NSTL国家科技图书文献中心

1. Customizing Spatial-Temporal Graph Mamba Networks for Pandemic Forecasting NSTL国家科技图书文献中心

Haowei Xu | Chao Gao ... - 《PRICAI 2024,Part I》 - Pacific Rim International Conference on Artificial Intelligence - 2025, - 236～242 - 共7页

摘要： previous studies used spatiotem-poral and graph | architecture search framework utilizing bidirectional Graph | Mamba Networks. We construct a graph* where nodes* | The global spread of COVID-19 has emphasized | the need for accurate pandemic prediction. While

关键词： Pandemic forecasting | Spatial-temporal graph representation learning | Mamba | Neural architecture search

2. Cluster-guided denoising graph auto-encoder for enhanced traffic data imputation and fault detection NSTL国家科技图书文献中心

Yongcan Huang | Hao Zhen ... - 《Expert Systems with Application》 - 2025,261(Feb.) - 125531.1～125531.17 - 共17页

摘要： spatial-temporal context leveraged by the model. | graph auto-encoder (DA-GAE) to identify clusters of | clusters, a cluster-guided denoising graph* auto-encoder* | reconstruction. The CG-DGAE employs a diffusion graph | In an era of increasing digitalization, the

关键词： Graph Representation Learning | Graph Auto-Encoder | Dual Encoding Attention | Data Imputation | Fault Detection | Spatial-Temporal Context | Traffic Sensor Clustering

3. A Spatial-Temporal Graph Convolutional Network for Video-Based Group Emotion Recognition NSTL国家科技图书文献中心

Xingzhi Wang | Tao Chen ... - 《Pattern Recognition,Part XIII》 - International Conference on Pattern Recognition - 2025, - 339～354 - 共16页

摘要：. Specifically, we construct a spatial-temporal* graph with* | -temporal characteristics via efficient deep learning | the spatial-temporal* interactive characteristics* | relationships within a group in spatial and temporal | -temporal* representation for GER. We fuse the decisions*

关键词： Spatial-temporal graph | Group emotion recognition | Graph attention network

4. Next Point-of-Interest Recommendation With Adaptive Graph Contrastive Learning NSTL国家科技图书文献中心

Xuan Rao | Renhe Jiang ... - 《IEEE Transactions on Knowledge and Data Engineering》 - 2025,37(3) - 1366～1379 - 共14页

摘要： graph-based contrastive learning, which encourages the | mechanism to integrate spatial-temporal* information into* | an adaptive graph* from user trajectories and* | compute POI representations using graph* neural networks* | (GNNs). However, a single graph* cannot capture the*

关键词： Adaptation models | Trajectory | Accuracy | Contrastive learning | Transformers | Vectors | Symbols | Frequency measurement | Data augmentation | Correlation

5. A Dynamic SpatialTemporal Subgraph Convolutional Network for Noncontact Fault Diagnosis NSTL国家科技图书文献中心

Cao, Yu | Chen, Yongyi ... - 《IEEE Transactions on Instrumentation and Measurement》 - 2025,74(Pt.1) - 3504711.1～3504711.11 - 共11页

摘要： methods struggle to capture the spatial-temporal | spatial-temporal subgraph convolutional network (DSTSGCN | enhanced by fusing multisignal spatial-temporal | Voiceprint recognition based on deep learning | . Additionally, the existing voiceprint graph* construction*

关键词： Spectrogram | Fault diagnosis | Feature extraction | Correlation | Convolution | Vibrations | Graph convolutional networks | Heuristic algorithms | Accuracy | Nearest neighbor methods...

6. Spatio-Temporal Heterogeneous Graph Neural Network With Multi-view Learning For Traffic Prediction NSTL国家科技图书文献中心

Liting Song | Qianqian Ren ... - 《Pattern Recognition,Part VII》 - International Conference on Pattern Recognition - 2025, - 35～52 - 共18页

摘要： representation ability for modeling spatial and temporal | predicting methods, graph* learning-based models attract* | Heterogeneous Graph Neural Network With Multi-View Learning | dependencies with graph* neural networks. Despite their* | -temporal* correlations of traffic data are complex and*

关键词： Traffic prediction | Multi-view | Graph convolution | Graph learning

7. HydroVision: LiDAR-Guided Hydrometric Prediction with Vision Transformers and Hybrid Graph Learning NSTL国家科技图书文献中心

Naghmeh Shafiee Roud... | Ursula Eicker ... - 《Advances in Visual Computing,Part II》 - International Symposium on Visual Computing - 2025, - 134～147 - 共14页

摘要： literature. We propose a hybrid graph* learning structure* | that combines static and dynamic graph* learning. A* | a dynamic graph* adapts to temporal changes* | , improving the overall graph representation. We apply graph | patches, efficiently captures spatial* features of*

关键词： Vision transformer | Graph learning | Hydrometric forecasting

8. Dynamic mode decomposition and short-time prediction of PM2.5 using the graph Neural Koopman network NSTL国家科技图书文献中心

Yuhan Yu | Hongye Zhou ... - 《International journal of geographical information science》 - 2025,39(1/2) - 277～300 - 共24页

摘要： Learning (SPCL) model utilizing a graph representation | Koopman theory and deep learning often neglect spatial | learning method was proposed to combine the graph | -Term Memory Networks, Spatio-Temporal Graph | modes. Furthermore, a Spatial* Physics Constrained*

关键词： Spatiotemporal prediction | deep Koopman | physics-constrained learning framework | Koopman pattern decomposition | PM2.5

9. Hierarchical Spatial-Temporal Graph-Enhanced Model for Map-Matching NSTL国家科技图书文献中心

Anjun Gao | Zhenglin Wan ... - 《Databases Theory and Applications》 - Australasian Database Conference - 2025, - 44～57 - 共14页

摘要：: hierarchical self-supervised learning and spatial-temporal | of spatial-temporal* relationships, and* | Graph to dynamically capture spatial relationships | incorporate a Spatial-Temporal* Factor to extract relevant* | -based methods, recent works in deep learning* for*

关键词： Map-matching | Spatial-temporal trajectories | Machine learning

10. Variational Graph Attention Networks With Self-Supervised Learning for Multivariate Time Series Anomaly Detection NSTL国家科技图书文献中心

Gao, Yu | Qi, Jin ... - 《IEEE Transactions on Instrumentation and Measurement》 - 2025,74(Pt.1) - 3503113.1～3503113.13 - 共13页

摘要： learning (VGATSL). We use stacked spatial-temporal graph | challenging to capture spatial-temporal* relationships* | variational graph* attention networks with self-supervised* | attention (STGAT) networks to capture the temporal* and* | places latent representation* on the surface of a unit*

关键词： Anomaly detection | Feature extraction | Time series analysis | Data models | Sun | Self-supervised learning | Transfer learning | Training | Predictive models | Monitoring...

摘要： previous studies used spatiotem-poral and graph | architecture search framework utilizing bidirectional Graph | Mamba Networks. We construct a graph where nodes | The global spread of COVID-19 has emphasized | the need for accurate pandemic prediction. While

关键词： Pandemic forecasting | Spatial-temporal graph representation learning | Mamba | Neural architecture search

摘要： spatial-temporal context leveraged by the model. | graph auto-encoder (DA-GAE) to identify clusters of | clusters, a cluster-guided denoising graph auto-encoder | reconstruction. The CG-DGAE employs a diffusion graph | In an era of increasing digitalization, the

关键词： Graph Representation Learning | Graph Auto-Encoder | Dual Encoding Attention | Data Imputation | Fault Detection | Spatial-Temporal Context | Traffic Sensor Clustering

摘要：. Specifically, we construct a spatial-temporal graph with | -temporal characteristics via efficient deep learning | the spatial-temporal interactive characteristics | relationships within a group in spatial and temporal | -temporal representation for GER. We fuse the decisions

关键词： Spatial-temporal graph | Group emotion recognition | Graph attention network

摘要： graph-based contrastive learning, which encourages the | mechanism to integrate spatial-temporal information into | an adaptive graph from user trajectories and | compute POI representations using graph neural networks | (GNNs). However, a single graph cannot capture the

关键词： Adaptation models | Trajectory | Accuracy | Contrastive learning | Transformers | Vectors | Symbols | Frequency measurement | Data augmentation | Correlation

摘要： methods struggle to capture the spatial-temporal | spatial-temporal subgraph convolutional network (DSTSGCN | enhanced by fusing multisignal spatial-temporal | Voiceprint recognition based on deep learning | . Additionally, the existing voiceprint graph construction

关键词： Spectrogram | Fault diagnosis | Feature extraction | Correlation | Convolution | Vibrations | Graph convolutional networks | Heuristic algorithms | Accuracy | Nearest neighbor methods...

关键词： Traffic prediction | Multi-view | Graph convolution | Graph learning

摘要： literature. We propose a hybrid graph learning structure | that combines static and dynamic graph learning. A | a dynamic graph adapts to temporal changes | , improving the overall graph representation. We apply graph | patches, efficiently captures spatial features of

关键词： Vision transformer | Graph learning | Hydrometric forecasting

摘要： Learning (SPCL) model utilizing a graph representation | Koopman theory and deep learning often neglect spatial | learning method was proposed to combine the graph | -Term Memory Networks, Spatio-Temporal Graph | modes. Furthermore, a Spatial Physics Constrained

关键词： Spatiotemporal prediction | deep Koopman | physics-constrained learning framework | Koopman pattern decomposition | PM2.5

摘要：: hierarchical self-supervised learning and spatial-temporal | of spatial-temporal relationships, and | Graph to dynamically capture spatial relationships | incorporate a Spatial-Temporal Factor to extract relevant | -based methods, recent works in deep learning for

关键词： Map-matching | Spatial-temporal trajectories | Machine learning

摘要： learning (VGATSL). We use stacked spatial-temporal graph | challenging to capture spatial-temporal relationships | variational graph attention networks with self-supervised | attention (STGAT) networks to capture the temporal and | places latent representation on the surface of a unit

关键词： Anomaly detection | Feature extraction | Time series analysis | Data models | Sun | Self-supervised learning | Transfer learning | Training | Predictive models | Monitoring...

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： previous studies used spatiotem-poral and graph | architecture search framework utilizing bidirectional Graph | Mamba Networks. We construct a graph* where nodes* | The global spread of COVID-19 has emphasized | the need for accurate pandemic prediction. While

摘要： spatial-temporal context leveraged by the model. | graph auto-encoder (DA-GAE) to identify clusters of | clusters, a cluster-guided denoising graph* auto-encoder* | reconstruction. The CG-DGAE employs a diffusion graph | In an era of increasing digitalization, the

摘要：. Specifically, we construct a spatial-temporal* graph with* | -temporal characteristics via efficient deep learning | the spatial-temporal* interactive characteristics* | relationships within a group in spatial and temporal | -temporal* representation for GER. We fuse the decisions*

摘要： graph-based contrastive learning, which encourages the | mechanism to integrate spatial-temporal* information into* | an adaptive graph* from user trajectories and* | compute POI representations using graph* neural networks* | (GNNs). However, a single graph* cannot capture the*

摘要： methods struggle to capture the spatial-temporal | spatial-temporal subgraph convolutional network (DSTSGCN | enhanced by fusing multisignal spatial-temporal | Voiceprint recognition based on deep learning | . Additionally, the existing voiceprint graph* construction*

摘要： literature. We propose a hybrid graph* learning structure* | that combines static and dynamic graph* learning. A* | a dynamic graph* adapts to temporal changes* | , improving the overall graph representation. We apply graph | patches, efficiently captures spatial* features of*

摘要： Learning (SPCL) model utilizing a graph representation | Koopman theory and deep learning often neglect spatial | learning method was proposed to combine the graph | -Term Memory Networks, Spatio-Temporal Graph | modes. Furthermore, a Spatial* Physics Constrained*

摘要：: hierarchical self-supervised learning and spatial-temporal | of spatial-temporal* relationships, and* | Graph to dynamically capture spatial relationships | incorporate a Spatial-Temporal* Factor to extract relevant* | -based methods, recent works in deep learning* for*