Search Results (6,233)

The accurate segmentation of skin lesions plays an important role in the diagnosis and treatment of skin cancers. However, skin lesion areas are rich in details and local features, including the appearance, size, shape, texture, etc., which pose challenges for the accurate localization and segmentation of the target area. Unfortunately, the consecutive pooling and stride convolutional operations in existing convolutional neural network (CNN)-based solutions lead to the loss of some spatial information and thus constrain the accuracy of lesion region segmentation. In addition, using only the traditional loss function in CNN cannot ensure that the model is adequately trained. In this study, a generative adversarial network is proposed, with global and local semantic feature awareness (GLSFA-GAN) for skin lesion segmentation based on adversarial training. Specifically, in the generator, a multi-scale localized feature fusion module and an effective channel-attention module are designed to acquire the multi-scale local detailed information of the skin lesion area. In addition, a global context extraction module in the bottleneck between the encoder and decoder of the generator is used to capture more global semantic features and spatial information about the lesion. After that, we use an adversarial training strategy to make the discriminator discern the generated labels and the segmentation prediction maps, which assists the generator in yielding more accurate segmentation maps. Our proposed model was trained and validated on three public skin lesion challenge datasets involving the ISIC2017, ISIC2018, and HAM10000, and the experimental results confirm that our proposed method provides a superior segmentation performance and outperforms several comparative methods. Full article

The purpose of entity linking is to connect entity mentions in text to real entities in the knowledge base. Existing methods focus on using the text topic, entity type, linking order, and association between entities to obtain the target entities. Although these methods have achieved good results, they ignore the exploration of candidate entities, leading to insufficient semantic information among entities. In addition, the implicit relationship and discrimination within the candidate entities also affect the accuracy of entity linking. To address these problems, we introduce information about candidate entities from Wikipedia and construct a graph model to capture implicit dependencies between different entity decisions. Specifically, we propose a cascade attention mechanism and develop a novel local entity linkage model termed CAM-LEL. This model leverages the interaction between entity mentions and candidate entities to enhance the semantic representation of entities. Furthermore, a global entity linkage model termed DG-GEL based on a dynamic graph is established to construct an entity association graph, and a random walking algorithm and entity entropy are used to extract the implicit relationships within entities to increase the differentiation between entities. Experimental results and in-depth analyses of multiple datasets show that our model outperforms other state-of-the-art models. Full article

The semantic segmentation of satellite and UAV remote sensing imagery is pivotal for address exploration, change detection, quantitative analysis and urban planning. Recent advancements have seen an influx of segmentation networks utilizing convolutional neural networks and transformers. However, the intricate geographical features and varied land cover boundary interferences in remote sensing imagery still challenge conventional segmentation networks’ spatial representation and long-range dependency capabilities. This paper introduces a novel U-Net-like network for UAV image segmentation. We developed a link aggregation Mamba at the critical skip connection stage of UNetFormer. This approach maps and aggregates multi-scale features from different stages into a unified linear dimension through four Mamba branches containing state-space models (SSMs), ultimately decoupling and fusing these features to restore the contextual relationships in the mask. Moreover, the Mix-Mamba module is incorporated, leveraging a parallel self-attention mechanism with SSMs to merge the advantages of a global receptive field and reduce modeling complexity. This module facilitates nonlinear modeling across different channels and spaces through multipath activation, catering to international and local long-range dependencies. Evaluations on public remote sensing datasets like LovaDA, UAVid and Vaihingen underscore the state-of-the-art performance of our approach. Full article

Ancient paintings, as a vital component of cultural heritage, encapsulate a profound depth of cultural significance. Over time, they often suffer from different degradation conditions, leading to damage. Existing ancient painting inpainting methods struggle with semantic discontinuities, blurred textures, and details in missing areas. To address these issues, this paper proposes a generative adversarial network (GAN)-based ancient painting inpainting method named RG-GAN. Firstly, to address the inconsistency between the styles of missing and non-missing areas, this paper proposes a Regional Attention-Style Transfer Module (RASTM) to achieve complex style transfer while maintaining the authenticity of the content. Meanwhile, a multi-scale fusion generator (MFG) is proposed to use the multi-scale residual downsampling module to reduce the size of the feature map and effectively extract and integrate the features of different scales. Secondly, a multi-scale fusion mechanism leverages the Multi-scale Cross-layer Perception Module (MCPM) to enhance feature representation of filled areas to solve the semantic incoherence of the missing region of the image. Finally, the Global Context Perception Discriminator (GCPD) is proposed for the deficiencies in capturing detailed information, which enhances the information interaction across dimensions and improves the discriminator’s ability to identify specific spatial areas and extract critical detail information. Experiments on the ancient painting and ancient Huaniao++ datasets demonstrate that our method achieves the highest PSNR values of 34.62 and 23.46 and the lowest LPIPS values of 0.0507 and 0.0938, respectively. Full article

The Changbai volcano, a globally recognized hotspot of volcanic activity, has garnered significant attention due to its persistent seismicity and ongoing magma activity. The volcano’s discontinuities and magma dynamics have raised concerns about the likelihood of future eruptions, which would likely result in substantial ecological, climatic, and economic impacts. Consequently, a comprehensive understanding of the Changbai volcanic system is essential for mitigating the risks associated with volcanic activity. In recent years, the P-wave coda autocorrelation method has gained popularity in lithosphere exploration as a reliable technique for detecting reflection coefficients. Additionally, the Common Reflection Point stacking approach has been employed to superimpose reflection signals in a spatial grid, enabling continuous observation of reflection coefficients in the study area. However, the accuracy of this approach is heavily reliant on better spatial data coverage. To better understand the internal dynamics of the Changbai volcano, we applied this approach to a densely packed short-period seismic array with an average station spacing of less than 1 km. Our results were constrained using waveform data of reflection coefficients and Moho dip angles. Our findings revealed a discontinuity in the Moho, which may indicate a conduit for mantle magma entering the crust. Furthermore, we identified two low-velocity anomalies within the crust, likely representing a magma chamber comprising molten and crystallized magma. Notably, our results also provided a clear definition of the lithosphere–asthenosphere boundary. Full article

In the field of navigation and positioning, the inertial navigation system (INS)/global navigation satellite system (GNSS) integrated navigation system is known for providing stable and high-precision navigation services for vehicles. However, in extreme scenarios where GNSS navigation data are completely interrupted, the positioning accuracy of these integrated systems declines sharply. While there has been considerable research into using neural networks to replace the GNSS signal output during such interruptions, these approaches often lack targeted modeling of sensor information, resulting in poor navigation stability. In this study, we propose an integrated navigation system assisted by a novel neural network: an inverted-Transformer (iTransformer) and the application of a frequency-enhanced channel attention mechanism (FECAM) to enhance its performance, called an INS/FECAM-iTransformer integrated navigation system. The key advantage of this system lies in its ability to simultaneously extract features from both the time and frequency domains and capture the variable correlations among multi-channel measurements, thereby enhancing the modeling capabilities for sensor data. In the experimental part, a public dataset and a private dataset are used for testing. The best experimental results show that compared to a pure INS inertial navigation system, the position error of the INS/FECAM-iTransformer integrated navigation system reduces by up to 99.9%. Compared to the INS/LSTM (long short-term memory) and INS/GRU (gated recurrent unit) integrated navigation systems, the position error of the proposed method decreases by up to 82.4% and 78.2%, respectively. The proposed approach offers significantly higher navigation accuracy and stability. Full article

China’s Yunnan Province, known for its tea plantations, faces significant challenges in smart pest management due to its ecologically intricate environment. To enable the intelligent monitoring of pests within tea plantations, this study introduces a novel image recognition algorithm, designated as YOLOv8n-WSE-pest. Taking into account the pest image data collected from organic tea gardens in Yunnan, this study utilizes the YOLOv8n network as a foundation and optimizes the original loss function using WIoU-v3 to achieve dynamic gradient allocation and improve the prediction accuracy. The addition of the Spatial and Channel Reconstruction Convolution structure in the Backbone layer reduces redundant spatial and channel features, thereby reducing the model’s complexity. The integration of the Efficient Multi-Scale Attention Module with Cross-Spatial Learning enables the model to have more flexible global attention. The research results demonstrate that compared to the original YOLOv8n model, the improved YOLOv8n-WSE-pest model shows increases in the precision, recall, mAP50, and F1 score by 3.12%, 5.65%, 2.18%, and 4.43%, respectively. In external validation, the mAP of the model outperforms other deep learning networks such as Faster-RCNN, SSD, and the original YOLOv8n, with improvements of 14.34%, 8.85%, and 2.18%, respectively. In summary, the intelligent tea garden pest identification model proposed in this study excels at precise the detection of key pests in tea plantations, enhancing the efficiency and accuracy of pest management through the application of advanced techniques in applied science. Full article

Semantic segmentation of rural roads presents unique challenges due to the unstructured nature of these environments, including irregular road boundaries, mixed surfaces, and diverse obstacles. In this study, we propose an enhanced PP-LiteSeg model specifically designed for rural road segmentation, incorporating a novel Strip Pooling Simple Pyramid Module (SP-SPPM) and a Bottleneck Unified Attention Fusion Module (B-UAFM). These modules improve the model’s ability to capture both global and local features, addressing the complexity of rural roads. To validate the effectiveness of our model, we constructed the Rural Roads Dataset (RRD), which includes a diverse set of rural scenes from different regions and environmental conditions. Experimental results demonstrate that our model significantly outperforms baseline models such as UNet, BiSeNetv1, and BiSeNetv2, achieving higher accuracy in terms of mean intersection over union (MIoU), Kappa coefficient, and Dice coefficient. Our approach enhances segmentation performance in complex rural road environments, providing practical applications for autonomous navigation, infrastructure maintenance, and smart agriculture. Full article

Environmental policy has long been regarded as the key to achieving sustainable growth goals. Because China is one of the most energy-consuming and carbon-emitting countries globally, its carbon reduction actions have received worldwide attention. This study aims to simultaneously focus on the impact of environmental disclosure and the level of environmental disclosure on enterprise performance. Thus, we use China’s 2013 “Carbon Trading Pilot” policy as an exogenous shock and adopt the DID (difference-in-differences) method to examine the impacts of policy-related disclosure and the disclosure level on the financial performance of listed enterprises from 2009 to 2020. The results are as follows: (1) The “Carbon Trading Pilot” policy-related environmental disclosure negatively affects enterprise financial performance; however, the environmental disclosure level is positively correlated with enterprise financial performance, and both impacts are heterogeneous. (2) The impact of the “Carbon Trading Pilot” project-related environmental disclosure level on enterprise financial performance has a threshold effect, where its impact is enhanced when the environmental disclosure index reaches 10.074. (3) Further exploration of mechanisms reveals that total liabilities play an action mechanism role in the above two relationships. Studying the impact of environmental policies on enterprise financial performance is of paramount significance for economic sustainability. Full article

Breast cancer is the most common type of cancer in women and poses a significant health risk to women globally. Developments in computer-aided diagnosis (CAD) systems are focused on specific tasks of classification and segmentation, but few studies involve a completely integrated system. In this study, a comprehensive CAD system was proposed to screen ultrasound, mammograms and magnetic resonance imaging (MRI) of breast cancer, including image preprocessing, breast cancer classification, and tumour segmentation. First, the total variation filter was used for image denoising. Second, an optimised XGBoost machine learning model using EfficicnetB0 as feature extraction was proposed to classify breast images into normal and tumour. Third, after classifying the tumour images, a hybrid CNN deep learning model integrating the strengths of MobileNet and InceptionV3 was proposed to categorise tumour images into benign and malignant. Finally, Attention U-Net was used to segment tumours in annotated datasets while classical image segmentation methods were used for the others. The proposed models in the designed CAD system achieved an accuracy of 96.14% on the abnormal classification and 94.81% on tumour classification on the BUSI dataset, improving the effectiveness of automatic breast cancer diagnosis. Full article

Classification and identification of eye diseases using Optical Coherence Tomography (OCT) has been a challenging task and a trending research area in recent years. Accurate classification and detection of different diseases are crucial for effective care management and improving vision outcomes. Current detection methods fall into two main categories: traditional methods and deep learning-based approaches. Traditional approaches rely on machine learning for feature extraction, while deep learning methods utilize data-driven classification model training. In recent years, Deep Learning (DL) and Machine Learning (ML) algorithms have become essential tools, particularly in medical image classification, and are widely used to classify and identify various diseases. However, due to the high spatial similarities in OCT images, accurate classification remains a challenging task. In this paper, we introduce a novel model called “OCTNet” that integrates a deep learning model combining InceptionV3 with a modified multi-scale attention-based spatial attention block to enhance model performance. OCTNet employs an InceptionV3 backbone with a fusion of dual attention modules to construct the proposed architecture. The InceptionV3 model generates rich features from images, capturing both local and global aspects, which are then enhanced by utilizing the modified multi-scale spatial attention block, resulting in a significantly improved feature map. To evaluate the model’s performance, we utilized two state-of-the-art (SOTA) datasets that include images of normal cases, Choroidal Neovascularization (CNV), Drusen, and Diabetic Macular Edema (DME). Through experimentation and simulation, the proposed OCTNet improves the classification accuracy of the InceptionV3 model by 1.3%, yielding higher accuracy than other SOTA models. We also performed an ablation study to demonstrate the effectiveness of the proposed method. The model achieved an overall average accuracy of 99.50% and 99.65% with two different OCT datasets. Full article

The reliable operation of scroll compressors is crucial for the efficiency of rotating machinery and refrigeration systems. To address the need for efficient and accurate fault diagnosis in scroll compressor technology under varying operating states, diverse failure modes, and different operating conditions, a multi-branch convolutional neural network fault diagnosis method (SSG-Net) has been developed. This method is based on the Swin Transformer, the Global Attention Mechanism (GAM), and the ResNet architecture. Initially, the one-dimensional time-series signal is converted into a two-dimensional image using the Short-Time Fourier Transform, thereby enriching the feature set for deep learning analysis. Subsequently, the method integrates the window attention mechanism of the Swin Transformer, the 2D convolution of GAM attention, and the shallow ResNet’s two-dimensional convolution feature extraction branch network. This integration further optimizes the feature extraction process, enhancing the accuracy of fault feature recognition and sensitivity to data variability. Consequently, by combining the global and local features extracted from these three branch networks, the model significantly improves feature representation capability and robustness. Finally, experimental results on scroll compressor datasets and the CWRU dataset demonstrate diagnostic accuracies of 97.44% and 99.78%, respectively. These results surpass existing comparative models and confirm the model’s superior recognition precision and rapid convergence capabilities in complex fault environments. Full article

Greenhouse gas emissions are a major factor contributing to global climate change and have received extensive attention from policymakers worldwide. As a cornerstone of China’s industry and a critical foundation of the global manufacturing sector, the introduction of carbon policies could increase production costs and reduce international competitiveness, thereby impacting its stable development. How can carbon emissions be reduced to meet the environmental standards of the international community while maintaining global market competitiveness? This paper develops a comprehensive set of indicators to assess the industrial resilience of the ferrous metal smelting and rolling industry. These indicators focus on the industry’s development capacity, market demand transformation, potential for technological innovation, and ability to adapt to external shocks and recover autonomously. Using the difference-in-differences (DID) model, it quantifies the effects of carbon policies from China and the EU on the industry’s resilience and examines adaptation mechanisms within the industrial chain. It is found that ferrous metal smelting and rolling industrial resilience has been strengthening, significantly influenced by national research and experimental development (R&D), gearing ratio, and government science and technology investments. China’s domestic carbon policies and the EU’s carbon policy have profoundly impacted the resilience of China’s ferrous metal industry, fostering green innovation and the transition to a low-carbon economy while ensuring industrial stability and competitiveness. Full article

Synthetic Aperture Radar (SAR) imaging is essential for monitoring geomorphic changes, urban transformations, and natural disasters. However, the inherent complexities of SAR, particularly pronounced speckle noise, often lead to numerous false detections. To address these challenges, we propose the Multidirectional Attention Fusion Network (MDAF-Net), an advanced framework that significantly enhances image quality and detection accuracy. Firstly, we introduce the Multidirectional Filter (MF), which employs side-window filtering techniques and eight directional filters. This approach supports multidirectional image processing, effectively suppressing speckle noise and precisely preserving edge details. By utilizing deep neural network components, such as average pooling, the MF dynamically adapts to different noise patterns and textures, thereby enhancing image clarity and contrast. Building on this innovation, MDAF-Net integrates multidirectional feature learning with a multiscale self-attention mechanism. This design utilizes local edge information for robust noise suppression and combines global and local contextual data, enhancing the model’s contextual understanding and adaptability across various scenarios. Rigorous testing on six SAR datasets demonstrated that MDAF-Net achieves superior detection accuracy compared with other methods. On average, the Kappa coefficient improved by approximately 1.14%, substantially reducing errors and enhancing change detection precision. Full article

Global change and the intensification of human activities have led to a sharp decline in global biodiversity and other ecological issues. Over the past 30 years, ecologists have increasingly focused on the question of whether and how the ongoing loss of biodiversity affects ecosystem functioning. However, historically, researchers have predominantly concentrated on individual ecosystem functions, neglecting the capacity of ecosystems to provide multiple ecosystem functions simultaneously, known as ecosystem multifunctionality (EMF). As a result, the connection between biodiversity and ecosystem multifunctionality (BEMF) has become the central theme in BEF relationship research. In recent years, the research on the BEMF relationship has developed rapidly, and new progress has been made in different ecosystems, the driving mechanism of the BEMF relationship, and the proposal and application of new quantitative methods. However, there are still shortcomings, such as the lack of uniform standards for the selection of functional indicators in EMF research, insufficient attention to belowground microbial diversity, and less research on biological interactions in addition to biodiversity. In the future, we need to enhance standard research on the selection of functional indicators, thoroughly assess the combined effects of aboveground and belowground biodiversity along with abiotic factors on EMF, and bolster the research and application of ecosystem multiserviceability (EMS) methods. Full article