Highlights Big data generated by connected vehicles is used for proactive safety management. A new Geographical Random Forest model is developed to uncover spatial heterogeneity and dependency. Local Random Forest appropriately handles multicollinearity. Pre-crash driving volatility measures (e.g., strong lateral acceleration) are leading factors of crash frequency. Variable Importance of predictors provides insights on potential countermeasures for at-risk intersections.
Abstract Accurate crash frequency prediction is critical for proactive safety management. The emerging connected vehicles technology provides us with a wealth of vehicular motion data, which enables a better connection between crash frequency and driving behaviors. However, appropriately dealing with the spatial dependence of crash frequency and multitudinous driving features has been a difficult but critical challenge in the prediction process. To this end, this study aims to investigate a new Artificial Intelligence technique called Geographical Random Forest (GRF) that can address spatial heterogeneity and retain all potential predictors. By harnessing more than 2.2 billion high-resolution connected vehicle Basic Safety Message (BSM) observations from the Safety Pilot Model Deployment in Ann Arbor, MI, 30 indicators of driving volatility are extracted, including speed, longitudinal and lateral acceleration, and yaw rate. The developed GRF was implemented to predict rear-end crash frequency at intersections. The results show that: 1) rear-end crashes are more likely to happen at intersections connecting minor roads compared to major roads; 2) a higher number of hard acceleration and deceleration events beyond two standard deviations in the longitudinal direction is a leading indicator of rear-end crashes; 3) the optimal GRF significantly outperforms Global Random Forest, with a 9% lower test error and a substantially better fit; and 4) geographical visualization of variable importance highlights the presence of spatial non-stationarity. The proposed framework can proactively identify at-risk intersections and alert drivers when leading indicators of driving volatility tend to worsen.
Predicting intersection crash frequency using connected vehicle data: A framework for geographical random forest
2022-10-20
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Analyse vehicle–pedestrian crash severity at intersection with data mining techniques
Taylor & Francis Verlag | 2022
|Enhanced Crash Frequency Models Using Surrogate Safety Measures from Connected Vehicle Fleet
Transportation Research Record | 2023
|