Primal–Dual Heuristic for Path Flow Estimation in Medium to Large Networks

2013 ◽  
Vol 2333 (1) ◽  
pp. 91-99 ◽  
Author(s):  
Shikai Tang ◽  
H. Michael Zhang
Keyword(s):  
Large Networks ◽  
Flow Estimation ◽  
Primal Dual ◽  
Path Flow Estimation

Path Flow Estimation Using Time Varying Coefficient State Space Model

2009 ◽  
Author(s):  
Yow-Jen Jou ◽  
Chien-Lun Lan ◽  
George Maroulis ◽  
Theodore E. Simos
Keyword(s):  
State Space ◽  
State Space Model ◽  
Time Varying ◽  
Flow Estimation ◽  
Space Model ◽  
Varying Coefficient ◽  
Path Flow Estimation

scholarly journals A STOCHASTIC FLOW-DEPENDENT MODEL FOR PATH FLOW ESTIMATION

2001 ◽  
Vol 18 ◽  
pp. 573-580
Author(s):  
Lin Cheng ◽  
Yasunori Iida ◽  
Nobuhiro Uno
Keyword(s):  
Stochastic Flow ◽  
Flow Estimation ◽  
Dependent Model ◽  
Path Flow Estimation

Path Flow Estimation in Traffic System Management

1997 ◽  
Vol 30 (8) ◽  
pp. 1247-1252 ◽  
Author(s):  
Michael G.H. Bell ◽  
Chris Cassir ◽  
Sergio Grosso ◽  
Stuart J. Clement
Keyword(s):  
System Management ◽  
Flow Estimation ◽  
Traffic System ◽  
Path Flow Estimation

scholarly journals Dynamic Path Flow Estimation Using Automatic Vehicle Identification and Probe Vehicle Trajectory Data: A 3D Convolutional Neural Network Model

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Can Chen ◽  
Yumin Cao ◽  
Keshuang Tang ◽  
Keping Li
Keyword(s):  
Neural Network ◽  
Data Sources ◽  
Flow Estimation ◽  
Probe Vehicle ◽  
Vehicle Identification ◽  
Automatic Vehicle Identification ◽  
Dynamic Path ◽  
Path Flow Estimation ◽  
Bootstrapping Method ◽  
Noisy Labels

Dynamic path flows, referring to the number of vehicles that choose each path in a network over time, are generally estimated with the partial observations as the input. The automatic vehicle identification (AVI) system and probe vehicle trajectories are now popular and can provide rich and complementary trip information, but the data fusion was rarely explored. Therefore, in this paper, the dynamic path flow estimation is based on these two data sources and transformed into a feature learning problem. To fuse the two data sources belonging to different detection ways at the data level, the virtual AVI points, analogous to the real AVI points (turning movements at nodes with AVI detectors), are defined and selected to statically observe the dynamic movement of the probe vehicles. The corresponding selection principles and a programming model considering the distribution of real AVI points are first established. The selected virtual AVI points are used to construct the input tensor, and the turning movement-based observations from both the data sources can be extracted and fused. Then, a three-dimensional (3D) convolutional neural network (CNN) model is designed to exploit the hidden patterns from the tensor and establish the high-dimensional correlations with path flows. As the path flow labels commonly with noises, the bootstrapping method is adopted for model training and the corresponding relabeling principle is defined to purify the noisy labels. The entire model is extensively tested based on a realistic road network, and the results show that the designed CNN model with the presented data fusion method can perform well in training time and estimation accuracy. The robustness of a model to noisy labels is also improved through the bootstrapping method. The dynamic path flows estimated by the trained model can be applied to travel information provision, proactive route guidance, and signal control with high real-time requirements.

Sign in / Sign up

Export Citation Format

Share Document