Search Results (851)

Accurate fault diagnosis in aerospace transmission systems is essential for ensuring equipment reliability and operational safety, especially for aero-engine bearings. However, current approaches relying on Convolutional Neural Networks (CNNs) for Euclidean data and Graph Convolutional Networks (GCNs) for non-Euclidean structures struggle to simultaneously capture heterogeneous data properties and complex spatio-temporal dependencies. To address these limitations, we propose a novel Spatial–Temporal Hypergraph Fault Diagnosis framework (STHFD). Unlike conventional graphs that model pairwise relations, STHFD employs hypergraphs to represent high-order spatial–temporal correlations more effectively. Specifically, it constructs distinct spatial and temporal hyperedges to capture multi-scale relationships among fault signals. A type-aware hypergraph learning strategy is then applied to encode these correlations into discriminative embeddings. Extensive experiments on aerospace fault datasets demonstrate that STHFD achieves superior classification performance compared to state-of-the-art diagnostic models, highlighting its potential for enhancing intelligent fault detection in complex aerospace systems. Full article

Kinase is an enzyme responsible for cell signaling and other complex processes. Mutations or changes in kinase can cause cancer and other diseases in humans, including leukemia, neuroblastomas, glioblastomas, and more. Considering these concerns, inhibiting overexpressed or dysregulated kinases through small drug molecules is very important. In the past, many machine learning and deep learning approaches have been used to inhibit unregulated kinase enzymes. In this work, we employ a Graph Neural Network (GNN) to predict the inhibition activities of kinases. A separate Graph Convolution Network (GCN) and combined Graph Convolution and Graph Attention Network (GCN_GAT) are developed and trained on two large datasets (Kinase Datasets 1 and 2) consisting of small drug molecules against the targeted kinase using 10-fold cross-validation. Furthermore, a wide range of molecules are used as independent datasets on which the performance of the models is evaluated. On both independent kinase datasets, our model combining GCN and GAT provides the best evaluation and outperforms previous models in terms of accuracy, Matthews Correlation Coefficient (MCC), sensitivity, specificity, and precision. On the independent Kinase Dataset 1, the values of accuracy, MCC, sensitivity, specificity, and precision are 0.96, 0.89, 0.90, 0.98, and 0.91, respectively. Similarly, the performance of our model combining GCN and GAT on the independent Kinase Dataset 2 is 0.97, 0.90, 0.91, 0.99, and 0.92 in terms of accuracy, MCC, sensitivity, specificity, and precision, respectively. Full article

The COVID-19 pandemic has presented significant challenges to global healthcare, bringing out the urgent need for reliable diagnostic tools. Computed Tomography (CT) scans have proven instrumental in detecting COVID-19-induced lung abnormalities. This study introduces Convolutional Neural Network, Graph Neural Network, and Vision Transformer (ViTGNN), an advanced hybrid model designed to enhance SARS-CoV-2 detection by combining Graph Neural Networks (GNNs) for feature extraction with Vision Transformers (ViTs) for classification. Using the strength of CNN and GNN to capture complex relational structures and the ViT capacity to classify global contexts, ViTGNN achieves a comprehensive representation of CT scan data. The model was evaluated on a SARS-CoV-2 CT scan dataset, demonstrating superior performance across all metrics compared to baseline models. The model achieved an accuracy of 95.98%, precision of 96.07%, recall of 96.01%, F1-score of 95.98%, and AUC of 98.69%, outperforming existing approaches. These results indicate that ViTGNN is an effective diagnostic tool that can be applied beyond COVID-19 detection to other medical imaging tasks. Full article

LiDAR point clouds, as direct carriers of 3D spatial information, comprehensively record the geometric features and spatial topological relationships of object surfaces, providing intelligent systems with rich 3D scene representation capability. However, current point cloud semantic segmentation methods primarily extract features through operations such as convolution and pooling, yet fail to adequately consider sparse features that significantly influence the final results of point cloud-based scene perception, resulting in insufficient feature representation capability. To address these problems, a sparse feature dynamic graph convolutional neural network, abbreviated as SFDGNet, is constructed in this paper for LiDAR point clouds of complex scenes. In the context of this paper, sparse features refer to feature representations in which only a small number of activation units or channels exhibit significant responses during the forward pass of the model. First, a sparse feature regularization method was used to motivate the network model to learn the sparsified feature weight matrix. Next, a split edge convolution module, abbreviated as SEConv, was designed to extract the local features of the point cloud from multiple neighborhoods by dividing the input feature channels, and to effectively learn sparse features to avoid feature redundancy. Finally, a multi-neighborhood feature fusion strategy was developed that combines the attention mechanism to fuse the local features of different neighborhoods and obtain global features with fine-grained information. Taking S3DIS and ScanNet v2 datasets, we evaluated the feasibility and effectiveness of SFDGNet by comparing it with six typical semantic segmentation models. Compared with the benchmark model DGCNN, SFDGNet improved overall accuracy $\left(OA\right)$, mean accuracy $\left(mAcc\right)$, mean intersection over union $\left(mIoU\right)$, and $sparsity$ by $1.8\%$, $3.7\%, 3.5\%$, and $85.5\%$ on the S3DIS dataset, respectively. The $mIoU$ on the ScanNet v2 validation set, $mIoU$ on the test set, and $sparsity$ were improved by $3.2\%, 7.0\%$, and $54.5\%$, respectively. Full article

Mineral prospectivity mapping (MPM) is a pivotal technique in geoscientific mineral resource exploration. To address three critical challenges in current deep convolutional neural network applications for geoscientific mineral resource prediction—(1) model bias induced by imbalanced distribution of ore deposit samples, (2) deficiency in global feature extraction due to excessive reliance on local spatial correlations, and (3) diminished discriminative capability caused by feature smoothing in deep networks—this study innovatively proposes a T-GCN model integrating Transformer with graph convolutional neural networks (GCNs). The model achieves breakthrough performance through three key technological innovations: firstly, constructing a global perceptual field via Transformer’s self-attention mechanism to effectively capture long-range geological relationships; secondly, combining GCNs’ advantages in topological feature extraction to realize multi-scale feature fusion; and thirdly, designing a feature enhancement module to mitigate deep network degradation. In practical application to the PangXD ore district, the T-GCN model achieved a prediction accuracy of 97.27%, representing a 3.76 percentage point improvement over the best comparative model, and successfully identified five prospective mineralization zones, demonstrating its superior performance and application value under complex geological conditions. Full article

This study presents a novel framework that integrates Vision Graph Neural Networks (ViGs) with supervised contrastive learning for enhanced spectro-temporal image analysis of speech signals in Parkinson’s disease (PD) detection. The approach introduces a frequency band decomposition strategy that transforms raw audio into three complementary spectral representations, capturing distinct PD-specific characteristics across low-frequency (0–2 kHz), mid-frequency (2–6 kHz), and high-frequency (6 kHz+) bands. The framework processes mel multi-band spectro-temporal representations through a ViG architecture that models complex graph-based relationships between spectral and temporal components, trained using a supervised contrastive objective that learns discriminative representations distinguishing PD-affected from healthy speech patterns. Comprehensive experimental validation on multi-institutional datasets from Italy, Colombia, and Spain demonstrates that the proposed ViG-contrastive framework achieves superior classification performance, with the ViG-M-GELU architecture achieving 91.78% test accuracy. The integration of graph neural networks with contrastive learning enables effective learning from limited labeled data while capturing complex spectro-temporal relationships that traditional Convolution Neural Network (CNN) approaches miss, representing a promising direction for developing more accurate and clinically viable speech-based diagnostic tools for PD. Full article

Single-cell Assay for Transposase-Accessible Chromatin using sequencing (scATAC-seq) technology enables single-cell resolution analysis of chromatin accessibility, offering critical insights into gene regulation, epigenetic heterogeneity, and cellular differentiation across various biological contexts. However, existing cell annotation methods face notable limitations. Cross-omics approaches, which rely on single-cell RNA sequencing (scRNA-seq) as a reference, often struggle with data alignment due to fundamental differences between transcriptional and chromatin accessibility modalities. Meanwhile, intra-omics methods, which rely solely on scATAC-seq data, are frequently affected by batch effects and fail to fully utilize genomic sequence information for accurate annotation. To address these challenges, we propose scAttG, a novel deep learning framework that integrates graph attention networks (GATs) and convolutional neural networks (CNNs) to capture both chromatin accessibility signals and genomic sequence features. By utilizing the nucleotide sequences corresponding to scATAC-seq peaks, scAttG enhances both the robustness and accuracy of cell-type annotation. Experimental results across multiple scATAC-seq datasets suggest that scAttG generally performs favorably compared to existing methods, showing competitive performance in single-cell chromatin accessibility-based cell-type annotation. Full article

The accurate segmentation of blood vessels and centerline extraction are critical in vascular imaging applications, ranging from preoperative planning to hemodynamic modeling. This study introduces a novel one-stage method for simultaneous vessel segmentation and centerline extraction using a multitask neural network. We designed a hybrid architecture that integrates convolutional and graph layers, along with a task-specific loss function, to effectively capture the topological relationships between segmentation and centerline extraction, leveraging their complementary features. The proposed end-to-end framework directly predicts the centerline as a polyline with real-valued coordinates, thereby eliminating the need for post-processing steps commonly required by previous methods that infer centerlines either implicitly or without ensuring point connectivity. We evaluated our approach on a combined dataset of 142 computed tomography angiography images of the thoracic and abdominal regions from LIDC-IDRI and AMOS datasets. The results demonstrate that our method achieves superior centerline extraction performance (Surface Dice with threshold of 3 mm: 97.65%$\pm$2.07%) compared to state-of-the-art techniques, and attains the highest subvoxel resolution (Surface Dice with threshold of 1 mm: 72.52%$\pm$8.96%). In addition, we conducted a robustness analysis to evaluate the model stability under small rigid and deformable transformations of the input data, and benchmarked its robustness against the widely used VMTK toolkit. Full article

Collaborative geometric reconstruction of building structures can significantly reduce communication consumption for data sharing, protect privacy, and provide support for large-scale robot application management. In recent years, geometric reconstruction of building structures has been partially studied, but there is a lack of alignment fusion studies for multi-UAV (Unmanned Aerial Vehicle)-reconstructed geometric structure models. The vertices and edges of geometric structure models are sparse, and existing methods face challenges such as low feature extraction efficiency and substantial data requirements when processing sparse graph structures after geometrization. To address these challenges, this paper proposes an efficient deep graph matching registration framework that effectively integrates interpretable feature extraction with network training. Specifically, we first extract multidimensional local properties of nodes by combining geometric features with complex network features. Next, we construct a lightweight graph neural network, named EKNet, to enhance feature representation capabilities, enabling improved performance in low-overlap registration scenarios. Finally, through feature matching and discrimination modules, we effectively eliminate incorrect pairings and enhance accuracy. Experiments demonstrate that the proposed method achieves a 27.28% improvement in registration speed compared to traditional GCN (Graph Convolutional Neural Networks) and an 80.66% increase in registration accuracy over the suboptimal method. The method exhibits strong robustness in registration for scenes with high noise and low overlap rates. Additionally, we construct a standardized geometric point cloud registration dataset. Full article

The problem of inadequate object detection accuracy in complex remote sensing scenarios has been identified as a primary concern. Traditional YOLO-series algorithms encounter challenges such as poor robustness in small object detection and significant interference from complex backgrounds. In this paper, a multi-scale feature fusion framework based on an improved version of YOLOv8_L is proposed. The combination of a graph attention network (GAT) and Dilated Encoder network significantly improves the algorithm detection and recognition performance for space remote sensing objects. It mainly includes abandoning the original Feature Pyramid Network (FPN) structure, proposing an adaptive fusion strategy based on multi-level features of backbone network, enhancing the expression ability of multi-scale objects through upsampling and feature stacking, and reconstructing the FPN. The local features extracted by convolutional neural networks are mapped to graph-structured data, and the nodal attention mechanism of GAT is used to capture the global topological association of space objects, which makes up for the deficiency of the convolutional operation in weight allocation and realizes GAT integration. The Dilated Encoder network is introduced to cover different-scale targets by differentiating receptive fields, and the feature weight allocation is optimized by combining it with a Convolutional Block Attention Module (CBAM). According to the characteristics of space missions, an annotated dataset containing 8000 satellite and space station images is constructed, covering a variety of lighting, attitude and scale scenes, and providing benchmark support for model training and verification. Experimental results on the space object dataset reveal that the enhanced algorithm achieves a mean average precision (mAP) of 97.2%, representing a 2.1% improvement over the original YOLOv8_L. Comparative experiments with six other models demonstrate that the proposed algorithm outperforms its counterparts. Ablation studies further validate the synergistic effect between the graph attention network (GAT) and the Dilated Encoder. The results indicate that the model maintains a high detection accuracy under challenging conditions, including strong light interference, multi-scale variations, and low-light environments. Full article

Forecasting financial time series is challenging due to their intrinsic nonlinearity, high volatility, and complex dependencies across temporal scales. This study introduces MSGformer, a novel hybrid architecture that integrates multi-scale graph neural networks (MSGNet) with Transformer encoders to capture both local temporal fluctuations and long-term global trends in high-frequency financial data. The MSGNet module constructs multi-scale representations using adaptive graph convolutions and intra-sequence attention, while the Transformer component enhances long-range dependency modeling via multi-head self-attention. We evaluate MSGformer on minute-level stock index data from the Chinese A-share market, including CSI 300, SSE 50, CSI 500, and SSE Composite indices. Extensive experiments demonstrate that MSGformer significantly outperforms state-of-the-art baselines (e.g., Transformer, PatchTST, Autoformer) in terms of MAE, RMSE, MAPE, and R². The results confirm that the proposed hybrid model achieves superior prediction accuracy, robustness, and generalization across various forecasting horizons, providing an effective solution for real-world financial decision-making and risk assessment. Full article

The style change detection (SCD) task asks to find the positions of authors’ style changes within multi-authored texts. It has several application areas, such as forensics, cybercrime, and literary analysis. Since 2017, SCD solutions in English have been actively investigated. However, to the best of our knowledge, this task has not yet been investigated in Arabic text. Moreover, most existing SCD solutions represent boundaries surrounding segments by concatenating them. This shallow concatenation may lose style patterns within each segment and also increase input lengths while several embedding models restrict these lengths. This study seeks to bridge these gaps by introducing an Edge Convolutional Neural Network for the Arabic SCD task (ECNN-ASCD) solution. It represents boundaries as standalone learnable parameters across layers based on graph neural networks. ECNN-ASCD was trained on an Arabic dataset containing three classes of instances according to difficulty level: easy, medium, and hard. The results show that ECNN-ASCD achieved a high $F_1$ score of 0.9945%, 0.9381%, and 0.9120% on easy, medium, and hard instances, respectively. The ablation experiments demonstrated the effectiveness of ECNN-ASCD components. As the first publicly available solution for Arabic SCD, ECNN-ASCD would open the door for more active research on solving this task and contribute to boosting research in Arabic NLP. Full article

Accurate address matching is crucial for the analysis, integration, and intelligent management of urban geospatial data and is also a key step in achieving geocoding. However, due to the complexity, diversity, and irregularity of address expression, address matching becomes a challenging task. This paper proposes a multi-semantic feature fusion method for complex address matching of Chinese addresses that formulates address matching as a classification task that directly predicts whether two addresses refer to the same location, without relying on predefined similarity thresholds. First, the address is resolved into address elements, and the Word2vec model is trained to generate word vector representations using these address elements. Then, multi-semantic features of the addresses are extracted using a Text Recurrent Convolutional Neural Network (Text-RCNN) and a Graph Attention Network (GAT). Finally, the Enhanced Sequential Inference Model (ESIM) is used to perform both local inference and inference composition on the multi-semantic features of the addresses to achieve accurate matching of addresses. Experiments were conducted using Points of Interest (POI) address data from Baidu Maps, Tencent Maps, and Amap within the Chengdu area. The results demonstrate that the proposed method outperforms existing address matching methods, with precision, recall, and F1 values all exceeding 95%. In addition, transfer experiments using datasets from five other cities including Beijing, Shanghai, Xi’an, Guangzhou, and Wuhan show that the model maintains strong generalization ability, achieving F1 values above 84% in cities such as Xi’an and Wuhan. Full article

Accurate vehicle type recognition in low-light environments remains a critical challenge for intelligent transportation systems (ITSs). To address the performance degradation caused by insufficient lighting, complex backgrounds, and light interference, this paper proposes a Twin-Stream Feature Fusion Graph Neural Network (TFF-Net) model. The model employs multi-scale convolutional operations combined with an Efficient Channel Attention (ECA) module to extract discriminative local features, while independent convolutional layers capture hierarchical global representations. These features are mapped as nodes to construct fully connected graph structures. Hybrid graph neural networks (GNNs) process the graph structures and model spatial dependencies and semantic associations. TFF-Net enhances the representation of features by fusing local details and global context information from the output of GNNs. To further improve its robustness, we propose an Adaptive Weighted Fusion-Bagging (AWF-Bagging) algorithm, which dynamically assigns weights to base classifiers based on their F1 scores. TFF-Net also includes dynamic feature weighting and label smoothing techniques for solving the category imbalance problem. Finally, the proposed TFF-Net is integrated into YOLOv11n (a lightweight real-time object detector) with an improved adaptive loss function. For experimental validation in low-light scenarios, we constructed the low-light vehicle dataset VDD-Light based on the public dataset UA-DETRAC. Experimental results demonstrate that our model achieves 2.6% and 2.2% improvements in mAP50 and mAP50-95 metrics over the baseline model. Compared to mainstream models and methods, the proposed model shows excellent performance and practical deployment potential. Full article

Background/Objectives: Electroencephalogram (EEG) signals, which reflect brain activity, are widely used in emotion recognition. However, the variety of EEG features presents significant challenges in identifying key features, reducing redundancy, and simplifying the computational process. Methods: To address these challenges, this paper proposes a multi-dimensional attention-based dynamic graph convolutional neural network (AttGraph) model. The model delves into the impact of different EEG features on emotion recognition by evaluating their sensitivity to emotional changes, providing richer and more accurate feature information. Results: Through the dynamic weighting of EEG features via a multi-dimensional attention convolution layer, the AttGraph method is able to precisely detect emotional changes and automatically choose the most discriminative features for emotion recognition tasks. This approach significantly improves the model’s recognition accuracy and robustness. Finally, subject-independent and subject-dependent experiments were conducted on two public datasets. Conclusions: Through comparisons and analyses with existing methods, the proposed AttGraph method demonstrated outstanding performances in emotion recognition tasks, with stronger generalization ability and adaptability. Full article