A hypergraph-based hybrid graph convolutional network for intracity human activity intensity prediction and geographic relationship interpretation

Keyphrases

• Hypergraph 100%
• Intra-city 100%
• Hybrid Graph 100%
• Graph Convolutional Network 100%
• Human Activity Intensity 100%
• Intensity Prediction 100%
• High-order Relations 75%
• Artificial Intelligence 50%
• Deep Learning Model 50%
• Law 25%
• Prediction Accuracy 25%
• Spatial Flow 25%
• Modeling Approach 25%
• Spatiotemporal Phenomena 25%
• Location-aware 25%
• Urban Planning 25%
• Generation Method 25%
• Spatial Structure 25%
• New Modeling 25%
• Edge Weight 25%
• Pairwise Relation 25%
• Spatial Fusion 25%
• Spatial Knowledge 25%
• Mobility Data 25%
• Graph Generation 25%
• Transportation System Planning 25%
• Fusion Layer 25%
• Spatial-temporal Graph Neural Network 25%
• Adaptive Graph 25%
• Dynamic Population Distribution 25%
• Spatial Relationship 25%
• State-of-the-art Models 25%
• Intelligent Transportation Systems 25%
• Spatiotemporal Knowledge 25%
• Hypergraph Convolution 25%
• Hypergraph Generation 25%
• Adaptive Hypergraph 25%

Computer Science

• Order Relationship 100%
• Graph Convolutional Network 100%
• Artificial Intelligence 66%
• Spatiotemporal Graph 33%
• Spatial Relationship 33%
• Deep Learning Model 33%
• Graph Neural Network 33%
• Spatial Structure 33%
• Graph Convolution 33%
• Deep Learning Method 33%
• Intelligent Transportation System 33%
• Convolution 33%