Vulnerable road users’ crash hotspot identification on multi-lane arterial roads using estimated exposure and considering context classification

Mahmoud, Nada; Abdel-Aty, Mohamed; Cai, Qing; Zheng, Ou

doi:10.1016/j.aap.2021.106294

Cited by 20 publications

(7 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FDOT, in particular, has advocated the use of the new context classification guide that categorizes roadways and intersections into eight categories in accordance with land use, development patterns, and roadway connectivity, as well as other primary and secondary measures in crash prediction models, to achieve higher predictive accuracy ( 11 ). The effectiveness of the context-based approach has been extensively investigated in the previous literature ( 12 , 24 , 25 ). For instance, Al-Omari et al ( 24 ) validated the performance of FDOT context classification-based SPFs in comparison with other levels of modeling; Li et al ( 26 ) utilized this approach to develop CMFs for alternative cross-sections of rural four-lane roadways in a variety of contexts.…”

Section: Literature Reviewmentioning

confidence: 99%

Developing Economic Loss-Based Thresholds for Improving Context-Specific Crash Prediction Models

Koloushani

Abazari

Khayamim

et al. 2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Negative binomial-based safety performance functions (SPFs) have been extensively used by United States Department of Transportation professionals for predictive crash analysis. Recently, the Florida Department of Transportation (FDOT) has developed a context classification approach and incorporated it into crash prediction models, which has the potential to significantly enhance their accuracy and reliability. The additional modeling contexts and parameters make it more challenging to diagnose and remedy modeling problems, however. Particularly for roadway segments with low annual average daily traffic (AADT), short lengths, or low counts of severe crashes, the SPF models significantly underestimate the actual number of crashes. This uncertainty in SPF predictions can lead FDOT practitioners to reach misleading conclusions, such as failing to detect sites with genuinely high crash rates. This project intends to establish thresholds for certain SPF parameters to ensure reliable crash predictions are obtained across various context classes. For this purpose, we (a) developed a functional statistical model that quantifies economic loss relative prediction errors as a function of AADT volume and (b) calculated the minimum context-specific AADT threshold for each segment length group, roadway category, context classification, and crash severity combination. Employing the developed AADT thresholds confirmed up to 89% reduction in SPF prediction errors for the most represented context class. In light of the results obtained, we are able to conclude that context-specific AADT thresholds perform well in significantly reducing prediction errors for the thresholded segments and contexts on Florida roadways.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Developing Economic Loss-Based Thresholds for Improving Context-Specific Crash Prediction Models

Koloushani

Abazari

Khayamim

et al. 2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…Moreover, business and commercial areas appeared to have strong associations with increased pedestrian-involved fatal crashes in a research study conducted by Kim et al ( 20 ). Mahmoud et al ( 25 ) also focused on crashes involving vulnerable road users to identify crash hotspots considering a context classification system. According to their study, the context classification system’s descriptions of various land uses have a significant correlation with crashes.…”

Section: Literature Reviewmentioning

confidence: 99%

Investigating Spatial Correlations Between Land Use and Pedestrian Injury Severity in Crashes Occurring Away From Intersections in Northwest Florida

Koloushani

Karaer

Özgüven

et al. 2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Roadway crashes are an increasing concern worldwide, and pedestrians are among the most vulnerable road users because of several special characteristics, including their fragility. While focusing on pedestrian-involved crashes that occurred far away from intersections, a more systematic investigation is needed to determine whether there is a relationship between the severity of these crashes and the land use types surrounding the crash locations. To investigate this issue, a network-based logistic regression model was employed to assess the impact of the distance between pedestrian-involved crash locations and the centroid of an associated land use of various types. In addition, a set of logistic models was developed to assess the effect of traffic- and environment-related factors, such as daylight and the average annual daily traffic (AADT), on the severity of crashes occurring around each land use. Several types of land use appeared to be influential in predicting pedestrian-involved crash severity. The probability of a severe pedestrian-involved crash increased around commercial land use types including retail stores or night clubs whereas it decreased around university campuses. Moreover, among the crash attributes, daylight contributed to the severity of pedestrian-involved crashes regardless of the surrounding land use type while average traffic was found to be a statistically significant factor for the crashes that occurred particularly around parking lots and office buildings. Pedestrian-involved crashes mostly occurred in the vicinity of office buildings during daylight hours, and the pedestrians were less likely to be severely injured. The findings provided valuable insight into the measurements concerning pedestrian safety with respect to various types of land use.

show abstract

“…The XGBoost comes in two versions: the Linear Booster and Tree Booster (Chen and Guestrin, 2016). It is noteworthy that these machine learning algorithms have been used in many application fields in the literature including cycling and transportation (Dadashova et al, 2020; Khasawneh et al, 2020; Litzenberger et al, 2018; Mahmoud et al, 2021; Munira and Sener, 2020; Sun and Mobasheri, 2017). To compare their performance, we tuned each model parameter separately to minimize the mean absolute error (MAE) and to maximize R 2 .…”

Section: Machine Learning Analysismentioning

confidence: 99%

Quantifying changes in bicycle volumes using crowdsourced data

Al-Ramini

Takallou

Piatkowski

et al. 2022

Environment and Planning B: Urban Analytics and City Science

View full text Add to dashboard Cite

Most cities in the United States lack comprehensive or connected bicycle infrastructure; therefore, inexpensive and easy-to-implement solutions for connecting existing bicycle infrastructure are increasingly being employed. Signage is one of the promising solutions. However, the necessary data for evaluating its effect on cycling ridership is lacking. To overcome this challenge, this study tests the potential of using readily-available crowdsourced data in concert with machine-learning methods to provide insight into signage intervention effectiveness. We do this by assessing a natural experiment to identify the potential effects of adding or replacing signage within existing bicycle infrastructure in 2019 in the city of Omaha, Nebraska. Specifically, we first visually compare cycling traffic changes in 2019 to those from the previous two years (2017–2018) using data extracted from the Strava fitness app. Then, we use a new three-step machine-learning approach to quantify the impact of signage while controlling for weather, demographics, and street characteristics. The steps are as follows: Step 1 (modeling and validation) build and train a model from the available 2017 crowdsourced data (i.e., Strava, Census, and weather) that accurately predicts the cycling traffic data for any street within the study area in 2018; Step 2 (prediction) use the model from Step 1 to predict bicycle traffic in 2019 while assuming new signage was not added; Step 3 (impact evaluation) use the difference in prediction from actual traffic in 2019 as evidence of the likely impact of signage. While our work does not demonstrate causality, it does demonstrate an inexpensive method, using readily-available data, to identify changing trends in bicycling over the same time that new infrastructure investments are being added.

show abstract

Vulnerable road users’ crash hotspot identification on multi-lane arterial roads using estimated exposure and considering context classification

Cited by 20 publications

References 71 publications

Developing Economic Loss-Based Thresholds for Improving Context-Specific Crash Prediction Models

Developing Economic Loss-Based Thresholds for Improving Context-Specific Crash Prediction Models

Investigating Spatial Correlations Between Land Use and Pedestrian Injury Severity in Crashes Occurring Away From Intersections in Northwest Florida

Quantifying changes in bicycle volumes using crowdsourced data

Contact Info

Product

Resources

About