Traffic Safety Region Estimation Based on SFS–PCA–LSSVM: An Application to Highway Crash Risk Evaluation

Abstract

Accurate real-time crash risk evaluation is essential for making prevention strategy in order to proactively improve traffic safety. Quite a number of models have been developed to evaluate traffic crash risk by using real-time surveillance data. In this paper, the basic idea of traffic safety region is introduced into highway crash risk evaluation. Sequential forward selection (SFS), principal components analysis (PCA) and least squares support vector machine (LSSVM) are used to estimate the traffic safety region and classify the traffic states (safe condition and unsafe condition). The proposed method works by first extracting state variables from the observed traffic variables. Two statistics [Formula: see text] and squared prediction error (SPE) are calculated by SFS–PCA and used as the final state variables for traffic state space. Next, LSSVM is used to estimate the boundary of traffic safety region and identify the traffic states in the traffic state space. To demonstrate the advantage of the proposed method, this study develops two crash risk evaluation models, namely SFS–LSSVM model and PCA–LSSVM model, based on crash data and non-crash data collected on freeway I-880N in Alameda. Validation results show that the method is of reasonably high accuracy for identifying traffic states.