Predicting injury severity and crash frequency: Insights into the impacts of geometric variables on downgrade crashes in Wyoming

Moomen, Milhan; Rezapour, Mahdi; Raja, Mustaffa N.; Ksaibati, Khaled

doi:10.1016/j.jtte.2019.04.002

Cited by 13 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hong and Oguchi examined the effect of geometric design on operating speed in Japan. The research findings verified that steep uphill in vertical curves affects the operating speed on a dry surface, and this relation is nonlinear [8].…”

Section: Introductionsupporting

confidence: 61%

“…Operating speed in steep uphill of vertical curves is between 95 km/h and 120 km/h in grade zone 0% to 2%. The diagram about operating speed in different grades, which is the result of research done by Hong and Oguchi in Japan, is shown in Figure 3 [8]. Therefore, selecting the length of the suitable vertical curve, especially for speeds over 90 km/h and by grade lower than 2%, is very important.…”

Section: The Effect Of Wet Pavement and High Speedmentioning

confidence: 99%

“…The main goal of Moomen's thesis was to present the predicting models of the impact of geometric conditions, traffic volumes, and speed on truck-related crashes in two-lane roadways. He used a negative binomial regression model for indicating this relationship [8]. For considering the importance of two-lane roads, we can refer to Chang et al research result [9].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Effect of Low Friction in Pavement Due to Floods and High-speed Vehicles in Increasing the Number of Rescue Vehicles' Driving Accidents

Khabiri

Ghaforifard

2020

HEDQ

View full text Add to dashboard Cite

Background: The rescue operation is dangerous during floods when the street surface is wet and the rescue vehicles moving fast. Rural roads are known with a high percentage of run-off-the-road crashes and accidents, mostly affected by the unsuitable and inappropriate speed of the car and failure to keep a safe side distance from the highway alignment. Determining the length of the vertical curve and the stopping distance depends on the speed parameter in the geometric design. This parameter depends on the traffic flow and the vehicle driver. Materials and Methods: The calculation of distance visibility, especially in the vertical and horizontal curves, has a significant role in the geometric design of roads and the safety of roads and drivers. This study investigates changes in two critical parameters of friction surface of pavement and vehicles’ speed on the probability of accidents. In the present study, by changing the speed parameter, namely, increasing speed and decreasing friction, and reducing the distance of vision, the required vertical curve is calculated and compared with the existing curve length. Thus, when the curve length does not match the required arch length, the accident’s probability increases. Results: One of the study’s findings indicates that with a 5% decrease in the friction coefficient of the vertical curve, the probability of accident increases by about 20%. The results show that an approximately 10% increase in speed can raise the likelihood of a crash by 25% on average. Conclusion: The use of accident reduction-related strategies for rescue vehicles and ambulances will help the victims affected by natural disasters. The results showed that choosing the right speed is very important in flooded wet streets. Driving fast to speed up the relief operation not only increases the risk of traffic accidents but also slows down the relief of natural disasters. The results indicate the proper performance of the model created by the probabilistic method. Besides, this model’s use has the advantage of correctly identifying the factors affecting the increase in risk. Also, it helps to take the right measures to increase safety in the relief of natural disasters, especially floods.

show abstract

Section: Introductionsupporting

confidence: 61%

Section: The Effect Of Wet Pavement and High Speedmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Effect of Low Friction in Pavement Due to Floods and High-speed Vehicles in Increasing the Number of Rescue Vehicles' Driving Accidents

Khabiri

Ghaforifard

2020

HEDQ

View full text Add to dashboard Cite

show abstract

“…The low number of observations for fatal, major, and minor crashes necessitated the combination of fatal, major, and minor crashes with injury crashes for the estimation of the model. The idea of binary classification into injury and PDO classes has been taken from similar studies [35][36][37].…”

Section: Resultsmentioning

confidence: 99%

Explainable Boosting Machine: A Contemporary Glass-Box Model to Analyze Work Zone-Related Road Traffic Crashes

Alahmadi,

Almujibah,

Alotaibi

et al. 2023

Safety

View full text Add to dashboard Cite

Examining the factors contributing to work zone crashes and implementing measures to reduce their occurrence can significantly improve road safety. In this research, we utilized the explainable boosting machine (EBM), a modern glass-box machine learning (ML) model, to categorize and predict work zone-related crashes and to interpret the various contributing factors. The issue of data imbalance was also addressed by utilizing work zone crash data from the state of New Jersey, comprising data collected over the course of two years (2017 and 2018) and applying data augmentation strategies such synthetic minority over-sampling technique (SMOTE), borderline-SMOTE, and SVM-SMOTE. The EBM model was trained using augmented data and Bayesian optimization for hyperparameter tuning. The performance of the EBM model was evaluated and compared to black-box ML models such as combined kernel and tree boosting (KTBoost, python 3.7.1 and KTboost package version 0.2.2), light gradient boosting machine (LightGBM version 3.2.1), and extreme gradient boosting (XGBoost version 1.7.6). The EBM model, using borderline-SMOTE-treated data, demonstrated greater efficacy with respect to precision (81.37%), recall (82.53%), geometric mean (75.39%), and Matthews correlation coefficient (0.43). The EBM model also allows for an in-depth evaluation of single and pairwise factor interactions in predicting work zone-related crash severity. It examines both global and local perspectives, and assists in assessing the influence of various factors.

show abstract

Safe and Efficient Advising Traffic System Around Critical Road Scenarios

Younes¹

2023

Int. J. ITS Res.

View full text Add to dashboard Cite

Predicting injury severity and crash frequency: Insights into the impacts of geometric variables on downgrade crashes in Wyoming

Cited by 13 publications

References 15 publications

The Effect of Low Friction in Pavement Due to Floods and High-speed Vehicles in Increasing the Number of Rescue Vehicles' Driving Accidents

The Effect of Low Friction in Pavement Due to Floods and High-speed Vehicles in Increasing the Number of Rescue Vehicles' Driving Accidents

Explainable Boosting Machine: A Contemporary Glass-Box Model to Analyze Work Zone-Related Road Traffic Crashes

Safe and Efficient Advising Traffic System Around Critical Road Scenarios

Contact Info

Product

Resources

About