Search Results (1,875)

Purpose: The pulmonary function test holds significant clinical value in assessing the severity, prognosis, and treatment efficacy of respiratory diseases. However, the test is limited by patient compliance, thereby limiting its practical application. Moreover, it only reflects the current state of the patient and cannot directly indicate future health trends or prognosis. Computational fluid dynamics (CFD), combined with airway models built from medical image data, can assist in analyzing a patient’s ventilation function, thus addressing the aforementioned issues. However, current airway models have shortcomings in accurately representing the structural features of a patient’s airway. Additionally, these models exhibit geometric defects such as low smoothness, topological errors, and noise, which further reduce their usability. This study generates airway skeletons based on CT data and, in combination with convolutional surface technology, proposes an individualized airway modeling method to solve these deficiencies. This study also provides a method for predicting a patient’s lung function based on the constructed airway model and using CFD simulation technology. This study also explores the application of this method in preoperative prediction of the required extent of airway expansion for patients with large airway stenosis. Methods: Based on airway skeleton data extracted from patient CT images, a personalized airway model is constructed using convolutional surface technology. The airway model is simulated according to the patient’s clinical statistical values of pulmonary function to obtain airway simulation data. Finally, a regression equation is constructed between the patient’s measured pulmonary function values and the airway simulation data to predict the patient’s pulmonary function values based on the airway simulation data. Results: To preliminarily demonstrate the above method, this study used the prediction of FEV1 in patients with large airway stenosis as an example for a proof-of-concept study. A linear regression model was constructed between the outlet flow rate from the simulation of the stenosed airway and the patient’s measured FEV1 values. The linear regression model achieved a prediction result of RMSE = 0.0246 and R² = 0.9822 for the test set. Additionally, preoperative predictions were made for the degree of airway dilation needed for patients with large airway stenosis. According to the linear regression model, the proportion of airway radius expansion required at the stenotic position to achieve normal FEV1 was calculated as 72.86%. Conclusions: This study provides a method for predicting patient pulmonary function based on CFD simulation technology and convolutional surface technology. This approach addresses, to some extent, the limitations in pulmonary function testing and accuracy caused by patient compliance. Meanwhile, this study provides a method for preoperative evaluation of airway dilation therapy. Full article

Extracting road network information from satellite remote sensing images is an effective method of dealing with dynamic changes in road networks. At present, the use of deep learning methods to automatically segment road networks from remote sensing images has become mainstream. However, existing methods often produce fragmented extraction results. This is usually caused by insufficient feature extraction and occlusion. In order to solve these problems, we propose an enhanced feature extraction and multi-branch occlusion discrimination network (EFMOD-Net) based on an encoder–decoder architecture. Firstly, a multi-directional feature extraction (MFE) module was proposed as the input for the network, which utilizes multi-directional strip convolution for feature extraction to better capture the linear features of the road. Subsequently, an enhanced feature extraction (EFE) module was designed to enhance the performance of the model in the feature extraction stage by using a dual-branch structure. The proposed multi-branch occlusion discrimination (MOD) module combines the attention mechanism and strip convolution to learn the topological relationship between pixels, enhance the network’s detection of occlusion and complex backgrounds, and reduce the generation of road debris. On the public dataset, the proposed method is compared with other SOTA methods. The experimental results show that the network designed in this paper achieves an IoU of 64.73 and 63.58 on the DeepGlobe and CHN6-CUG datasets, respectively, which is 1.66% and 1.84% higher than the IoU of performance-based methods. The proposed method combines multi-directional bar convolution and a multi-branch structure for road extraction, which provides a new idea for linear object segmentation in complex backgrounds that could be applied directly to urban renewal, disaster assessment, and other application scenarios. Full article

The line structure is an efficient form of representation and modeling for LiDAR point clouds, while the Line Structure Construction (LSC) method aims to extract complete and coherent line structures from complex 3D point clouds, thereby providing a foundation for geometric modeling, scene understanding, and downstream applications. However, traditional LSC methods often fall short in preserving both the geometric integrity and topological connectivity of line structures derived from such datasets. To address this issue, we propose the Geometry and Topology Preservable Line Structure Construction (GTP-LSC) method, based on the Encoding and Extracting Framework (EEF). First, in the encoding phase, point cloud features related to line structures are mapped into a high-dimensional feature space. A 3D U-Net is then employed to compute Subsets with Structure feature of Line (SSL) from the dense, unstructured, and noisy indoor LiDAR point cloud data. Next, in the extraction phase, the SSL is transformed into a 3D field enriched with line features. Initially extracted line structures are then constructed based on Morse theory, effectively preserving the topological relationships. In the final step, these line structures are optimized using RANdom SAmple Consensus (RANSAC) and Constructive Solid Geometry (CSG) to ensure geometric completeness. This step also facilitates the generation of complex entities, enabling an accurate and comprehensive representation of both geometric and topological aspects of the line structures. Experiments were conducted using the Indoor Laser Scanning Dataset, focusing on the parking garage (D₁), the corridor (D₂), and the multi-room structure (D₃). The results demonstrated that the proposed GTP-LSC method outperformed existing approaches in terms of both geometric integrity and topological connectivity. To evaluate the performance of different LSC methods, the IoU Buffer Ratio (IBR) was used to measure the overlap between the actual and constructed line structures. The proposed method achieved IBR scores of 92.5% (D₁), 94.2% (D₂), and 90.8% (D₃) for these scenes. Additionally, Precision, Recall, and F-Score were calculated to further assess the LSC results. The F-Score of the proposed method was 0.89 (D₁), 0.92 (D₂), and 0.89 (D₃), demonstrating superior performance in both visual analysis and quantitative results compared to other methods. Full article

The aromaticity of small boron clusters remains under scrutiny due to persistent inconsistencies between magnetic and electronic descriptors. Here, we reexamine B₃⁻, B₃⁺, B₄, B₄²⁺, and B₄²⁻ using a multidimensional approach that integrates Adaptive Natural Density Partitioning, Electron Density of Delocalized Bonds, magnetically induced current density, and the z-component of the induced magnetic field. We introduce a model in which σ-aromaticity arises from two distinct delocalization topologies: a radial 2e⁻ σ-pathway and a tangential multicenter circuit formed by alternating filled and vacant sp² orbitals. This framework accounts for the evolution of aromaticity upon oxidation or reduction, preserving coherence between electronic structure and magnetic response. B₃⁻ features cooperative radial and tangential σ-delocalization, together with a delocalized 2e⁻ π-bond, yielding robust double aromaticity. B₃⁺ retains σ- and π-aromaticity, but only via a tangential 6e⁻ σ-framework, leading to a more compact delocalization and slightly attenuated ring currents. In B₄, the presence of a radial 2e⁻ σ-bond and a 4c–2e π-bond confers partial aromatic character, while the tangential 8e⁻ σ-framework satisfies the 4n rule and induces a paratropic current. In contrast, B₄²⁺ lacks the radial σ-component but retains a tangential 8e⁻ σ-circuit and a 2e⁻ 4c–2e π-bond, leading to a σ-antiaromatic and π-aromatic configuration. Finally, B₄²⁻, exhibits delocalized π- and σ-circuits, yielding consistent diatropic ring currents, which confirms its fully doubly aromatic nature. Altogether, this analysis underscores the importance of resolving σ-framework topology and demonstrates that, when radial and tangential contributions are correctly distinguished, Hückel’s rule remains a powerful tool for interpreting aromaticity in small boron rings. Full article

In air–ground cooperative systems, identifying the identities of unmanned ground vehicles (UGVs) from an unmanned aerial vehicle (UAV) perspective is a critical step for downstream tasks. Traditional approaches involving attaching markers, like AprilTags on UGVs, fail under low-resolution or occlusion conditions, and the visually identical UGVs are hard to distinguish through similar visual features. This paper proposes a markerless method that associates UGV onboard sensor data with UAV visual detections to achieve identification. Our approach employs a Dempster–Shafer fused methodology integrating two proposed complementary association techniques: a projection-based method exploiting sequential motion patterns through reprojection error validation, and a topology-based method constructing distinctive topology using positional and orientation data. The association process is further integrated into a multi-object tracking framework to reduce ID switches during occlusions. Experiments demonstrate that under low-noise conditions, the projection-based method and the topology-based method achieves association precision at 89.5% and 87.6% respectively, which is superior to the previous methods. The fused approach enables robust association at 79.9% precision under high noise conditions, nearly 10% higher than original performance. Under false detection scenarios, our method achieves effective false-positive exclusion, and the integrated tracking process effectively mitigates occlusion-induced ID switches. Full article

Fatigue in air traffic controllers (ATCOs), particularly within remote tower operations, poses a substantial risk to aviation safety due to its detrimental effects on vigilance, decision-making, and situational awareness. While electroencephalography (EEG) provides a promising avenue for objective fatigue monitoring, existing models often fail to adequately capture both the spatial dependencies across brain regions and the temporal dynamics of cognitive states. To address this challenge, we propose a novel EEG-based fatigue detection framework, Spatio-Temporal Graph with Center Loss Network (STG-CLNet), which jointly models topological brain connectivity and temporal EEG evolution. The model leverages a multi-stage graph convolutional network to encode spatial dependencies and a triple-layer LSTM module to capture temporal progression, while incorporating center loss to enhance feature discriminability in the embedding space. We constructed a domain-specific EEG dataset involving 34 ATCO participants operating in high- and low-traffic remote tower simulations, with fatigue labels derived from three validated subjective metrics. Experimental results demonstrate that STG-CLNet achieves superior classification performance (accuracy = 96.73%, recall = 92.01%, F1-score = 87.15%), outperforming several strong baselines, including LSTM and EEGNet. These findings underscore the potential of STG-CLNet for integration into real-time cognitive monitoring systems in air traffic control, contributing to both theoretical advancement and operational safety enhancement. Full article

Background: Traditional morphology-based classification of the Oriental Plover (Anarhynchus veredus) is inconsistent with molecular evidence, underscoring the necessity of incorporating molecular data to elucidate its evolutionary relationships within Charadriidae. Methods: Here, we present the first complete mitochondrial genome of A. veredus by Illumina NovaSeq Sequencing and explore its evolutionary implications within Charadriidae. Results: The mitogenome spans 16,886 bp and exhibits conserved structural features typical of Charadriidae, including gene order, overlapping coding regions, and intergenic spacers. Nucleotide composition analysis revealed a GC content of 44.3%, aligning with other Charadriidae species (44.5–45.8%), and hierarchical GC distribution across rRNA, tRNA, and protein-coding genes (PCGs) reflects structural and functional optimization. Evolutionary rate heterogeneity was observed among PCGs, with ATP8 and ND6 showing accelerated substitution rates (Ka/Ks = 0.1748 and 0.1352) and COX2 under strong purifying selection (Ka/Ks = 0.0678). Notably, a conserved translational frameshift in ND3 (position 174) was identified. Phylogenetic analyses (ML/NJ) of 88 Charadriiformes species recovered robust topologies, confirming that the division of Charadriidae into four monophyletic clades (Pluvialis, Vanellus, Charadrius, and Anarhynchus) and supporting the reclassification of A. veredus under Anarhynchus. Conclusions: This study resolves the systematic position of A. veredus and highlights the interplay between conserved mitochondrial architecture and lineage-specific adaptations in shaping shorebird evolution. Full article

This work presents a novel Graph Neural Network (GNN) based framework for structural damage detection and localization in composite aerospace structures. The sensor network is modeled as a graph whose nodes correspond to the strain measurement points placed on the system, while the edges capture spatial and structural relationships among sensors. Strain mode shapes, extracted via Automated Operational Modal Analysis (AOMA), are used as input features for the GNN. Two architectures are developed: one for binary damage detection and another for damage localization, the latter outputting a spatial probability distribution of damage over the structure. Both networks are trained and validated on synthetic datasets generated from high-fidelity finite element transient simulations performed on a composite wing equipped with 40 strain sensors. The obtained results show strong effectiveness in both detection and localization tasks, thus highlighting the potential of leveraging GNNs for topology-aware Structural Health Monitoring applications. In particular, the proposed framework achieves an AUC of 0.97 for damage detection and a mean localization error of approximately 3% of the wingspan on the synthetic dataset. The performance of the GNN is also compared with a fully connected and a convolutional neural network, demonstrating significant improvements in the localization accuracy. Full article

The narrative structure of animated films plays a critical role in shaping audience perception, yet quantitative investigations into how character interaction networks influence film ratings remain limited. To address this gap, we apply complex network theory to analyze 82 animated films, extracting character networks from narrative interactions and examining key topological features—including centrality heterogeneity, protagonist relative centrality, network density, clustering coefficient, average shortest path length, and semantic diversity of relationships. Our findings demonstrate that higher-rated films are characterized by greater disparities in character centrality, lower network density and efficiency, longer average shortest path lengths, and richer semantic diversity. These structural patterns suggest that loosely connected yet hierarchically organized character networks enhance narrative complexity and audience engagement. The proposed framework offers a quantitative, data-driven approach to narrative design and provides a theoretical foundation for analyzing storytelling structures across diverse media, including novels, television series, and comics. Full article

Functional near-infrared spectroscopy (fNIRS) offers a safe and portable signal source for brain–computer interface (BCI) applications, particularly in motor imagery (MI) decoding. However, its low sampling rate and hemodynamic delay pose challenges for temporal modeling and dynamic brain network analysis. To address these limitations in temporal dynamics, static graph modeling, and feature fusion interpretability, we propose TopoTempNet, an innovative topology-enhanced temporal network for biomedical signal decoding. TopoTempNet integrates multi-level graph features with temporal modeling through three key innovations: (1) multi-level topological feature construction using local and global functional connectivity metrics (e.g., connection strength, density, global efficiency); (2) a graph-modulated attention mechanism combining Transformer and Bi-LSTM to dynamically model key connections; and (3) a multimodal fusion strategy uniting raw signals, graph structures, and temporal representations into a high-dimensional discriminative space. Evaluated on three public fNIRS datasets (MA, WG, UFFT), TopoTempNet achieves superior accuracy (up to 90.04% ± 3.53%) and Kappa scores compared to state-of-the-art models. The ROC curves and t-SNE visualizations confirm its excellent feature discrimination and structural clarity. Furthermore, the statistical analysis of graph features reveals the model’s ability to capture task-specific functional connectivity patterns, enhancing the interpretability of decoding outcomes. TopoTempNet provides a novel pathway for building interpretable and high-performance BCI systems based on fNIRS. Full article

Enterprise bankruptcy prediction is a critical task in financial risk management. Traditional methods, such as logistic regression and decision trees, rely heavily on structured financial data, which limits their ability to capture complex relational networks and unstructured industry information. Heterogeneous graph neural networks (HGNNs) offer a solution by modeling multiple relationships between enterprises. However, current models struggle with financial risk graph data challenges, such as the oversimplification of internal financial features and the lack of dynamic imputation for missing external topological features. To address these issues, we propose HGNN-EBP, an enterprise bankruptcy prediction algorithm that integrates both internal and external features. The model constructs a multi-relational heterogeneous graph that combines structured financial data, unstructured textual information, and real-time industry data. A multi-scale graph convolution network captures diverse relationships, while a Transformer-based self-attention mechanism dynamically imputes missing external topological features. Finally, a multi-layer perceptron (MLP) predicts bankruptcy probability. Experimental results on a dataset of 32,459 Chinese enterprises demonstrate that HGNN-EBP outperforms traditional models, especially in handling relational diversity, missing features, and dynamic financial risk data. Full article

The precise mapping of rock joint traces is fundamental to the design and safety assessment of foundations, retaining structures, and underground cavities in building and civil engineering. Existing deep learning approaches either impose prohibitive computational demands for on-site deployment or disrupt the topological continuity of subpixel lineaments that govern rock mass behavior. This study presents BATNet-Lite, a lightweight encoder–decoder architecture optimized for joint segmentation on resource-constrained devices. The encoder introduces a Boundary-Aware Token-Mixing (BATM) block that separates feature maps into patch tokens and directionally pooled stripe tokens, and a bidirectional attention mechanism subsequently transfers global context to local descriptors while refining stripe features, thereby capturing long-range connectivity with negligible overhead. A complementary Multi-Scale Line Enhancement (MLE) module combines depth-wise dilated and deformable convolutions to yield scale-invariant responses to joints of varying apertures. In the decoder, a Skeletal-Contrastive Decoder (SCD) employs dual heads to predict segmentation and skeleton maps simultaneously, while an InfoNCE-based contrastive loss enforces their topological consistency without requiring explicit skeleton labels. Training leverages a composite focal Tversky and edge IoU loss under a curriculum-thinning schedule, improving edge adherence and continuity. Ablation experiments confirm that BATM, MLE, and SCD each contribute substantial gains in boundary accuracy and connectivity preservation. By delivering topology-preserving joint maps with small parameters, BATNet-Lite facilitates rapid geological data acquisition for tunnel face mapping, slope inspection, and subsurface digital twin development, thereby supporting safer and more efficient building and underground engineering practice. Full article

There is voluminous literature concerning the scope of topological relations that span various embedding spaces from ${\mathbb{R}}^1$ to ${\mathbb{R}}^2$, ${\mathbb{Z}}^2$ , ${\mathbb{S}}^1$ and ${\mathbb{S}}^2$ , and ${\mathbb{T}}^2$. In the case of the ${*}^1$ spaces, those relations have been considered as conceptualizations of both spatial relations and temporal relations. Missing from that list are the set of digital relations that exist within ${\mathbb{Z}}^1$ , representing discretized time, discretized ordered line segments, or discretized linear features as embedding spaces. Discretized time plays an essential role in timeseries data, spatio-temporal information systems, and geo-foundation models where time is represented in layers of consecutive spatial rasters and/or spatial vector objects colloquially referred to as space–time cubes or spatio-temporal stacks. This paper explores the digital relations that exist in ${\mathbb{Z}}^1$ interpreted as a regular topological space under the digital Jordan curve model as well as a folded-over temporal interpretation of that space for use in spatio-temporal information systems and geo-foundation models. The digital Jordan curve model represents the maximum expressive power between discretized objects, making it the ideal paradigm for a decision support system model. It identifies 34 9-intersection relations in ${\mathbb{Z}}^1$ , 42 9-intersection + margin relations in ${\mathbb{Z}}^1$ , and 74 temporal relations in ${\mathbb{Z}}^1$ , utilizing the 9+-intersection, the commercial standard for spatial information systems for querying topological relations. This work creates opportunities for better spatio-temporal reasoning capacity within spatio-temporal stacks and a more direct interface with intuitive language concepts, instrumental for effective utilization of spatial tools. Three use cases are demonstrated in the discussion, representing each of the utilities of ${\mathbb{Z}}^1$ within the spatial data science community. Full article

This paper investigates the oscillatory effect of a single blade on the turbulence wake downstream of a low-pressure turbine cascade. Experimental investigations were conducted at a chord-based Reynolds number of $2.3\times {10}^5$ with an excitation frequency of 73 Hz. The experimental campaign encompassed two incidence angles (−3° and +6°) and three blade motion conditions: stationary, bending, and torsional vibrations. Turbulence characteristics were analyzed using hot-wire anemometry. The results indicate that the bending mode notably alters the wake topology, causing a 5% decline in streamwise velocity deficit compared to other modes. Additionally, the bending motion promotes the formation of large-scale coherent vortices within the wake, increasing the integral length scale by 7.5 times. In contrast, Kolmogorov’s microscale stays mostly unaffected by blade oscillations. However, increasing the incidence angle causes the smallest eddies in the inter-blade region to grow three times larger. Moreover, the data indicate that at −3°, bending-mode results in an approximate 13% reduction in the turbulence energy dissipation rate compared to the stationary configuration. Furthermore, the study emphasizes the spectral features of turbulent flow and provides a detailed assessment of the Taylor microscale under different experimental conditions. Full article

To tackle the limitations in simultaneously modeling long-term dependencies in the time dimension and nonlinear interactions in the feature dimension, as well as their inability to fully reflect the impact of real-time load changes on spatial dependencies, a short-term multi-energy load forecasting method based on Transformer Spatio-Temporal Graph neural network (TSTG) is proposed. This method employs a multi-head spatio-temporal attention module to model long-term dependencies in the time dimension and nonlinear interactions in the feature dimension in parallel across multiple subspaces. Additionally, a dynamic adaptive graph convolution module is designed to construct adaptive adjacency matrices by combining physical topology and feature similarity, dynamically adjusting node connection weights based on real-time load characteristics to more accurately characterize the spatial dynamics of multi-energy interactions. Furthermore, TSTG adopts an end-to-end spatio-temporal joint optimization framework, achieving synchronous extraction and fusion of spatio-temporal features through an encoder–decoder architecture. Experimental results show that TSTG significantly outperforms existing methods in short-term load forecasting tasks, providing an effective solution for refined forecasting in integrated energy systems. Full article