Sequence-to-Sequence Recurrent Graph Convolutional Networks for Traffic Estimation and Prediction Using Connected Probe Vehicle Data

Abdelraouf, Amr; Abdel-Aty, Mohamed; Mahmoud, Nada

doi:10.1109/tits.2022.3168865

Cited by 22 publications

(12 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent studies have also used LSTMs [38,39] for comparing model performance. In studies [33,39] using GNN for short-term traffic forecasting, we observed that even though graph-based models (DCRNN) give the best performance, LSTM's performance is still competitive. LSTM is considered a more advanced version of the standard vanilla RNN.…”

Section: Lstm Modelmentioning

confidence: 96%

“…Recently, Abdelraouf et al. (2022) [33] used speed and volume features from PVD as an input to recurrent GCN to predict the traffic state parameters. In contrast to other indirect estimation works, using the flow from PVD as an additional feature provides direct information for accurate prediction but also makes the model dependent on such data.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Zhang et al (2020) [32] used a geometric matrix completion model for network-wide traffic flow estimation, using real-world (twenty-four road segments) and synthetic datasets. Recently, Abdelraouf et al (2022) [33] used speed and volume features from PVD as an input to recurrent GCN to predict the traffic state parameters. In contrast to other indirect estimation works, using the flow from PVD as an additional feature provides direct information for accurate prediction but also makes the model dependent on such data.…”

Section: Traffic State Estimationmentioning

confidence: 99%

“…In contrast to other indirect estimation works, using the flow from PVD as an additional feature provides direct information for accurate prediction but also makes the model dependent on such data. Among the above, only few studies [7,33] consider data from more than a hundred detectors, whereas the other studies use relatively minor datasets. Further, Neumann et al (2013) [7] note that their model performance was not accurate enough for freeways or roads with higher speed limits.…”

Section: Traffic State Estimationmentioning

confidence: 99%

See 3 more Smart Citations

Predicting network flows from speeds using open data and transfer learning

Mahajan

Cantelmo

Rothfeld

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Traffic flow/volume data are commonly used to calibrate and validate traffic simulation models. However, these data are generally obtained from stationary sensors (e.g. loop detectors), which are expensive to install and maintain and cover a small number of locations in the transport network. On the other hand, Floating Car Data (FCD) are readily available at the network level, usually from a sample of vehicles. We present an indirect traffic flow estimation approach using transfer learning to address the traffic flow data scarcity and model generalization across cities. Using two cities (Paris and Madrid) as study areas, we demonstrate the indirect estimation using only exogenous features for flow prediction, mirroring limited predictive features without past link flows. Subsequently, we use the model pre‐trained on data from Paris city and test on data from Madrid city, and investigate the scenarios for successful transfer learning. Overall, the training set must adequately capture the flow‐speed relationship for successful indirect flow estimation. Transfer learning is beneficial when the data for the target task is minimal, in which case transferred models outperform newly trained models from scratch. Using real‐world and publicly available data, our approach and models can help scale a smaller traffic flow dataset to a larger sample across cities.

show abstract

Section: Lstm Modelmentioning

confidence: 96%

Section: Literature Reviewmentioning

confidence: 99%

Section: Traffic State Estimationmentioning

confidence: 99%

Section: Traffic State Estimationmentioning

confidence: 99%

See 2 more Smart Citations

Predicting network flows from speeds using open data and transfer learning

Mahajan

Cantelmo

Rothfeld

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…Probe vehicle technology has emerged as a cost-effective alternative for traffic monitoring, and the coverage of probe data has significantly expanded 17 . Numerous studies have been conducted to validate the accuracy and reliability of probe source data [17][18][19][20] , indicating notable improvements in the data quality of probe vehicles.…”

Section: Literature Reviewmentioning

confidence: 99%

Exploring the Influence of Drivers’ Visual Surroundings on Speeding Behavior

Ugan

Abdel-Aty

Islam

2023

Preprint

Self Cite

View full text Add to dashboard Cite

Despite awareness campaigns and legal consequences, speeding is a significant cause of road accidents and fatalities globally,. To combat this issue, understanding the impact of a driver's visual surroundings is crucial in designing roadways that discourage speeding. This study investigates the influence of visual surroundings on drivers in 15 US cities using 3,407,253 driver view images from Lytx, covering 4,264 miles of roadways. By segmenting and analyzing these images along with vehicle-related variables, the study examines factors affecting speeding behavior. After filtering the images, to ensure an accurate representation of the driver’s view, 1,340,035 driver view images were used for analysis. Statistical models, including hurdle beta and bivariate probit models with random driver effects as well as Machine Learning’s eXtreme Gradient Boosting (XGBoost), were employed to estimate speeding behavior. The results indicate that factors within the driver's visual environment, weather conditions, and driver heterogeneity significantly impact speeding. Speeding behavior also varies across geographic locations, even within the same city, suggesting a connection between local context and speeding. The study highlights the importance of the driver's environment, showing that more open spaces encourage speeding, while areas with trees and buildings are associated with reduced speeding. Notably, this research differs from previous studies by utilizing real-time data from dash cameras, providing a dynamic and accurate representation of the driver's visual surroundings. This approach enhances the reliability of the findings and empowers transportation engineers and planners to make informed decisions when designing roadways and implementing interventions to address effectively excessive speeding. In addition to examining speeding behavior, the study also analyzes time-headway, a key factor affecting safety and risky driver behavior, to explore its relationship with speeding. The findings offer valuable insights into the factors influencing speeding and the driver's visual environment. These insights can inform efforts to create environments that discourage speeding (and close car following) and ultimately reduce severe accidents caused by excessive speed (and tailgating).

show abstract

Learning spatial-temporal dynamics and interactivity for short-term passenger flow prediction in urban rail transit

et al. 2023

Appl Intell

View full text Add to dashboard Cite

Sequence-to-Sequence Recurrent Graph Convolutional Networks for Traffic Estimation and Prediction Using Connected Probe Vehicle Data

Cited by 22 publications

References 47 publications

Predicting network flows from speeds using open data and transfer learning

Predicting network flows from speeds using open data and transfer learning

Exploring the Influence of Drivers’ Visual Surroundings on Speeding Behavior

Learning spatial-temporal dynamics and interactivity for short-term passenger flow prediction in urban rail transit

Contact Info

Product

Resources

About