A5045699018- Transportation Planning and Optimization
- Traffic Prediction and Management Techniques
- Human Mobility and Location-Based Analysis
- Urban Transport and Accessibility
- Traffic control and management
- Transportation and Mobility Innovations
- Urban and Freight Transport Logistics
- Advanced Computational Techniques and Applications
- Electric Vehicles and Infrastructure
- Industrial Technology and Control Systems
- Advanced Battery Technologies Research
- Data Management and Algorithms
- Interconnection Networks and Systems
- Vehicle Routing Optimization Methods
- Vehicle emissions and performance
- Traffic and Road Safety
- Regional Development and Environment
- Building Energy and Comfort Optimization
- Advanced Image Processing Techniques
- Image Enhancement Techniques
- Infrastructure Resilience and Vulnerability Analysis
- Sustainable Supply Chain Management
- Urban Heat Island Mitigation
- Medical Research and Treatments
- Machine Learning in Bioinformatics
Beihang University
2016-2025
Ministry of Transport
2020-2025
Shandong University of Science and Technology
2024
Hubei University of Medicine
2024
China National Institute of Standardization
2019-2024
Tianjin University of Commerce
2024
Jiangsu Normal University
2021-2023
Inner Mongolia Electric Power (China)
2020-2023
Hebei University of Technology
2023
Hospital of Hebei Province
2023
This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide speed with high accuracy. Spatiotemporal dynamics are converted to describing the time space relations of flow via two-dimensional time-space matrix. A CNN is applied image following two consecutive steps: abstract feature extraction prediction. The effectiveness proposed evaluated by taking real-world transportation networks, second ring road north-east...
Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, which future object can be predicted based on previous scenes, we propose a grid representation method that retain fine-scale structure network. Network-wide speeds are converted into series static images input novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for forecasting. The...
Understanding how congestion at one location can cause ripples throughout large-scale transportation network is vital for researchers and practitioners to pinpoint traffic bottlenecks mitigation. Traditional studies rely on either mathematical equations or simulation techniques model dynamics. However, most of the approaches have limitations, largely due unrealistic assumptions cumbersome parameter calibration process. With development Intelligent Transportation Systems (ITS) Internet Things...
Identifying and quantifying the influential factors on incident clearance time can benefit management for accident causal analysis prediction, consequently mitigate impact of non-recurrent congestion. Traditional studies rely either statistical models with rigorous assumptions or artificial intelligence (AI) approaches poor interpretability. This paper proposes a novel method, gradient boosting decision trees (GBDTs), to predict nonlinear imbalanced based different types explanatory...
Accurate metro ridership prediction can guide passengers in efficiently selecting their departure time and transferring from station to station. An increasing number of deep learning algorithms are being utilized forecast due the development computational intelligence. However, limited efforts have been exerted consider spatiotemporal features, which important forecasting through methods, large-scale networks. To fill this gap, paper proposes a parallel architecture comprising convolutional...
Traffic forecasting has attracted considerable attention due to its importance in proactive urban traffic control and management. Scholars engineers have exerted efforts improving the performance of algorithms terms accuracy, reliability, efficiency. Spatial feature representation flow is a core component that greatly influences performance. In previous studies, several spatial attributes are ignored following issues: a) propagation does not comply with road network, b) pattern varies over...
Understanding the relationship between short-term subway ridership and its influential factors is crucial to improving accuracy of prediction. Although there has been a growing body studies on prediction approaches, limited effort made investigate considering bus transfer activities temporal features. To fill this gap, relatively recent data mining approach called gradient boosting decision trees (GBDT) applied used capture associations with independent variables. Taking three stations in...
Accurate and reliable traffic forecasting for complicated transportation networks is of vital importance to modern management. The spatial dependencies roadway links the dynamic temporal patterns states make it particularly challenging. To address these challenges, we propose a new capsule network (CapsNet) extract features utilize nested LSTM (NLSTM) structure capture hierarchical in sequence data. A framework network-level also proposed by sequentially connecting CapsNet NLSTM. On basis...