Abstract
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.
Highlights
Unlike the static path flows, which represent the average path flows during a long period, the dynamic path flows represent the real-time path flows in a relatively small time interval and the corresponding estimation problem becomes more challenging. e dynamic path flow data have a wide range of applications, such as the analysis of user travel patterns, large-scale traffic network simulation, and traffic planning and management. e path flow and OD matrix estimates are sometimes similar and interdependent. e OD flows can be assigned to obtain path flows and the sum of several path flows can be used to obtain one specific OD flow
Four error metrics are used for our evaluation: mean absolute error (MAE), relative MAE (%), root mean square error (RMSE), and relative RMSE (%)
To make full use of the rich and complementary individuals’ trip information provided by automatic vehicle identification (AVI) and probe vehicle data, and to avoid intractable mathematical program solution, the dynamic path flow estimation is treated as a datadriven feature learning problem and these two data sources are fused at the data level
Summary
Unlike the static path flows, which represent the average path flows during a long period, the dynamic path flows represent the real-time path flows in a relatively small time interval and the corresponding estimation problem becomes more challenging. e dynamic path flow data have a wide range of applications, such as the analysis of user travel patterns, large-scale traffic network simulation, and traffic planning and management. e path flow and OD matrix estimates are sometimes similar and interdependent. e OD flows can be assigned to obtain path flows and the sum of several path flows can be used to obtain one specific OD flow. Due to the high cost and less efficiency of manual survey for directly observing path flows, a typical way has been widely used to indirectly estimate them from observed link flows. It is common for a network that the number of OD pairs is much larger than the number of observed links [1, 2], which is often referred to the underspecified problem. More information such as prior OD matrices is needed and the bi-level programming framework is mostly applied among existing studies [3, 4].
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.