A5103259414- Traffic Prediction and Management Techniques
- Transportation Planning and Optimization
- Human Mobility and Location-Based Analysis
- Traffic control and management
- Recommender Systems and Techniques
- Complex Network Analysis Techniques
- Advanced Graph Neural Networks
- Advanced biosensing and bioanalysis techniques
- Data Management and Algorithms
- DNA and Nucleic Acid Chemistry
- Caching and Content Delivery
- Luminescence and Fluorescent Materials
- Topic Modeling
Beihang University
2021-2024
Shenyang Pharmaceutical University
2024
Forecasting traffic flow is an important task in urban areas, and a large number of methods have been proposed for prediction. However, most the existing follow general technical route to aggregate historical information spatially temporally. In this paper, we propose different approach Our major motivation more effectively incorporate various intrinsic patterns real-world flows, such as fixed spatial distributions, topological correlations, temporal periodicity. Along line, novel...
Due to the increasing diversification of urban transportation modes, many areas have problem unbalanced traffic demand, which makes accurate prediction demand very important. However, most existing studies focus on improving accuracy single spatial relationship a mode, ignoring diversity relationships and heterogeneity stations in network. In this paper, we propose Co-Modal Graph Attention neTwork(CMGAT) framework uncover impact different mode interactions demand. Specifically, first utilize...
Popularity prediction, which aims to forecast how many users would like interact with a target item or online content in the future, can help shopping social media platforms identify popular items digital contents. Many efforts have been made study multi-faceted factors, such as features, user preferences, and influence, affect user-item interactions, but little work has focused on evolutionary dynamics of these factors for individuals groups. In that light, this paper develops...
Transportation demand prediction is a classic problem in intelligent transportation research. However, most exist studies have been focused on improving the accuracy single mode, and there lack of understanding impact multiple modes. To this paper, we aim to uncover interactions modes develop co-prediction method for multimodal prediction. Specifically, first propose self-learned spatial graph construction method, which automatically learns dependencies both homogeneous heterogeneous...
Signaling data are records of the interactions users’ mobile phones with their nearest cellular stations, which could provide long-term and continuous-time location large-scale citizens, therefore have great potential in intelligent transportation, smart cities, urban sensing. However, utilizing raw signaling often suffers from two problems: (1) Low positioning accuracy. Since only describes interaction between user base station, they can restore approximate geographical location. (2) Poor...
Dynamic graph learning has attracted much attention in recent years due to the fact that most of real-world graphs are dynamic and evolutionary. As a result, many methods have been proposed cope with changes node states over time. Among these studies, critical issue is how update representations nodes when new temporal events observed. In this paper, we provide novel memory structure - Memory Map (MemMap) for problem. MemMap an adaptive evolutionary latent space, where each cell corresponds...