A5038735174- Traffic Prediction and Management Techniques
- Traffic control and management
- Blind Source Separation Techniques
- Human Mobility and Location-Based Analysis
- Traffic and Road Safety
- Automated Road and Building Extraction
- Anomaly Detection Techniques and Applications
- EEG and Brain-Computer Interfaces
- Crime Patterns and Interventions
- Video Surveillance and Tracking Methods
- Autonomous Vehicle Technology and Safety
- Transportation Planning and Optimization
- Data Management and Algorithms
- Neural Networks and Applications
Beijing University of Technology
2022-2025
Jiangsu Normal University
2024
Multivariate time series forecasting plays an important role in many domain applications, such as air pollution and traffic forecasting. Modeling the complex dependencies among is a key challenging task multivariate Many previous works have used graph structures to learn inter-series correlations, which achieved remarkable performance. However, networks can only capture spatio-temporal between pairs of nodes, cannot handle high-order correlations series. We propose Dynamic Hypergraph...
Existing traffic flow prediction methods generally only consider the spatiotemporal characteristics of flow. However, in addition to characteristics, interference various external factors needs be considered prediction, including severe weather, major events, control, and metro failures. The current research still cannot fully use information contained these factors. To address this issue, we propose a novel method (KGR-STGNN) based on knowledge graph representation learning. We construct...
Abstract Trajectory prediction is essential for intelligent autonomous systems like driving, behavior analysis, and service robotics. Deep learning has emerged as the predominant technique due to its superior modeling capability trajectory data. However, deep learning‐based models face challenges in effectively utilizing scene information accurately agent interactions, largely complexity uncertainty of real‐world scenarios. To mitigate these challenges, this study presents a novel multiagent...