CGAN-EB: A Non-parametric Empirical Bayes Method for Crash Hotspot Identification Using Conditional Generative Adversarial Networks: A Real-world Crash Data Study
This work addresses road safety screening for transportation agencies by improving hotspot identification, but it is incremental as it extends prior simulation-based research to real-world data.
The authors tackled the problem of identifying crash hotspots in road safety by applying a non-parametric empirical Bayes method using Conditional Generative Adversarial Networks (CGAN-EB) to real-world crash data from Washington State, and found that it outperformed the conventional negative binomial-based method in prediction power and hotspot identification tests.
The empirical Bayes (EB) method based on parametric statistical models such as the negative binomial (NB) has been widely used for ranking sites in road network safety screening process. This paper is the continuation of the authors previous research, where a novel non-parametric EB method for modelling crash frequency data data based on Conditional Generative Adversarial Networks (CGAN) was proposed and evaluated over several simulated crash data sets. Unlike parametric approaches, there is no need for a pre-specified underlying relationship between dependent and independent variables in the proposed CGAN-EB and they are able to model any types of distributions. The proposed methodology is now applied to a real-world data set collected for road segments from 2012 to 2017 in Washington State. The performance of CGAN-EB in terms of model fit, predictive performance and network screening outcomes is compared with the conventional approach (NB-EB) as a benchmark. The results indicate that the proposed CGAN-EB approach outperforms NB-EB in terms of prediction power and hotspot identification tests.