Rule discovery to identify patterns contributing to overrepresentation and severity of run-off-the-road crashes

Montella, Alfonso; Mauriello, Filomena; Pernetti, Mariano; Riccardi, Maria Rella

doi:10.1016/j.aap.2021.106119

Cited by 32 publications

(16 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, as motorists become older, pedestrians are more likely to suffer no injuries once in a crash. Male drivers were also more likely to be involved in the most serious crashes, and our results confirm previous findings [22,62]. These factors may reflect the typically more aggressive way of driving of young male drivers.…”

Section: Discussionsupporting

confidence: 90%

Parametric and Non-Parametric Analyses for Pedestrian Crash Severity Prediction in Great Britain

et al. 2022

Self Cite

View full text Add to dashboard Cite

The study aims to investigate the factors that are associated with fatal and severe vehicle–pedestrian crashes in Great Britain by developing four parametric models and five non-parametric tools to predict the crash severity. Even though the models have already been applied to model the pedestrian injury severity, a comparative analysis to assess the predictive power of such modeling techniques is limited. Hence, this study contributes to the road safety literature by comparing the models by their capabilities of identifying the significant explanatory variables, and by their performances in terms of the F-measure, the G-mean, and the area under curve. The analyses were carried out using data that refer to the vehicle–pedestrian crashes that occurred in the period of 2016–2018. The parametric models confirm their advantages in offering easy-to-interpret outputs and understandable relations between the dependent and independent variables, whereas the non-parametric tools exhibited higher classification accuracies, identified more explanatory variables, and provided insights into the interdependencies among the factors. The study results suggest that the combined use of parametric and non-parametric methods may effectively overcome the limits of each group of methods, with satisfactory prediction accuracies and the interpretation of the factors contributing to fatal and serious crashes. In the conclusion, several engineering, social, and management pedestrian safety countermeasures are recommended.

show abstract

Section: Discussionsupporting

confidence: 90%

Parametric and Non-Parametric Analyses for Pedestrian Crash Severity Prediction in Great Britain

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent studies used various techniques to conduct pattern mining using large amounts of crash data, such as ARM [36], Bayesian networks [41], neural networks [42], linear regression networks [43], cluster analysis [44], random forests [45], and support vector machine [46]. ARM has the advantage of finding meaningful associations and providing valuable insights into the interdependence between roadway, environmental, and driver-related factors and the frequency and severity of crashes [29]. Besides, ARM is more suitable for discovering patterns in large data The number of moving or traffic violations the participant has had in the three years 1 2 or more NUMcrash 0…”

Section: Methodsmentioning

confidence: 99%

Crash/Near-Crash Analysis of Naturalistic Driving Data Using Association Rule Mining

Liu

et al. 2022

Journal of Advanced Transportation

View full text Add to dashboard Cite

This study explores the associations between crash/near-crash (C/NC) events and roadway, driver-related, and environmental factors in naturalistic driving studies (NDS). We used the Naturalistic Engagement in Secondary Tasks (NEST) dataset, which is massive and detailed and contains 50 million miles of naturalistic driving data resulting from the Strategic Highway Research Program 2 (SHRP2). Association rule mining (ARM) is applied to extract the rules for frequently occurring events. The generated association rules are filtered by four metrics (support, confidence, lift, and conviction) and validated by the lift increase criterion. A three-step analysis is performed to obtain a comprehensive understanding of the rules of C/NC events. The 20 most frequent items are first selected to investigate their relationship with the C/NC events. Subsequently, the association rules are used to identify the factors contributing to C/NC events. Finally, correlations between contributing factors and different severities of crashes (I—most severe, II—police-reportable, III—minor crash, and IV—low-risk tire strike) are analyzed by ARM. The results demonstrate that C/NC events occur most frequently on straight and level road segments with no controlled intersections or traffic control devices when drivers are performing secondary tasks. Thus, the reasons for these crashes are carelessness and overconfidence. In addition, a median strip or barrier and a wider road can significantly reduce the frequency and severity of crash events. Moreover, gender, age, average annual mileage, and secondary tasks are highly correlated with the frequency and severity of C/NC events. Drivers with visual-spatial disabilities or crash records are more likely to be involved in the most severe crash events. Near-crash events occur more frequently at higher traffic density and on roads with traffic control devices and controlled intersections. These conditions may keep drivers alert, preventing crashes.

show abstract

“…With an understandable rules framework, ARM advantageously identifies fuzzy patterns and heterogeneous effects among several variables in large databases [ 23 ]. Moreover, it has been widely used for multivariate analysis of crashes involving rainy weather [ 24 ], hazardous material vehicles [ 25 ], pedestrian collisions [ 26 ], roundabouts [ 27 ], and run-off-the-road (ROR) [ 28 ].…”

Section: Introductionmentioning

confidence: 99%

Multivariate analysis of roadway multi-fatality crashes using association rules mining and rules graph structures: A case study in China

Xu²,

Gao³

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

Roadway multi-fatality crashes have always been a vital issue for traffic safety. This study aims to explore the contributory factors and interdependent characteristics of multi-fatality crashes using a novel framework combining association rules mining and rules graph structures. A case study is conducted using data from 1068 severe fatal crashes in China from 2015 to 2020, and 1452 interesting rules are generated using an association rule mining approach. Several modular rules graph structures are constructed based on graph theory to reflect the interactions and patterns between different variables. The results indicate that multi-fatality crashes are highly associated with improper operations, passenger overload, fewer lanes, mountainous terrain, and run-off-the-road crashes, representing the key variables of factors concerning driver, vehicle, road, environment, and accident, respectively. Furthermore, crashes involving different severity levels, road categories, and terrain are verified to possess unique association rules and independent crash patterns. Moreover, the proportion of severe crashes caused by a combination of human-vehicle-road-environment factors (43%) is much higher than that of normal crashes (3%). This study reveals that the hidden associations between various factors contribute to the overrepresentation and severity of multi-fatality crashes. It also demonstrates that the crash mechanisms involving multi-fatality crashes and their interactions are more complex at the system level than those for normal crashes. The proposed framework can effectively map the intrinsic link between multiple crash factors and potential risks, providing transportation agencies with helpful insights for targeted safety measures and preventive strategies.

show abstract

Rule discovery to identify patterns contributing to overrepresentation and severity of run-off-the-road crashes

Cited by 32 publications

References 58 publications

Parametric and Non-Parametric Analyses for Pedestrian Crash Severity Prediction in Great Britain

Parametric and Non-Parametric Analyses for Pedestrian Crash Severity Prediction in Great Britain

Crash/Near-Crash Analysis of Naturalistic Driving Data Using Association Rule Mining

Multivariate analysis of roadway multi-fatality crashes using association rules mining and rules graph structures: A case study in China

Contact Info

Product

Resources

About