Rear-End Crash Risk Analysis considering Drivers’ Visual Perception and Traffic Flow Uncertainty: A Hierarchical Hybrid Bayesian Network Approach

Ding, Naikan; Lu, Linsheng; Jiao, Nisha

doi:10.1155/2021/7028660

Cited by 3 publications

(3 citation statements)

References 81 publications

(173 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, if the vehicle following behind fails to exercise caution or is unable to brake promptly, there is an increased risk of a rear-end collision. Furthermore, Ding, et al [51] emphasized the importance of rear-end crashes on curved roads, with a particular focus on factors such as visual perception and traffic flow uncertainty. Their study further corroborated the association between curved road areas and heightened crash probabilities.…”

Section: Discussionmentioning

confidence: 99%

Analysis of the Effects of Highway Geometric Design Features on the Frequency of Truck-Involved Rear-End Crashes Using the Random Effect Zero-Inflated Negative Binomial Regression Model

Champahom,

Se,

Jomnonkwao

et al. 2023

Safety

View full text Add to dashboard Cite

Statistical data indicate that trucks are more prone to rear-end crashes, making this an area of concern. The objective of this study is to create a model that analyzes the factors influencing the frequency of rear-end crashes involving trucks (TIRC). To achieve this, researchers identified the most appropriate model as Spatial Zero-Inflated Negative Binomial Regression (SZINB). This model takes into account spatial correlation, which plays a significant role in the occurrences of TIRC on different road segments supervised by each highway ward. The estimation of parameters in the SZINB model has led to key findings that shed light on the factors contributing to a higher likelihood of TIRC. These findings include the increased probability of TIRC on curved roads compared to straight ones, roads that feature open middle islands, six lanes per direction, a slope, right-of-way shoulder width, pavement type, lane width, and a post speed limit. Based on these key findings, this study developed policy recommendations and sample measures aimed at reducing the frequency of TIRC. Implementing measures such as improving the road design on curved sections, optimizing middle islands, and enhancing traffic management on wider roads can help mitigate the risk of crashes involving trucks.

show abstract

Section: Discussionmentioning

confidence: 99%

Analysis of the Effects of Highway Geometric Design Features on the Frequency of Truck-Involved Rear-End Crashes Using the Random Effect Zero-Inflated Negative Binomial Regression Model

Champahom,

Se,

Jomnonkwao

et al. 2023

Safety

View full text Add to dashboard Cite

show abstract

“…With rapid urbanization and an increase in vehicular traffic, ensuring the safety of road users has become paramount [11]. Accurate traffic flow prediction not only aids in efficient traffic management, but also plays a crucial role in enhancing road safety by anticipating and mitigating potential traffic hazards [12].…”

Section: Introductionmentioning

confidence: 99%

“…Two recent examples demonstrate the importance of uncertainty in deep learning. Such misclassifications or misjudgments in traffic flow predictions can have dire consequences, leading to unsafe road conditions or accidents [12]. Ensuring the reliability of the predictions is not only about accuracy, but is also about ensuring the safety of all road users [6].…”

Section: Introductionmentioning

confidence: 99%

Why Uncertainty in Deep Learning for Traffic Flow Prediction Is Needed

Kim,

Lee

2023

Sustainability

View full text Add to dashboard Cite

Recently, traffic flow prediction has gained popularity in the implementation of intelligent transportation systems. Most of the existing models for traffic flow prediction focus on increasing the prediction performance and providing fast predictions for real-time applications. In addition, they can reveal the integrity of a prediction when an actual value is provided. However, they cannot explain prediction uncertainty. Uncertainty has recently emerged as an important problem to be solved in deep learning. To address this issue, a Monte Carlo dropout method was proposed. This method estimates the uncertainty of a traffic prediction model. Using 5,729,640 traffic data points from Seoul, the model was designed to predict both the uncertainty and measurements. Notably, it performed better than the LSTM model. Experiments were conducted to show that the values predicted by the model and their uncertainty can be estimated together without significantly decreasing the performance of the model. In addition, a normality test was performed on the traffic flow uncertainty to confirm the normality, through which a benchmark for uncertainty was presented. Following these findings, the inclusion of uncertainty provides additional insights into our model, setting a new benchmark for traffic predictions, and enhancing the capabilities of intelligent transportation systems.

show abstract

Using multicolor perceptual markings as a rear-end crash risk mitigator: A field investigation

Zhang

Hou²,

Ding³

et al. 2023

Accident Analysis & Prevention

View full text Add to dashboard Cite

Rear-End Crash Risk Analysis considering Drivers’ Visual Perception and Traffic Flow Uncertainty: A Hierarchical Hybrid Bayesian Network Approach

Cited by 3 publications

References 81 publications

Analysis of the Effects of Highway Geometric Design Features on the Frequency of Truck-Involved Rear-End Crashes Using the Random Effect Zero-Inflated Negative Binomial Regression Model

Analysis of the Effects of Highway Geometric Design Features on the Frequency of Truck-Involved Rear-End Crashes Using the Random Effect Zero-Inflated Negative Binomial Regression Model

Why Uncertainty in Deep Learning for Traffic Flow Prediction Is Needed

Using multicolor perceptual markings as a rear-end crash risk mitigator: A field investigation

Contact Info

Product

Resources

About