Predicting motor vehicle crashes using Support Vector Machine models.

By Xiugang Li, D. Lord, Yunlong Zhang, Yuanchang Xie. Accident Analysis and Prevention, 2008

332 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Applications of machine learning methods for engineering risk assessment – A review (2020, background): “Applications, such as processing vehicle accident data to predict crash severity for a given location (Li et al., 2008), processing textual data to identify key messages in accident investigation reports (Marucci-Wellman et al.”
Big data, traditional data and the tradeoffs between prediction and causality in highway-safety analysis (2020, methodology): “, support vector machines (Li et al., 2008; Yu and Abdel-Aty, 2013), Bayesian networks (Hossain and Muromachi, 2012; Sun and Sun, 2015), classiﬁcation and regression trees and hierarchical tree-based regression (Karlaftis and Golias, 2002), Bayesian neural networks (Riviere et al., 2006; Xie et…”
Crash Frequency Analysis with Generalized Additive Models (2008, background): “In response to this limitation of GLMs, some researchers proposed using neural networks and support vector machines for crash injury (9) and crash frequency (10, 11) studies.”
Enhanced pedotransfer functions with support vector machines to predict water retention of calcareous soil (2016, methodology): “In our case, the radial basis function (RBF) kernel was used to train and construct our SVR classifiers because the linear kernel is a special case of the RBF kernel (Keerthi & Lin, 2001), which has just one hyperparameter, γ , compared with polynomial and sigmoid kernels (Li et al., 2008).”