Search Results (5,906)

To improve the predictive accuracy of wind-field distributions during fires in high-rise buildings, this study targets the shortcomings of traditional prediction methods, including insufficient information fusion and dispersed feature representations under high-rise fire conditions. An efficient attention mechanism, termed Adaptive Channel and Multi-Scale Spatial Fusion Attention Mechanism (CSFAM), is proposed, which endows the model with enhanced adaptive focusing and multi-scale integration capabilities. CSFAM can account for environmental features across multiple dimensions to enable high-spatial-resolution wind-field reconstruction, thereby improving robustness and prediction accuracy in complex environments. To validate the effectiveness of CSFAM for predicting wind fields under high-rise-fire conditions, CFD-based scenario modeling was employed to generate a dataset of 1050 CFD-derived wind-field distributions across diverse inflow-wind and fire-source scenarios, partitioned into training, testing, and validation sets according to the fire-source size. When applying the CSFAM-enhanced multi-layer perceptron (MLP), the wind-field predictions achieved a mean squared error (MSE) of 0.0004, a mean absolute error (MAE) of 0.0141, and an R² of 0.9766, outperforming state-of-the-art methods. The results demonstrate that CSFAM plays a significant role in markedly improving wind-speed prediction accuracy during high-rise-building fires, and enhances the model’s ability to identify and express vortex-like and other key aerodynamic features generated by the fire, thereby improving the capture of the complex nonlinear aerodynamic structures induced by fire. Full article

Environmental, Social, and Governance (ESG) text classification is important for applications in sustainable finance. However, it remains a challenging task due to domain terminology and regulatory constraints. While transformer-based models achieve strong predictive performance, they often lead to high energy costs and provide limited interpretability. To address these limitations, we introduce ESG-Graph, a lightweight and interpretable graph-based framework for modeling ESG disclosures. In our approach, each sentence is represented as a token-level dependency graph augmented with virtual nodes initialized from a European Sustainability Reporting Standards (ESRS)-based taxonomy, enabling the addition of new ESG concepts without retraining. A multi-layer Graph Attention Network is used instead of transformer encoders, allowing grammatical structure and domain semantics to be modeled jointly. Experiments on three ESG benchmark datasets show that ESG-Graph achieves performance comparable to efficient transformer baselines while consuming up to 60× less energy and using 10× fewer parameters. Additional attribution and ablation studies suggest the method’s policy alignment, interpretability, and robustness. Full article

Geopolymers have attracted increasing attention as sustainable binders, but their long-term durability in chloride-rich environments remains a critical concern. To elucidate the mechanistic role of calcined layered double hydroxides (CLDHs) in regulating the mechanical properties and chloride diffusion behavior of geopolymers, geopolymer pastes containing different CLDH contents were prepared. The compressive strength and chloride diffusion coefficient were determined, and the underlying mechanism was analyzed from the perspectives of geopolymerization degree, gel structure development, and pore structure evolution. The results indicate that the incorporation of CLDHs can promote geopolymerization, which may be associated with a nano-seeding effect, increasing the amount and degree of polymerization of the gel phases, refining the pore structure, and reducing pore connectivity. As a result, the compressive strength increases from 38.1 MPa to 49.2 MPa, while the chloride diffusion coefficient decreases by approximately 31.7% when the CLDH content reaches 6 wt.%. However, when the CLDH content exceeds this level, particle agglomeration limits effective gel growth, leading to microstructural deterioration and a weakened regulating effect. Full article

Infrared small-target segmentation (IRSTS) is crucial for a wide range of applications, including maritime search-and-rescue operations and intelligent traffic surveillance. However, current deep learning methods struggle with dynamic scale variations in infrared small targets, resulting in false detections and missed detections, alongside inadequate core localization accuracy. To address these challenges, we propose an infrared small-target segmentation framework founded on morphological attention and an energy core loss function, IRSTS_Unet. Specifically, we design a Dynamic Shape-adaptive Deformable Attention Module (DSDAM), which achieves parameterized feature extraction via “initial localization–offset deformation–precise sampling”. This approach enables the network to differentially focus on target cores and background cues to suppress clutter. To improve the efficiency of multi-scale feature aggregation, we embed the DSDAM within both the feature extraction and cross-layer fusion stages. Furthermore, we formulate a Core Energy-aware Core-Priority loss (CECP-Loss) function that incorporates the energy prior distribution of small targets, effectively counteracting the “core dilution” phenomenon endemic to conventional loss functions. Through extensive experiments on multiple public datasets, we demonstrate that IRSTS_U-Net outperforms state-of-the-art approaches in terms of both detection accuracy and robustness. Full article

In response to the subjective issues, inconsistent quality standards, high labor intensity and low sorting efficiency during the drying process of green pepper, an improved YOLOv11 algorithm was proposed for quality detection. A multi-scale edge enhancement module (MEEM) is introduced into the backbone network, replacing the original basic C3K2 module with C3K2-MEEM to enhance the extraction of detailed features in images of dried green Sichuan pepper and prevent missed detections, false detections, and boundary confusion. The LRSA module is integrated into the 10th layer of the backbone network to improve the clarity of the tumor-like texture of the Sichuan pepper and reduce the influence of impurities, automatically allocating attention based on feature similarity to preserve local information. In the neck layer, the DPCF module is added to the FPN+PAN feature fusion stage to achieve multi-scale feature collaboration, meeting the detection requirements of dried green Sichuan pepper. The results show that the accuracy recall rate, mean average precision, and model size of the improved MLD-YOLOv11 algorithm are 92.1%, 96.6%, 95.6%, and 11.06 MB, respectively. Compared with the training results of the original YOLOv11 model, the average accuracy of the improved model has increased by 2.2 percentage points, and GFLOPs have definitely decreased by 2 G, with parameter reduction of approximately 3.10%. Compared with other mainstream models, the MLD-YOLOv11 model has significant advantages in terms of mean average precision, model size, and floating point operations per second, making it more suitable for industrial applications and providing an efficient, accurate, and lightweight solution for the quality detection of dried green Sichuan pepper. Full article

Images of wind turbine blades captured by drones often feature complex backgrounds, and small targets such as minor defects or images have low resolution, leading to reduced recognition rates. To address environments with complex feature backgrounds, this paper proposes the PPS-MSDeim model. Based on the lightweight end-to-end detection framework DEIM-N, it introduces three core innovations to tackle the challenge of detecting small, irregular defects on wind turbine blades against complex backgrounds. First, we design an inverted multi-scale deep separable convolutional module (MDSC). After compressing channels via a bottleneck layer, it concurrently processes 3 × 3, 5 × 5, and 7 × 7 inverted deep separable convolutions. By first fusing channel information and then extracting multi-receiver-field spatial features, this approach enhances the ability to characterize morphologically variable defects while reducing computational overhead. The MDSC is then embedded into the backbone network HGNetv2. Second, we construct a Multi-Scale Feature Aggregation and Diffusion Pyramid Network (MFADPN). Through a Multi-Scale Feature Aggregation Module (MSFAM), it directly fuses features from layers P2 to P5, achieving deep integration of high-level semantics and low-level details. Combining dilated convolutions with expansion ratios of 1, 3, and 5 captures multi-level context, and a Sobel edge branch is introduced to enhance defect contours; subsequently, a feature diffusion operation is performed to distribute the enhanced features back to each level, shortening information paths and preventing signal decay; simultaneously, a high-resolution detection head is added to P2 and the P5 head is removed to improve sensitivity for small object detection. Finally, we propose the PPSformer module to replace the original Transformer encoding layer. It uses patch embedding to convert images into sequences and introduces a multi-head probabilistic sparse self-attention mechanism that focuses only on key-value pairs during attention computation. This design efficiently captures irregularly varying feature information and globally detects data anomalies induced by external defects. This study uses real engineering data sets, and the results show that PPS-MSDeim, based on DEIM, increased mAP@0.5 by 6.7%, reaching 95.1%. mAP@0.5–0.95 increased by 12.0%, reaching 70.1%. This indicates that the proposed method has a significant advantage in detecting defects in wind turbine blades. Full article

Understanding how the brain processes complex real-world experiences remains a central challenge in cognitive neuroscience. Naturalistic movie neuroimaging has gained prominence by using temporally continuous stimuli that approximate everyday perception. However, cinematic experience is not equivalent to real-world cognition. Films are systematically constructed through film forms such as editing, camera movement, and sound, which diverge from natural perceptual conditions and shape cognitive processing. In this review, we rethink naturalistic movie neuroimaging by foregrounding film form as a central explanatory factor. We propose a conceptual framework for studying human cognition through film form, in which film form is conceptualized as a mediating layer between naturalistic movie neuroimaging and cognitive processing. We synthesize behavioral and neuroimaging evidence showing that multiple film forms exert domain-specific influences on attention, emotion, and memory. To organize these findings, we propose the Film Cognition Matrix, which maps film forms onto core cognitive domains and supports comparative research. Finally, we argue that interpretations of naturalistic movie neuroimaging should explicitly model film form as a mediator. Future directions include computationally modeling to isolate film-form effects on neural activity, expanding film-form–cognition mapping, exploring interactive and immersive media, and clarifying the boundary between real-world cognition and cinematic aesthetics. Full article

As unique settlements born of industrial civilization, workers’ residential areas carry rich heritage and the collective memory of communities they contain, endowing them with distinct historical and cultural significance. Assessing and enhancing their resilience are essential for both heritage preservation and sustainable community development. Despite the prevalence of such neighborhoods in China’s old industrial cities, systematic evaluation of their comprehensive resilience remains limited. To address this research gap, we take Taiyuan Mining Machinery Dormitory as a case study. Integrating multi-source spatial and demographic data, we construct a resilience evaluation framework based on the DPSIR model, comprising five criterion layers, 22 element layers, and 49 indicators. Combined with an obstacle degree model, it identifies key factors constraining resilience. Results indicate that comprehensive resilience of the study area is at a “moderate” level, with the “response” subsystem scoring notably low, reflecting insufficient stakeholder attention. Major obstacles include per capita shelter area, building quality, road accessibility, residents’ willingness to participate in governance, and organizational leadership capacity. Based on these findings, targeted strategies are proposed to enhance resilience amid increasing risks. This study contributes to community resilience theory and offers practical insights for the conservation and regeneration of workers’ residential areas under urban renewal. Full article

With the rapid advancement of autonomous driving in modern society, dense pedestrian detection technology has encountered performance bottlenecks. To address this, we propose a robust and lightweight pedestrian detection algorithm, RMP-YOLO, designed to efficiently detect small, occluded, and low-light objects. Firstly, RFAConv is utilized as the core component of the backbone network, combining standard convolution with attention mechanisms and using group convolution to extract features from the spatial receptive field. Secondly, MobileViTv3 is introduced into the backbone to combine CNNs with Transformers. The model is further enhanced by adjusting feature fusion, introducing residual connections, and optimizing local representation with deep convolutional layers. Finally, the PIoUv2 loss function is employed for bounding-box regression, significantly reducing detection errors for small-scale pedestrians in crowded environments. Experimental results demonstrate that RMP-YOLO improves mAP@0.5 by 1.3% on a custom dataset and 0.91% on the WiderPerson dataset. Crucially, it maintains high efficiency with only 3.71 million parameters and 6.29 GFLOPs, meeting the deployment requirements for low computational power and high precision. Full article

Rock–fill composite slopes formed during the transition from underground to open-pit mining in metal mines are highly susceptible to interface hydraulic weakening and sudden sliding under intense rainfall, mainly due to the permeability contrast between the two media. Taking the Shizhuyuan Mine as a case study, a coupled hydro-mechanical numerical model was developed in ABAQUS 2025 to investigate slope stability under different rainfall patterns and interface strength degradation scenarios. The spatiotemporal evolution of seepage and deformation fields was examined in detail, with particular attention given to the variation of the safety factor, the distribution of pore water pressure along the interface, and the characteristics of interface slip. The results show that: (1) the deterioration of the hydraulic condition within the slope is governed by the water-blocking effect of the interface and the infiltration threshold of the surface layer. Under the same total rainfall, prolonged low-intensity rainfall is more likely than short-duration intense rainfall to produce sustained deep infiltration, and the factor of safety decreases from the initial 1.369 to 1.173 (0.005 m/h, 288 h) and 1.255 (0.02 m/h, 72 h), respectively, indicating that the former exerts a more pronounced weakening effect on slope stability. (2) Slope instability exhibits a clear interface-controlled pattern. Regardless of the degree of parameter degradation, the base of the plastic zone consistently develops along the rock–fill interface, accompanied by extensive plastic deformation within the overlying fill material. (3) Failure initiates at the slope toe where the mechanical equilibrium along the rock–fill interface is first disturbed. Under the combined influence of topographic conditions and the water-blocking effect of the interface, rainfall infiltration tends to converge toward the slope toe and form a local high-pore-pressure zone, resulting in a marked reduction in the effective normal stress at the interface. Once the local shear stress exceeds the shear strength, yielding is triggered first at the slope–toe interface, which then induces plastic deformation in the overlying fill material and ultimately leads to overall slope instability. Full article

The oilfield gathering and transportation system (OGTS) accounts for a substantial share of total energy consumption, demonstrating considerable potential for energy-saving optimization. Previous research primarily focused on the independent optimization of gathering pipeline networks or processing stations, with little attention given to their integrated optimization. This study investigates the OGTS of a domestic oilfield block. It develops artificial neural network (ANN) surrogate models for both pipelines and processing station equipment to accurately capture system operating states. An optimization model linking the pipeline network and processing station is established, and a differential evolution algorithm is applied to enhance computational efficiency. The results indicate that optimal predictive performance was achieved when the first hidden layer of the backpropagation neural network (BPNN) contained 50 neurons with a rectified linear unit (ReLU) activation function, with the surrogate models achieving coefficient of determination (R²) values exceeding 0.85. Under a 30 min optimization cycle, total system energy consumption decreased by 2.28%, with computation completed in under 3 min, while daily average optimization led to a 1.55% reduction. These findings demonstrate that the proposed integrated optimization framework offers both a robust methodological foundation and practical engineering guidance for coordinated, low-carbon, and energy-efficient operation of oilfields. Full article

Bone tissue plays a vital role in the human body and possesses intrinsic self-repair mechanisms; however, large defects or pathological fractures may exceed its natural healing capacity. Bone tissue engineering provides promising strategies to restore bone integrity through the use of scaffolds, growth factors, and stem cells. While calcium phosphate (CaP)-based ceramics, such as hydroxyapatite (HAp) and tricalcium phosphate (TCP), represent the current benchmark, their limitations, including slow degradation (HAp) and limited osteoinductivity (TCP), have driven the development of alternative biomaterials. In this context, magnesium phosphate (MgP)-based materials have gained increasing attention due to their tunable resorption rate, improved biodegradability, and ability to stimulate osteogenesis and angiogenesis through the release of magnesium (Mg²⁺) ions. This study reports on composite scaffolds based on electrospun poly(ε-caprolactone) (PCL) fibres coated with MgP layers doped with lithium (Li) and zinc (Zn), designed to mimic the nanofibrous architecture of the extracellular matrix. Lithium and zinc were selected due to their known ability to modulate cellular response, with lithium promoting osteogenic activity and zinc contributing to improved cell proliferation and antibacterial potential. The phosphate phases obtained by coprecipitation were deposited onto the PCL fibres using Matrix-Assisted Pulsed Laser Evaporation (MAPLE), enabling controlled surface functionalization. Following thermal treatment, the formation of the crystalline magnesium pyrophosphate (Mg₂P₂O₇) phase was confirmed by chemical and structural characterization. The combination of a slowly degrading PCL matrix, providing sustained structural support, and a bioactive MgP coating, enabling rapid and controlled ion release, results in improved scaffold performance in terms of biocompatibility, biodegradability, and bioactivity. While the slow degradation rate of PCL ensures mechanical stability over an extended period, the surface-deposited MgP phase allows immediate interaction with the biological environment, facilitating faster ion release and enhancing cell–material interactions. These findings highlight the potential of the developed composites as promising candidates for trabecular bone regeneration and as viable alternatives to conventional CaP-based scaffolds in regenerative medicine. Full article

Early plant leaf disease detection and timely control is important for agricultural yield and stability. Yet, it is difficult for manual labor to monitor the health of the plant leaf 24 h a day. Existing detection approach cannot meet the demands of texture enhancement features. Therefore, this paper proposes a new detection approach which undergoes three-layer transformations: convolutional layer, attention mechanism layer and loss function layer. Firstly, ADown is used to extract fine-grained texture features from suspected leaves to reduce computational load. Secondly, Gabor texture enhancement is proposed to extract and enhance the contour and the directional texture of suspected areas using multi-directional filtering, followed by a combination Transformer to enhance the global context modeling capability. Thirdly, a dynamic boundary loss function (DBL) is employed to dynamically adjust the probability distribution of bounding box regression through adaptive temperature coefficient and information entropy, thereby improving the positioning accuracy of the detection box. The experiments show that ATD-Net achieved an average accuracy of 87.42% (mAP50) and an accuracy of 85.96%, with a computational complexity of 6.5 GFLOPs. The visualization results and ablation experiments show that the collaborative work of the proposed modules significantly improves the detection robustness in complex backgrounds, early diseases, and small target scenes. Compared to the original model, ATD-Net achieves a performance improvement of 1.1% at mAP50 and a speed increase of 17.7%. The model size remains almost unchanged, at 5.2 MB. It is an efficient and promising solution for future real-time disease recognition in complex agricultural environments. Full article

Addressing the challenges of complex background interference, low lighting conditions, small target recognition, and difficulty in maturity grading in the automated detection of Pleurotus ostreatus, this study proposes a lightweight improved scheme based on color feature enhancement. By collecting 4779 images from five developmental stages in three typical planting environments, including greenhouses and mushroom houses, an HSV hue analysis database was established to determine key hue intervals [4°, 38°] or [110°, 155°] for different environments. Secondly, based on the hue interval distribution of Pleu-rotus ostreatus, YOLOv13 was used as the base model, with the addition of an HSV hue mask as the fourth channel to improve the input layer. The custom ColorWeight module was used to enhance color feature expression; the hypergraph computation module was improved to enhance feature correlation; and the neck network incorporated the StockenAttention module to improve the ability to capture maturity features. The accuracy of the improved model was increased to 89.5% in mAP@0.5 (+3.3%), surpassing the mainstream YOLOv8n-12n series. Efficiency optimization achieved real-time detection at 12.58 FPS on the RTX3090Ti platform. In practical applications, the accuracy of maturity recognition was significantly improved, with a 73.6% decrease in the misclassification rate of maturity and a reduction in missed detections, achieving an F1 score of 0.91. In conclusion, through the deep integration of Hue features and deep learning models, while ensuring lightweight deployment (with only a 10.5% increase in parameter count), the accuracy and practicality of Pleurotus ostreatus detection were significantly improved, providing an effective solution for intelligent mushroom house management. Full article

Skin cancer represents a significant public health challenge, necessitating early detection and timely treatment for optimal management. Timely and accurate evaluation of skin lesions is crucial, as delays can lead to more severe outcomes. However, identifying skin lesions accurately can be challenging due to differences in color, shape, and the various types of imaging equipment used for diagnosis. While recent studies have demonstrated the potential of ensemble convolutional neural networks (CNNs) for early diagnosis of skin disorders, these models are often too large and inefficient for processing contextual information. Although lightweight networks like MobileNetV3 and EfficientNet have been developed to reduce parameters and enable deep neural networks on mobile devices, their performance is limited by inadequate feature representation depth. To mitigate these limitations, we propose a new hybrid attention dual-stream deep learning model for skin lesion detection. Our model uses one training process to preprocess the images and splits the task into two branches. Each branch extracts different features using multi-stage and multi-branch attention techniques, improving the model’s ability to detect skin lesions accurately. The first branch processes the original image using a convolutional layer integrated with three novel attention modules: Enhanced Separable Depthwise Convolution (SCAttn), stage attention, and branch attention. The second branch utilizes Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the input image, improving local contrast and revealing finer details. The integration of CLAHE with SCAttn modules leverages enhanced local contrast to capture more nuanced features while maintaining computational efficiency. A classification module receives the concatenated hierarchical characteristics that were taken from both branches. Utilizing the PAD2020 and ISIC 2019 datasets, we assessed the proposed model and obtained an accuracy rate of 98.59% for PAD2020, surpassing the state-of-the-art performance by 2%, and stable performance accuracy for the ISIC 2019 dataset. This illustrates how well the model can integrate several attention mechanisms and feature enhancement methods, providing a reliable and effective means of detecting skin cancer. Full article