Search Results (205)

Semantic change detection technology based on remote sensing data holds significant importance for urban and rural planning decisions and the monitoring of ground objects. However, simple convolutional networks are limited by the receptive field, cannot fully capture detailed semantic information, and cannot effectively perceive subtle changes and constrain edge information. Therefore, a dynamic graph reasoning network with layer-by-layer semantic decomposition for semantic change detection in remote sensing data is developed in response to these limitations. This network aims to understand and perceive subtle changes in the semantic content of remote sensing data from the image pixel level. On the one hand, low-level semantic information and cross-scale spatial local feature details are obtained by dividing subspaces and decomposing convolutional layers with significant kernel expansion. Semantic selection aggregation is used to enhance the characterization of global and contextual semantics. Meanwhile, the initial multi-scale local spatial semantics are screened and re-aggregated to improve the characterization of significant features. On the other hand, at the encoding stage, the weight-sharing approach is employed to align the positions of ground objects in the change area and generate more comprehensive encoding information. Meanwhile, the dynamic graph reasoning module is used to decode the encoded semantics layer by layer to investigate the hidden associations between pixels in the neighborhood. In addition, the edge constraint module is used to constrain boundary pixels and reduce semantic ambiguity. The weighted loss function supervises and optimizes each module separately to enable the network to acquire the optimal feature representation. Finally, experimental results on three open-source datasets, such as SECOND, HIUSD, and Landsat-SCD, show that the proposed method achieves good performance, with an SCD score reaching 35.65%, 98.33%, and 67.29%, respectively. Full article

Yeasts possess a range of environmental adaptations that allow them to colonize soil and sand. They can circulate seasonally between different components of lake ecosystems, including beach sand, water, and the coastal phyllosphere. The accumulation of people on beaches promotes the development and transmission of yeasts, posing an increasing sanitary and epidemiological risk. The aim of this study was to determine the species and quantitative composition of potentially pathogenic and pathogenic yeasts for humans present in the sand of supervised and unsupervised beaches along the shores of lakes in the city of Olsztyn (northeastern Poland). The study material consisted of sand samples collected during two summer seasons (2019; 2020) from 12 research sites on sandy beaches of four lakes located within the administrative boundaries of Olsztyn. Standard isolation and identification methods used in diagnostic mycological laboratories were applied and are described in detail in the following sections of this study. A total of 259 yeast isolates (264, counting species in two-species isolates separately) belonging to 62 species representing 47 genera were obtained during the study. Among all the isolates, five were identified as mixed (two species from a single colony). Eight isolated species were classified into biosafety level 2 (BSL-2) and risk group 2 (RG-2). The highest average number of viable yeast cells was found in sand samples collected in July 2019 (5.56 × 10² CFU/g), August, and September 2020 (1.03 × 10³ CFU/g and 1.94 × 10³ CFU/g, respectively). The lowest concentrations were in samples collected in April, September, and October 2019, and October 2020 (1.48 × 10² CFU/g, 1.47 × 10² CFU/g, 1.40 × 10² CFU/g, and 1.40 × 10² CFU/g, respectively). The results indicate sand contamination with yeasts that may pose etiological factors for human mycoses. In light of these findings, continuous sanitary-epidemiological monitoring of beach sand and further studies on its mycological cleanliness are warranted, along with actions leading to appropriate legal regulations. Full article

Creating high-fidelity digital twins (DTs) for Industry 4.0 applications, it is fundamentally reliant on the accurate 3D modeling of physical assets, a task complicated by the inherent imperfections of real-world point cloud data. This paper addresses the challenge of reconstructing accurate, watertight, and topologically sound 3D meshes from sparse, noisy, and incomplete point clouds acquired in complex industrial environments. We introduce a robust two-stage completion-to-reconstruction framework, C2R3D-Net, that systematically tackles this problem. The methodology first employs a pretrained, self-supervised point cloud completion network to infer a dense and structurally coherent geometric representation from degraded inputs. Subsequently, a novel adaptive surface reconstruction network generates the final high-fidelity mesh. This network features a hybrid encoder (FKAConv-LSA-DC), which integrates fixed-kernel and deformable convolutions with local self-attention to robustly capture both coarse geometry and fine details, and a boundary-aware multi-head interpolation decoder, which explicitly models sharp edges and thin structures to preserve geometric fidelity. Comprehensive experiments on the large-scale synthetic ShapeNet benchmark demonstrate state-of-the-art performance across all standard metrics. Crucially, we validate the framework’s strong zero-shot generalization capability by deploying the model—trained exclusively on synthetic data—to reconstruct complex assets from a custom-collected industrial dataset without any additional fine-tuning. The results confirm the method’s suitability as a robust and scalable approach for 3D asset modeling, a critical enabling step for creating high-fidelity DTs in demanding, unseen industrial settings. Full article

Water body detection in synthetic aperture radar (SAR) imagery plays a critical role in applications such as disaster response, water resource management, and environmental monitoring. However, it remains challenging due to complex background interference in SAR images. To address this issue, a bi-encoder and hybrid feature fuse network (BiEHFFNet) is proposed for achieving accurate water body detection. First, a bi-encoder structure based on ResNet and Swin Transformer is used to jointly extract local spatial details and global contextual information, enhancing feature representation in complex scenarios. Additionally, the convolutional block attention module (CBAM) is employed to suppress irrelevant information of the output features of each ResNet stage. Second, a cross-attention-based hybrid feature fusion (CABHFF) module is designed to interactively integrate local and global features through cross-attention, followed by channel attention to achieve effective hybrid feature fusion, thus improving the model’s ability to capture water structures. Third, a multi-scale content-aware upsampling (MSCAU) module is designed by integrating atrous spatial pyramid pooling (ASPP) with the Content-Aware ReAssembly of FEatures (CARAFE), aiming to enhance multi-scale contextual learning while alleviating feature distortion caused by upsampling. Finally, a composite loss function combining Dice loss and Active Contour loss is used to provide stronger boundary supervision. Experiments conducted on the ALOS PALSAR dataset demonstrate that the proposed BiEHFFNet outperforms existing methods across multiple evaluation metrics, achieving more accurate water body detection. Full article

Dissolved gas analysis remains the most widely utilized non-intrusive diagnostic method for detecting incipient faults in insulating liquid-immersed transformers. Despite their prevalence, conventional ratio-based methods often suffer from ambiguity and limited potential for automation applicrations. To address these limitations, this study proposes a unified multiclass classification model that integrates traditional gas ratio features with supervised machine learning algorithms to enhance fault diagnosis accuracy. The performance of six machine learning classifiers was systematically evaluated using training and testing data generated through four widely recognized gas ratio schemes. Grid search optimization was employed to fine-tune the hyperparameters of each model, while model evaluation was conducted using 10-fold cross-validation and six performance metrics. Across all the diagnostic approaches, ensemble models, namely random forest, XGBoost, and LightGBM, consistently outperformed non-ensemble models. Notably, random forest and LightGBM classifiers demonstrated the most robust and superior performance across all schemes, achieving accuracy, precision, recall, and F1 scores between 0.99 and 1, along with Matthew correlation coefficient values exceeding 0.98 in all cases. This robustness suggests that ensemble models are effective at capturing complex decision boundaries and relationships among gas ratio features. Furthermore, beyond numerical classification, the integration of physicochemical and dielectric properties in this study revealed degradation signatures that strongly correlate with thermal fault indicators. Particularly, the CIGRÉ-based classification using a random forest classifier demonstrated high sensitivity in detecting thermally stressed units, corroborating trends observed in chemical deterioration parameters such as interfacial tension and CO₂/CO ratios. Access to over 80 years of operational data provides a rare and invaluable perspective on the long-term performance and degradation of power equipment. This extended dataset enables a more accurate assessment of ageing trends, enhances the reliability of predictive maintenance models, and supports informed decision-making for asset management in legacy power systems. Full article

The incorporation of renewable energy sources in power grids has necessitated innovative solutions for effective energy management. Smart grids have emerged as transformative systems which integrate consumer, generator and dual-role entities to deliver secure, sustainable and economical electricity supplies. This review explores the important role of artificial intelligence and machine learning approaches in managing the developing stability characteristics of smart grids. This work starts with a discussion of the smart grid’s dynamic structures and subsequently transitions into an overview of machine learning approaches that explore various algorithms and their applications to enhance smart grid operations. A comprehensive analysis of frameworks illustrates how machine learning and artificial intelligence solve issues related to distributed energy supplies, load management and contingency planning. This review includes general pseudocode and schematic architectures of artificial intelligence and machine learning methods which are categorized into supervised, semi-supervised, unsupervised and reinforcement learning. It includes support vector machines, decision trees, artificial neural networks, extreme learning machines and probabilistic graphical models, as well as reinforcement strategies like dynamic programming, Monte Carlo methods, temporal difference learning and Deep Q-networks, etc. Examination extends to stability, voltage and frequency regulation along with fault detection methods that highlight their applications in increasing smart grid operational boundaries. The review underlines the various arrays of machine learning algorithms that emphasize the integration of reinforcement learning as a pivotal enhancement in intelligent decision-making within smart grid environments. As a resource this review offers insights for researchers, practitioners and policymakers by providing a roadmap for leveraging intelligent technologies in smart grid control and stability analysis. Full article

The high dimensionality of hyperspectral data, coupled with limited labeled samples and complex scene structures, makes spatial–spectral feature learning particularly challenging. To address these limitations, we propose a dual-branch deep learning framework named MSDCA, which performs spatial–spectral joint modeling under limited supervision. First, a multiscale 3D spatial–spectral feature extraction module (3D-SSF) employs parallel 3D convolutional branches with diverse kernel sizes and dilation rates, enabling hierarchical modeling of spatial–spectral representations from large-scale patches and effectively capturing both fine-grained textures and global context. Second, a multi-branch directional feature module (MBDFM) enhances the network’s sensitivity to directional patterns and long-range spatial relationships. It achieves this by applying axis-aware depthwise separable convolutions along both horizontal and vertical axes, thereby significantly improving the representation of spatial features. Finally, the enhanced cross-attention Transformer encoder (ECATE) integrates a dual-branch fusion strategy, where a cross-attention stream learns semantic dependencies across multi-scale tokens, and a residual path ensures the preservation of structural integrity. The fused features are further refined through lightweight channel and spatial attention modules. This adaptive alignment process enhances the discriminative power of heterogeneous spatial–spectral features. The experimental results on three widely used benchmark datasets demonstrate that the proposed method consistently outperforms state-of-the-art approaches in terms of classification accuracy and robustness. Notably, the framework is particularly effective for small-sample classes and complex boundary regions, while maintaining high computational efficiency. Full article

Camouflaged object detection (COD) aims to detect objects that seamlessly integrate with their surrounding environment and are thereby intractable to distinguish from the background. Existing approaches face difficulties in dynamically adapting to scenarios where the foreground closely resembles the background. Additionally, these methods primarily rely on single-domain boundary supervision while overlooking multi-dimensional constraints, leading to indistinct object boundaries. Inspired by the hawk’s visual predation mechanism, namely, global perception and local refinement, we design an innovative two-stage boundary-aware network, namely, SFNet, which relies on supervision in the spatial-frequency domains. In detail, to simulate the global perception mechanism, we design a multi-scale dynamic attention module to capture contextual relationships between camouflaged objects and surroundings and to enhance key feature representation. In the local refinement stage, we introduce a dual-domain boundary supervision mechanism that jointly optimizes boundaries in frequency and spatial domains, along with an adaptive gated boundary guided module to maintain global semantic consistency. Extensive experiments on four camouflaged object detection datasets demonstrate that SFNet surpasses state-of-the-art methods by 4.1%, with lower computational overhead and memory costs. Full article

Prompt and precise cropland mapping is indispensable for safeguarding food security, enhancing land resource utilization, and advancing sustainable agricultural practices. Conventional approaches faced difficulties in complex terrain marked by fragmented plots, pronounced elevation differences, and non-uniform field borders. To address these challenges, we propose DAENet, a novel deep learning framework designed for accurate cropland extraction from high-resolution GaoFen-1 (GF-1) satellite imagery. DAENet employs a novel Geometric-Optimized and Boundary-Restrained (GOBR) Block, which combines channel attention, multi-scale spatial attention, and boundary supervision mechanisms to effectively mitigate challenges arising from disjointed cropland parcels, topography-cast shadows, and indistinct edges. We conducted comparative experiments using 8 mainstream semantic segmentation models. The results demonstrate that DAENet achieves superior performance, with an Intersection over Union (IoU) of 0.9636, representing a 4% improvement over the best-performing baseline, and an F1-score of 0.9811, marking a 2% increase. Ablation analysis further validated the indispensable contribution of GOBR modules in improving segmentation precision. Using our approach, we successfully extracted 25,556.98 hectares of cropland within the study area, encompassing a total of 67,850 individual blocks. Additionally, the proposed method exhibits robust generalization across varying spatial resolutions, underscoring its effectiveness as a high-accuracy solution for agricultural monitoring and sustainable land management in complex terrain. Full article

Accurate segmentation of the ventricular region in embryonic heart videos of medaka fish (Oryzias latipes) holds significant scientific value for research on heart development mechanisms. However, existing medaka ventricular datasets are overly simplistic and fail to meet practical application requirements. And the video frames contain multiple complex interfering factors, including optical interference from the filming environment, dynamic color changes caused by blood flow, significant diversity in ventricular scales, image blurring in certain video frames, high similarity in organ structures, and indistinct boundaries between the ventricles and atria. These challenges mean existing methods still face notable technical difficulties in medaka embryonic ventricular segmentation tasks. To address these challenges, this study first constructs a medaka embryonic ventricular video dataset containing 4200 frames with pixel-level annotations. Building upon this, we propose a semi-supervised video segmentation model based on the hierarchical propagation feature decoupling framework (DeAOT) and innovatively design an architecture that combines the LA-ResNet encoder with the AFPViS decoder, significantly improving the accuracy of medaka ventricular segmentation. Experimental results demonstrate that, compared to the traditional U-Net model, our method achieves a 13.48% improvement in the mean Intersection over Union (mIoU) metric. Additionally, compared to the state-of-the-art DeAOT method, it achieves a notable 4.83% enhancement in the comprehensive evaluation metric Jaccard and F-measure (J&F), providing reliable technical support for research on embryonic heart development. Full article

Accurate clustering of buildings is a prerequisite for map generalization in densely populated urban data. Edge buildings at the edge of building groups, identified through human-eye recognition, may serve as boundary constraints for clustering. This paper proposes the use of seven Gestalt factors to distinguish edge buildings from other buildings. Employing the DGI model to produce high-quality node embeddings, optimize the mutual information between the local node representation and the global summary vector. We then conduct training to identify edge buildings in the two test datasets using eight feature combinations. This research introduces a modified distance metric called the ‘m_dis’ feature, which is used to describe the closeness between two adjacent buildings. Finally, the clusters of edge and inner buildings are determined through a constrained graph traversal that is based on the ‘m_dis’ feature. This method is capable of effectively identifying and distinguishing densely distributed building groups in Chengdu City, China, as demonstrated by experimental results. It offers novel concepts for edge building recognition in dense urban areas, confirms the significance of the LOF factor and the ‘m_dis’ feature, and achieves superior clustering results in comparison to other methods. Additionally, this semi-supervised clustering method (DGI-EIC) has the potential to achieve an ARI index of approximately 0.5. Full article

Data corruption, including missing and noisy entries, is a common challenge in real-world machine learning. This paper examines its impact and mitigation strategies through two experimental setups: supervised NLP tasks (NLP-SL) and deep reinforcement learning for traffic signal control (Signal-RL). This study analyzes how varying corruption levels affect model performance, evaluate imputation strategies, and assess whether expanding datasets can counteract corruption effects. The results indicate that performance degradation follows a diminishing-return pattern, well modeled by an exponential function. Noisy data harm performance more than missing data, especially in sequential tasks like Signal-RL where errors may compound. Imputation helps recover missing data but can introduce noise, with its effectiveness depending on corruption severity and imputation accuracy. This study identifies clear boundaries between when imputation is beneficial versus harmful, and classifies tasks as either noise-sensitive or noise-insensitive. Larger datasets reduce corruption effects but offer diminishing gains at high corruption levels. These insights guide the design of robust systems, emphasizing smart data collection, imputation decisions, and preprocessing strategies in noisy environments. Full article

Camouflaged object detection (COD) encounters substantial difficulties owing to the visual resemblance between targets and their environments, together with discrepancies in multiscale representation of features. Current methodologies confront obstacles with feature distraction, modeling far-reaching dependencies, fusing multiple-scale details, and extracting boundary specifics. Consequently, we propose ATDMNet, an amalgamated architecture combining CNN and transformer within a numerous phases feature extraction framework. ATDMNet employs Res2Net as the foundational encoder and incorporates two essential components: multi-head agent attention (MHA) and top-k dynamic mask (TDM). MHA improves local feature sensitivity and long-range dependency modeling by incorporating agent nodes and positional biases, whereas TDM boosts attention with top-k operations and multiscale dynamic methods. The decoding phase utilizes bilinear upsampling and sophisticated semantic guidance to enhance low-level characteristics, hence ensuring precise segmentation. Enhanced performance is achieved by deep supervision and a hybrid loss function. Experiments applying COD datasets (NC4K, COD10K, CAMO) demonstrate that ATDMNet establishes a new benchmark in both precision and efficiency. Full article

Current weakly supervised salient object detection (SOD) methods for RGB-D images mostly rely on image-level labels and sparse annotations, which makes it difficult to completely contour object boundaries in complex scenes, especially when detecting objects with filamentary structures. To address the aforementioned issues, we propose a novel cross-modal weakly supervised SOD framework. The framework can adequately exploit the advantages of cross-modal weak labels to generate high-quality pseudo-labels, and it can fully couple the multi-scale features of RGB and depth images for precise saliency prediction. The framework mainly consists of a cross-modal pseudo-label generation network (CPGN) and an asymmetric salient-region prediction network (ASPN). Among them, the CPGN is proposed to sufficiently leverage the precise pixel-level guidance provided by point labels and the enhanced semantic supervision provided by text labels to generate high-quality pseudo-labels, which are used to supervise the subsequent training of the ASPN. To better capture the contextual information and geometric features from RGB and depth images, the ASPN, an asymmetrically progressive network, is proposed to gradually extract multi-scale features from RGB and depth images by using the Swin-Transformer and CNN encoders, respectively. This significantly enhances the model’s ability to perceive detailed structures. Additionally, an edge constraint module (ECM) is designed to sharpen the edges of the predicted salient regions. The experimental results demonstrate that the method shows better performance in depicting salient objects, especially the filamentary structures, than other weakly supervised SOD methods. Full article

Medical assistance in dying (MAID) remains a sensitive and evolving issue in Europe, frequently linked with discussions about human freedom, life dignity, and healthcare policy. While national consensus in Italy is absent, the Region of Tuscany has enacted Law No. 16/2025, which establishes a MAID procedure based on recent Constitutional Court rulings. The commentary aims to provide a preliminary analysis of the new law, addressing ethical, medico-legal, and social issues that emerge in relation to the Italian and global debate on the topic. The law establishes a three-stage process based on four eligibility criteria: irreversible disease, psycho-physical suffering, life-support dependence, and informed consent. However, Tuscany’s model poses medico-legal and ethical concerns, particularly about the boundaries of regional legislative competence, the duties of healthcare professionals, and the possibility of intra-national inequity or “health migration.” In addition, critical organisational implications derived from informed consent and lethal drug self-administration impede clinical implementation in some individuals with mental or neurological disorders. The lack of clarity in the different steps of the procedure, the uncertain supervision system, and the potential consequences for specific categories of vulnerable people underline the need for comprehensive national regulation. A future regulatory framework must balance procedural clarity with individual autonomy and equitable access, bringing Italy in line with larger European context for end-of-life care. Full article