Application of Conditional Deep Generative Networks (CGAN) in empirical bayes estimation of road crash risk and identifying crash hotspots  

作　　者：Mohammad Zarei Bruce Hellinga Pedram Izadpanah 

机构地区：[1]Department of Civil and Environmental Engineering,University of Waterloo,Waterloo,ON N2L3G1,Canada

出　　处：《International Journal of Transportation Science and Technology》2024年第1期258-269,共12页交通科学与技术(英文)

摘　　要：The conditional generative adversarial network(CGAN)is used in this paper for empirical Bayes(EB)analysis of road crash hotspots.EB is a well-known method for estimating the expected crash frequency of sites(e.g.road segments,intersections)and then prioritising these sites to identify a subset of high priority sites(e.g.hotspots)for additional safety audits/improvements.In contrast to the conventional EB approach,which employs a statis tical model such as the negative binomial model(NB-EB)to model crash frequency data,the recently developed CGAN-EB approach uses a conditional generative adversarial net work,a form of deep neural network,that can model any form of distributions of the crash frequency data.Previous research has shown that the CGAN-EB performs as well as or bet ter than NB-EB,however that work considered only a small range of crash data character istics and did not examine the spatial and temporal transferability.In this paper a series of simulation experiments are devised and carried out to assess the CGAN-EB performance across a wide range of conditions and compares it to the NB-EB.The simulation results show that CGAN-EB performs as well as NB-EB when conditions favor the NB-EB model(i.e.data conform to the assumptions of the NB model)and outperforms NB-EB in experi ments reflecting conditions frequently encountered in practice(i.e.low sample mean crash rates,and when crash frequency does not follow a log-linear relationship with covariates).Also,temporal and spatial transferability of both approaches were evaluated using field data and both CGAN-EB and NB-EB approaches were found to have similar performance.

关 键 词：Conditional Generative Adversarial Networks(CGAN) Hotspot identification Empirical Bayes method Safety performance function Negative binomial model Network screening Crash data simulation 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]