A5001574131- Traffic Prediction and Management Techniques
- Transportation Planning and Optimization
- Railway Systems and Energy Efficiency
- Railway Engineering and Dynamics
- Network Traffic and Congestion Control
- Mobile Agent-Based Network Management
- Landslides and related hazards
- Image Processing and 3D Reconstruction
- Human Mobility and Location-Based Analysis
- Vehicular Ad Hoc Networks (VANETs)
- Privacy-Preserving Technologies in Data
- Seismology and Earthquake Studies
- Traffic control and management
- Mobile Crowdsensing and Crowdsourcing
Beijing Jiaotong University
2020-2022
Due to the long train marshaling and complex line conditions, operating modes in heavy haul rail systems frequently change when trains travel. Improper traction or braking operation made by drivers will increase longitudinal impact force causes decoupling, severely affecting safe operations of trains. It is quite desirable replace manual control with intelligent systems. Traditional machine learning-based methods suffer from insufficient data. lacking effective incentives trust, data...
With the acceleration of urbanization, dynamic passenger flow has an ever-growing impact on actual train operation. In this paper, we propose a learning based intelligent regulation method with prediction. To capture characteristics metro flow, convolutional neural network is established to predict real-time from two dimensions including space and time. As prediction accuracy restricted by insufficiency practical data, deep generative adversarial constructed generate data that have same...
Urban rail transit systems produce big automatic fare collection (AFC) data. With the support of data analytics, more accurate forecasting passenger flow in urban system can optimize train operation timetable and alleviate traffic congestion. Lacking adequate data, most existing works study using time series analysis. The historical at one station is used to predict its future flow, where correlation between largely ignored. In this paper, we use fusion space flow. We obtain pristine from...
With the accelerated development of cities, traffic capacity cannot catch up with rising. The urban rail transit system is facing severe challenges. Accurate prediction passenger flow can help optimize operation plan and improve efficiency. Traditional machine learning-based intelligent control methods are restricted by insufficient data. Owing to lacking effective incentives trust, data from different lines or operators be shared directly. In this paper, we propose a distributed federal...
Communication Based Train Control (CBTC) systems are signal to ensure the safe operation of rail transit. However, with increasing demand for efficiency transit operations, train control system based on train-to-ground communication has exposed many problems such as complex structure and high construction cost. Compared communication, train-to-train (T2T) advantages fast response speed, simple structure, low operating The data which is core part T2T realizes continuous large-capacity two-way...
This paper investigates the distributed optimization of train scheduling and waiting passengers control problem for metro lines to improve operational efficiency service level. Integrating departure time passengers, a multi-train coupling state-space model is established. To computational efficiency, we propose algorithm decompose complex joint multiple trains into several subproblems that can be computed in parallel. Based on alternating direction method multiplier (ADMM) algorithm,...