Short Duration Crash Prediction for Rural Two-Lane Roadways: Applying Explainable Artificial Intelligence

Wei, Zihang; Das, Subasish; Zhang, Yunlong

doi:10.1177/03611981221096113

Cited by 13 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The likelihood of driver's mistakes resulting from the high speed compounds with loss of control of the vehicle and failure to anticipate and avoid risk in a timely manner. Although many studies have examined the speed-crash association and the association between driver behavior and the presence of passengers (47)(48)(49)(50)(51)(52)(53)(54)(55), examination of the presence of child occupants has not been explored as extensively. The unique contribution of this paper is that it explores the patterns of speeding behavior with child occupancy by utilizing household travel survey data from multiple study areas in Texas.…”

Section: Discussionmentioning

confidence: 99%

Probing into Driver Speeding Patterns and Their Influence on Child Occupancy in Urban Areas

Das

Kong

Wei

et al. 2023

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

Many studies have investigated how child occupants lead to distraction-associated crashes. However, not many studies have focused on how the presence of child passengers influences drivers’ speeding behavior. This study examines how the presence of child passengers can affect driving behavior considering sociodemographic characteristics such as driver’s age, gender, ethnicity, employment, and driving aggressiveness. The current study used resourceful, open-source data based on urban areas in Texas to identify the key patterns of speeding behavior and associated safety surrogates in the presence or absence of child occupants. A unique data analysis procedure known as Taxicab Correspondence Analysis (TCA) was used to analyze the data. The results indicate that speeding patterns are affected by child occupancy during a trip. The results find that regardless of the presence of child passengers, female and unemployed drivers are more likely to drive defensively and male and employed drivers are more likely to drive aggressively. The findings also indicate that drivers from the young age group (20–29 years old) are strongly associated with speeding trips without child occupancy. However, young parent drivers from this age group are strongly associated with non-speeding trips and driving defensively. The study also finds that the impact of child occupancy on driving behaviors varies across different ethnicities. These findings will benefit transportation agencies in identifying aggressive driver groups and developing countermeasures to mitigate speeding behaviors, especially for trips with child occupancy.

show abstract

Section: Discussionmentioning

confidence: 99%

Probing into Driver Speeding Patterns and Their Influence on Child Occupancy in Urban Areas

Das

Kong

Wei

et al. 2023

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

show abstract

“…These factors are possible with small variation across the data to have great prediction power and dominant associations with the critical near-crash events. In recent years, several studies have applied interpretable machine learning in safety analysis (42)(43)(44)(45). There is a need for additional research focus on the application of machine learning related explainability for wide adoption of machine learning based models.…”

Section: Discussionmentioning

confidence: 99%

In-Depth Understanding of Pedestrian–Vehicle Near-Crash Events at Signalized Intersections: An Interpretable Machine Learning Approach

Kong

Das

Zhang

et al. 2022

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

This study used a pedestrian-involved near-crash database and adopted an interpretable machine learning framework using SHapley Additive exPlanations (SHAP) to understand the factors associated with critical pedestrian-involved near-crash events. The results indicate that pedestrians with a relatively higher walking speed are more likely to be involved in critical near-crash events. Furthermore, critical pedestrian-involved near-crash events are highly associated with vehicles with driving speeds of less than 10 mph. A higher pedestrian volume is highly associated with critical near-crash events with left-turn vehicles. It is possible that a higher pedestrian volume increases the occurrence of jaywalking behavior or encourages more pedestrians to step into the crosswalk when they should not. By contrast, a higher pedestrian volume is highly associated with non-critical near-crash events with right-turn vehicles. Right-turn vehicles often expect that there will be pedestrians crossing, and a higher volume of pedestrian traffic increases a driver’s awareness and caution while turning. The study also found that a longer signal cycle is highly associated with critical near-crash events when the pedestrian volume is low, while a relatively short signal cycle length is highly associated with critical near-crash events when the pedestrian volume is high. During non-peak hours, pedestrians have less tolerance for a relatively longer signal cycle. Moreover, a relatively shorter signal cycle length at peak hours will limit the number of pedestrians that can cross during a cycle and encourage the possibility of pedestrians jaywalking or stepping onto the crosswalk when they should not.

show abstract

“…The choice of adopting SMOTE, consistent with Orsini et al (3), was mainly because of the limited sample size available, which would have made RUMC unfeasible, in particular for short data collection durations. It is also worth noting that the practice of using SMOTE is becoming quite established in road safety modeling, and many recent works have applied it with good results (22)(23)(24)(25)(26)(27).…”

Section: Methodsmentioning

confidence: 99%

Conflict-Based Real-Time Road Safety Analysis: Sensitivity to Data Collection Duration and its Implications for Model Resilience

Orsini

Gastaldi

Rossi

2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Conflict-based approaches to real-time road safety analysis can provide several benefits over traditional crash-based models. In particular, as traffic conflicts are much more frequent than crashes, models can be trained with significantly shorter collection periods. Since existing literature has not investigated the sensitivity of real-time conflict prediction models (RTConfPM) to data collection duration, here we aim to fill this gap and discuss the implications for model resilience. A real-world highway case study was analyzed. Methodologically, various traffic variables aggregated into 5 min intervals were selected as predictors, synthetic minority oversampling technique (SMOTE) was applied to deal with unbalanced classification issues, and support vector machine (SVM) was chosen as classifier. The dichotomous response variable separated safe and unsafe intervals into two classes; the latter were defined considering a minimum number of rear-end conflicts within the interval, which were identified using a surrogate measure of safety (SMS), that is, time-to-collision. Several RTConfPMs were trained and tested, considering different data collection durations and different criteria to define the unsafe situation class. The results, which were shown to be robust with respect to the machine learning classifier used, indicate that the models were able to provide reliable predictions with just three to five days of data, and that the increase in performance with collection periods longer than 10 to 15 days was negligible. These findings can be generalized by considering the number of unsafe situations corresponding to the data collection period of each tested model; they highlight the relevance of RTConfPM as a more flexible and resilient alternative to the crash-based approach.

show abstract

Short Duration Crash Prediction for Rural Two-Lane Roadways: Applying Explainable Artificial Intelligence

Cited by 13 publications

References 34 publications

Probing into Driver Speeding Patterns and Their Influence on Child Occupancy in Urban Areas

Probing into Driver Speeding Patterns and Their Influence on Child Occupancy in Urban Areas

In-Depth Understanding of Pedestrian–Vehicle Near-Crash Events at Signalized Intersections: An Interpretable Machine Learning Approach

Conflict-Based Real-Time Road Safety Analysis: Sensitivity to Data Collection Duration and its Implications for Model Resilience

Contact Info

Product

Resources

About