experimental results demonstrate that DAEF-YOLO surpasses YOLOv5s, YOLOv7-Tiny, YOLOv7, YOLOv9s, and YOLOv10s in both accuracy and computational efficiency. Compared with YOLOv8s, DAEF-YOLO achieved a 4.56% increase in precision, 6.37% in recall, 5.50% in F1-score, and 4.59% in mAP@0.5, reaching 94.65%, 92.17%, 93.39%, and 96.10%, respectively. A generalizable classification strategy is further introduced by adding a complementary “Other” category to include behaviors beyond predefined classes. This approach ensures complete recognition coverage and demonstrates strong transferability for multi-task detection across species and environments. Ablation studies indicated that mAP@0.5 remained consistent (~96.1%), while mAP@0.5:0.95 improved in the absence of the “Other” class (75.68% vs. 69.82%). Despite this trade-off, incorporating the “Other” category ensures annotation completeness and more robust multi-task behavior recognition under real-world variability. Full article

Tea is a globally important economic crop, and the ability to quickly and accurately identify tea leaf diseases can significantly improve both the yield and quality of tea production. With advances in deep learning, many recent studies have demonstrated that convolutional neural networks are both feasible and effective for identifying tea leaf diseases. In this paper, we propose a modified EfficientNetB0 lightweight convolutional neural network, enhanced with the ECA module, to reliably identify various tea leaf diseases. We used two tea leaf disease datasets from the Kaggle platform: the Tea_Leaf_Disease dataset, which contains six categories, and the teaLeafBD dataset, which includes seven categories. Experimental results show that our method substantially reduces computational costs, the number of parameters, and overall model size. Additionally, it achieves accuracies of 99.49% and 90.73% on these widely used datasets, making it highly suitable for practical deployment on resource-constrained edge devices. Full article

With the development of infrared imaging technology and the integration of intelligent algorithms, the realization of non-contact, dynamic and real-time detection of SF6 gas leakage based on infrared video has been a significant research direction. However, the existing real-time detection algorithms exhibit low accuracy in detecting SF6 leakage and are susceptible to noise, which makes it difficult to meet the actual needs of engineering. To address this problem, this paper proposes a real-time SF6 leakage detection method, VGEC-Net, based on multi-channel fusion and spatiotemporal feature extraction. The proposed method first employs the ViBe-GMM algorithm to extract foreground masks, which are then fused with infrared images to construct a dual-channel input. In the backbone network, a CE-Net structure—integrating CBAM and ECA-Net—is combined with the P3D network to achieve efficient spatiotemporal feature extraction. A Feature Pyramid Network (FPN) and a temporal Transformer module are further integrated to enhance multi-scale feature representation and temporal modeling, thereby significantly improving the detection performance for small-scale targets. Experimental results demonstrate that VGEC-Net achieves a mean average precision (mAP) of 61.7% on the dataset used in this study, with a mAP@50 of 87.3%, which represents a significant improvement over existing methods. These results validate the effectiveness and advancement of the proposed method for infrared video-based gas leakage detection. Furthermore, the model achieves 78.2 frames per second (FPS) during inference, demonstrating good real-time processing capability while maintaining high detection accuracy, exhibiting strong application potential. Full article

In recent years, frequent outbreaks of Enteromorpha disasters in the Yellow Sea have caused substantial economic losses to coastal cities. In order to tackle the challenges of the low detection accuracy and high false negative rate of Enteromorpha detection in complex marine environments, this study proposes an object detection algorithm CEE-YOLOv8, improved from YOLOv8n, and establishes the Enteromorpha dataset. Firstly, this study integrates a C2f-ConvNeXtv2 module into the YOLOv8n Backbone network to augment multi-scale feature extraction capabilities. Secondly, an ECA attention mechanism is incorporated into the Neck network to enhance the perception ability of the model to different sizes of Enteromorpha. Finally, the CIoU loss function is replaced with EIoU to optimize bounding box localization precision. Experiment results on the self-made Enteromorpha dataset show that the improved CEE-YOLOv8 model achieves a 3.2% increase in precision, a 3.3% improvement in recall, and a 4.1% gain in mAP50-95 compared to the benchmark model YOLOv8n. Consequently, the proposed model provides robust technical support for future Enteromorpha monitoring initiatives. Full article

Soil bacterial communities are vital for ecosystem functioning in the humid tropics, yet their response to land-use change remains poorly understood. This knowledge gap is exacerbated by the lack of long-term studies. We employed a space-for-time substitution approach to assess the effects of land-use intensification on soil bacterial communities across a gradient of anthropogenic disturbance in Trinidad. Three sub-watersheds (Arouca = pristine, Maracas = intermediate, Tacarigua = intensive) were selected, each containing adjacent forest, grassland, and agricultural land uses. We combined geophysical soil apparent electrical conductivity (ECa-directed) sampling with 16S rDNA gene amplicon sequencing to characterize bacterial communities and their relationships with soil and landscape properties. Soil properties were the primary determinant of bacterial community structure, explaining 56% of the variation (p < 0.001), with pH, clay content, hygroscopic water, and nutrient availability as key drivers. Bacterial α-diversity differed significantly among sub-watersheds (p < 0.01), with Tacarigua exhibiting lower richness and diversity compared to Arouca and Maracas, but not across land uses. While a core microbiome of ten bacterial families was ubiquitous across land uses, indicating a stable foundational community, land-use intensification significantly altered β-diversity (p < 0.01 among sub-watersheds). Agricultural soils showed the greatest divergence from forest soils (p < 0.05), with a marked decline in key Proteobacterial families (e.g., Xanthomonadaceae, Pseudomonadaceae) involved in nutrient cycling and plant growth promotion. Although inherent soil properties shape the core microbiome, land-use intensification acts as a strong secondary filter, shifting soil bacterial communities toward more stress-resistant Firmicutes with potentially less diverse functions. Our findings demonstrate the utility of integrating space-for-time substitution with molecular profiling to predict long-term microbial responses to environmental change in vulnerable tropical ecosystems. Full article

The electromagnetic induction (EMI) and frequency domain reflectometry (FDR) sensors, which measure the soil apparent electrical conductivity (ECa) in situ, have emerged as efficient and rapid tools for the indirect assessment of soil salinity, conventionally determined by the electrical conductivity of the saturated soil paste extract (ECe). However, the limitations of applying a single soil sensor and the ECa dependence on multiple soil properties, such as soil moisture and texture, can hinder the interpretation of ECe, whereas selecting the most appropriate set of sensors is challenging. To address these issues, this study explored the prediction ability of a noninvasive EM38-MK2 (EMI) and a capacitance dielectric WET-2 probe (FDR) in assessing topsoil salinity and texture within 0–30 cm depth across diverse soil and land-use conditions in Laconia, Greece. To this aim, multiple linear regression models of laboratory-estimated ECe and soil texture were constructed by the in situ measurements of EM38-MK2 and WET-2, and their performances were individually evaluated using statistical metrics. As was shown, in heterogeneous soils with sufficient wetness and high salinity levels, both sensors produced models with high adjusted coefficients of determination (adj. R² > 0.82) and low root mean square error (RMSE) and mean absolute error (MAE), indicating strong model fit and reliable estimations of topsoil salinity. For the EM38-MK2, model accuracy improved when clay was included in the regression, while for the WET-2, the soil pore water electrical conductivity (ECp) was the most accurate predictor. The drying soil surface was the greatest constraint to both sensors’ predictive performances, whereas in non-saline soils, the silt and sand were moderately assessed by the EM38-MK2 readings (0.49 < adj. R² < 0.51). The results revealed that a complementary use of the contemporary EM38-MK2 and the low-cost WET-2 could provide an enhanced interpretation of the soil properties in the topsoil without the need for additional data acquisition, although more dense soil measurements are recommended. Full article

Outdoor substations present complex conditions such as uneven terrain, strong illumination variations, and frequent occlusions, which pose significant challenges for autonomous robotic inspection. To address these issues, we develop an embedded inspection robot that integrates attention-enhanced semantic segmentation with GPS-assisted navigation for reliable operation. A lightweight DeepLabV3+ model is improved with ECA-SimAM and CBAM attention modules and further extended with a GPS-guided attention component that incorporates coarse location priors to refine feature focus and improve boundary recognition under challenging lighting and occlusion. The segmentation outputs are used to generate real-time road masks and navigation lines via center-of-mass and least-squares fitting, while RTK-GPS provides global positioning and triggers waypoint-based behaviors such as turning and stopping. Experimental results show that the proposed method achieves 85.26% mean IoU and 89.45% mean pixel accuracy, outperforming U-Net, PSPNet, HRNet, and standard DeepLabV3+. Deployed on an embedded platform and validated in real substations, the system demonstrates both robustness and scalability for practical infrastructure inspection tasks. Full article

Diabrotica virgifera virgifera Le Conte, 1868 (Coleoptera: Chrysomelidae), known as the western corn rootworm, is one of the most important alien insect pests affecting maize crops globally. It causes significant economic losses by feeding on the roots, which affects plant stability and nutrient absorption, as well as by attacking essential aerial organs (leaves, silk, pollen). Since its accidental introduction into Europe, the species has expanded its range across maize-growing regions, raising concerns about future distribution under climate change. This study aimed to estimate the risk of pest establishment across Europe over three future time frames (2034, 2054, 2074) based on geographic coordinates, climate data, and maize distribution. Spatial simulations were performed in QGIS using national centroid datasets, risk classification criteria, and temperature anomaly maps derived from Copernicus and ECA&D databases for 1992–2024. The results indicate consistently high risk in southern and southeastern regions, with projected expansion toward central and western areas by 2074. Risk zones showed clear spatial aggregation and directional spread correlated with warming trends and maize availability. The pest’s high reproductive potential, thermal tolerance, and capacity for human-assisted dispersal further support these predictions. The model emphasizes the need for expanded surveillance in at-risk zones and targeted policies in areas where D. v. virgifera has not yet established. Future work should refine spatial predictions using field validation, genetic monitoring, and dispersal modeling. The results contribute to anticipatory pest management planning and can support sustainable maize production across changing agroclimatic zones in Europe. Full article

Background: Carotid artery stenting (CAS) is a common revascularization approach for carotid artery stenosis. While its impact on the internal carotid artery (ICA) has been extensively studied, the effects on the external carotid artery (ECA)—a key collateral pathway for cerebral perfusion—remain insufficiently explored. This study aimed to assess structural changes in the ECA following CAS and their clinical significance. Methods: A retrospective observational cohort study of 963 patients treated with CAS between 2018 and 2024 was conducted. Demographic data, comorbidities, and procedural characteristics were collected. Pre- and postprocedural ICA and ECA diameters were measured via angiography. Spearman’s correlation, regression modeling, and receiver operating curver (ROC) analysis were used to identify predictors of ECA narrowing and occlusion and their relationship with neurological outcomes. Results: The median ECA diameter decreased post-CAS (from 4.7 mm to 3.8 mm, p < 0.001). ECA overstenting occurred in 96.4% of cases, with 71.7% exhibiting diameter reduction. De novo ECA occlusion occurred in 2.5% of patients and was associated with a higher incidence of stroke, transient ischemic attack, and in-stent restenosis (ISR). Multivariate analysis identified preoperative ECA diameter (p < 0.001), ICA diameter (p = 0.001), and second-generation stents (p = 0.02) as independent predictors of ECA narrowing. ROC analysis confirmed that a preoperative ECA diameter ≤ 3.05 mm strongly predicted occlusion (Area under the curve (AUC) = 0.93, p < 0.001). Conclusions: CAS frequently leads to ECA remodeling, including occlusion, compromising collateral perfusion and contributing to adverse ischemic incidences and ISR. Preprocedural ECA assessment may aid in optimizing patient selection and procedural planning. Full article

Brain tumors usually appear as masses formed by localized abnormal cell proliferation. Although complete removal of tumors is an ideal treatment goal, this process faces many challenges due to the aggressive nature of malignant tumors and the need to protect normal brain tissue. Therefore, early diagnosis is crucial to mitigate the harm posed by brain tumors. In this study, the classification accuracy is improved by improving the ResNet50 model. Specifically, the image is preprocessed and enhanced firstly, and the image is denoised by fractional calculus; then, transfer learning technology is adopted, the ECA attention mechanism is introduced, the convolutional layer in the residual block is optimized, and the multi-scale convolutional layer is fused. These optimization measures not only enhance the model’s ability to grasp the overall details but also improve its ability to recognize micro and macro features. This allows the model to understand data features more comprehensively and process image details more efficiently, thereby improving processing accuracy. In addition, the improved ResNet50 model is combined with EfficientNetB0 to further optimize performance and improve classification accuracy by utilizing EfficientNetB0’s efficient feature extraction capabilities through feature fusion. In this study, we used a brain tumor image dataset containing 5712 training images and 1311 validation images. The optimized ResNet50 model achieves a verification accuracy of 98.78%, which is 3.51% higher than the original model, and the Kappa value is also increased by 4.7%. At the same time, the lightweight design of the EfficientNetB0 improves performance while reducing uptime. These improvements can help diagnose brain tumors earlier and more accurately, thereby improving patient outcomes and survival rates. Full article

Climate change has exacerbated the need for transitional shifts within high-impact sectors, notably maritime transport, which facilitates nearly 90% of global trade. In response, the International Maritime Organization (IMO) has implemented stricter environmental regulations under MARPOL Annex VI, which includes, among other things, the designation of Emission Control Areas (ECAs) and Particularly Sensitive Sea Areas (PSSAs). These regulatory instruments have prompted the uptake of new technologies, such as scrubbers, LNG propulsion, and low-sulfur fuels to mitigate emissions in these zones. However, emerging evidence has raised environmental concerns about these solutions which may offset their intended climate benefits. This study investigates the hypothesis that ECAs and PSSAs act as catalysts for maritime environmental advancements through a systematic mapping of 76 peer-reviewed articles. Drawing on data from Scopus and Web of Science, the study analyzes trends in technological advances, publication timelines, geographic research distribution, and the increasing role of decision-support tools for regulatory compliance. Findings show increased academic outputs particularly in China, North America, and Europe, and suggest that achieving effective emissions reduction requires globally harmonized policies, bridging research practice gaps, and targeted financial support to ensure sustainable outcomes throughout the sector. The study suggests that for ECAs and PSSAs to deliver truly sustainable outcomes, global regulation must be supported by empirical performance assessments, environmental safeguards for compliance technologies, and targeted support for developing maritime regions. Full article

The Kazakh horse is a highly valuable indigenous Chinese breed known for its use in both milk and meat production. However, the mechanisms underlying color variation in the abdominal adipose tissue of this breed remain poorly understood. In this study, the sequencing of non-coding RNAs (ncRNAs) was conducted on abdominal adipose tissue of different colors from Kazakh horses, with the aim of investigating the molecular mechanisms responsible for this variation. A total of 205 differentially expressed long non-coding RNAs (DELncRNAs) including ENSECAG00000003836, ENSECAG00000017858, and ENSECAG00000035167; 52 differentially expressed microRNAs (DEmiRNAs) including miR-200-y and eca-miR-9a; and 559 differentially expressed circular RNAs (DEcircRNAs) including ZNF226 and ITPKC, were identified between Group W and Group Y. GO annotation and KEGG enrichment analyses of the DEGs revealed that these genes were primarily involved in biological processes such as chemical homeostasis (biological process, BP), intracellular components (cellular component, CC), and iron-sulfur cluster binding (molecular function, MF) as well as in metabolic pathways related to lipid biosynthesis and metabolism including vitamin B6 metabolism, tryptophan metabolism, and glycerolipid metabolism. The sequencing accuracy was further validated using reverse transcription quantitative PCR (RT-qPCR). This study identified key DEGs and signaling pathways associated with the color variation in adipose tissue of Kazakh horses and sheds light on the regulatory genes and biological processes involved. These findings provide a theoretical basis and research foundation for future studies on color variations in the adipose tissue of equine species. Full article