A5102854639- Traffic Prediction and Management Techniques
- Traffic control and management
- Evaluation Methods in Various Fields
- Transportation Planning and Optimization
- Advanced Algorithms and Applications
- Image and Signal Denoising Methods
- Vehicle emissions and performance
- Automated Road and Building Extraction
- Power Systems and Renewable Energy
- Time Series Analysis and Forecasting
- Advanced Decision-Making Techniques
- Smart Grid and Power Systems
- Structural Health Monitoring Techniques
- Advanced Image Fusion Techniques
- Data Management and Algorithms
- Advanced Measurement and Detection Methods
Jilin University
2013-2023
Jilin Medical University
2023
State Key Laboratory of Automotive Simulation and Control
2016
Short-term traffic flow prediction is one of the most important issues in field intelligent transport system (ITS). Because uncertainty and nonlinearity, short-term a challenging task. In order to improve accuracy short-time prediction, hybrid model (SSA-KELM) proposed based on singular spectrum analysis (SSA) kernel extreme learning machine (KELM). SSA used filter out noise time series. Then, filtered data train KELM model, optimal input form determined by phase space reconstruction,...
Vehicles are often caught in dilemma zone when they approach signalized intersections yellow interval. The existence of which is significantly influenced by driver behavior seriously affects the efficiency and safety intersections. This paper proposes models interval logistic regression fuzzy decision tree modeling, respectively, based on camera image data. Vehicle’s speed distance to stop line considered model, also brings a dummy variable describe installation countdown timer display....
Short-term traffic flow prediction is one of the most important issues in field adaptive control system and dynamic guidance system. In order to improve accuracy short-term prediction, a local method based on combined kernel function relevance vector machine (CKF-RVM) model put forward. The C-C used calculate delay time embedding dimension. number neighboring points determined by use Hannan-Quinn criteria, CKF-RVM built genetic algorithm. Finally, case validation carried out using inductive...
Short-term traffic flow prediction is an important part of intelligent transportation systems research and applications. For further improving the accuracy short-time prediction, a novel hybrid model (multivariate phase space reconstruction–combined kernel function-least squares support vector machine) based on multivariate reconstruction combined machine proposed. The C-C method used to determine optimal time delay embedding dimension variables’ (flow, speed, occupancy) series for...
To improve the accuracy and robustness of urban link travel time estimation with limited resources, this research developed a methodology to estimate using low frequency GPS probe vehicle data. First, focusing on case without reporting points for target in current window, virtual report point creation model based the<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M1"><mml:mrow><mml:mi>K</mml:mi></mml:mrow></mml:math>-Nearest Neighbour Rule was proposed. Then an improved back...
In the real world, traffic scenes are complex and contain intricate road networks, which makes shortest path computation on large-scale networks a challenging task. Existing research has concentrated small-scale urban or grid maps. practical scenarios, however, we often faced with seeking paths networks. For this reason, it is imperative to develop efficient searching algorithms, as offers significant savings in time resources. To tackle issue, paper proposes two improved A* namely Weighted...
Aiming at the deficiencies of traffic signal cycle optimization in regional control system and considering vehicle emission pollution, this paper proposed a method based on bi-level programming model, attempted to take reducing as one objective parameters. Then improved PSO algorithm was solve model. Finally, effectiveness model verified through VISSIM MATLAB. The results indicate that can effectively reduce network delay emission.