CGAN-EB: A non-parametric empirical Bayes method for crash frequency modeling using conditional generative adversarial networks as safety performance functions

Aggarwal, K., Kirchmeyer, M., Yadav, P., Keerthi, S.S., Gallinari, P., 2019. Conditional generative adversarial networks for regression. ArXiv190512868 Cs Stat.(10). Cai, 2020, Real-time crash prediction on expressways using deep generative models, Transp. Res. Part C Emerg. Technol., 117, 102697, 10.1016/j.trc.2020.102697 Cameron, 1990, Regression-based tests for overdispersion in the poisson model, J. Econometrics, 46, 347, 10.1016/0304-4076(90)90014-K Chang, 2005, Analysis of freeway accident frequencies: negative binomial regression versus artificial neural network, Saf. Sci., 43, 541, 10.1016/j.ssci.2005.04.004 Chen, 2019, Traffic flow imputation using parallel data and generative adversarial networks, IEEE Trans. Intell. Transp. Syst., 21, 1624, 10.1109/TITS.2019.2910295 Chen, 2021, A novel explainable deep belief network framework and its application for feature importance analysis, IEEE Sens. J. Cheng, 2005, Experimental evaluation of hotspot identification methods, Acc. Anal. Prevent., 37, 870, 10.1016/j.aap.2005.04.015 Cheng, 2008, New criteria for evaluating methods of identifying hot spots, Transp. Res. Rec., 2083, 76, 10.3141/2083-09 Chollet, F. et al., 2018. Keras: The python deep learning library, ascl ascl–1806. Creswell, 2018, Generative adversarial networks: An overview, IEEE Signal Process. Mag., 35, 53, 10.1109/MSP.2017.2765202 Dong, 2018, An improved deep learning model for traffic crash prediction, J. Adv. Transp., 2018, 10.1155/2018/3869106 Francis, 2012, Characterizing the performance of the conway-maxwell poisson generalized linear model, Risk Analysis: An, Int. J., 32, 167 Geedipally, 2012, The negative binomial-lindley generalized linear model: Characteristics and application using crash data, Acc. Anal. Prevent., 45, 258, 10.1016/j.aap.2011.07.012 Goodfellow, I., 2016. Nips 2016 tutorial: Generative adversarial networks, arXiv preprint arXiv:1701.00160. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y., 2014. Generative adversarial nets. In: Advances in neural information processing systems, pp. 2672–2680. Hauer, E., 1977. Observational before/after studies in road safety. estimating the effect of highway and traffic engineering measures on road safety. Hauer, 2002, Estimating safety by the empirical bayes method: a tutorial, Transp. Res. Rec., 1784, 126, 10.3141/1784-16 Huang, 2009, Empirical evaluation of alternative approaches in identifying crash hot spots: Naive ranking, empirical Bayes, full Bayes methods, Transp. Res. Rec., 2103, 32, 10.3141/2103-05 Huang, 2016, Predicting crash frequency using an optimised radial basis function neural network model, Transp. Transp. Sci., 12, 330 Islam, 2021, Crash data augmentation using variational autoencoder, Acc. Anal. Prevent., 151, 105950, 10.1016/j.aap.2020.105950 Jiang, 2014, Application of poisson random effect models for highway network screening, Acc. Anal. Prevent., 63, 74, 10.1016/j.aap.2013.10.029 Karlaftis, 2011, Statistical methods versus neural networks in transportation research: Differences, similarities and some insights, Transp. Res. Part C Emerg. Technol., 19, 387, 10.1016/j.trc.2010.10.004 Lee, 2002, Modeling young driver motor vehicle crashes: data with extra zeros, Acc. Anal. Prevent., 34, 515, 10.1016/S0001-4575(01)00049-5 Li, 2020, Real-time crash risk prediction on arterials based on lstm-cnn, Acc. Anal. Prevent., 135, 105371, 10.1016/j.aap.2019.105371 Lord, 2010, The statistical analysis of crash-frequency data: a review and assessment of methodological alternatives, Transp. Res. Part A Policy Pract., 44, 291, 10.1016/j.tra.2010.02.001 Lord, 2005, Poisson, poisson-gamma and zero-inflated regression models of motor vehicle crashes: balancing statistical fit and theory, Acc. Anal. Prevent., 37, 35, 10.1016/j.aap.2004.02.004 Lord, 2021, Highway safety analytics and modeling Miaou, 1840, Modeling traffic crash-flow relationships for intersections: dispersion parameter, functional form, and bayes versus empirical bayes methods, Transp. Res. Rec., 2003, 31 Miranda-Moreno, 1908, Alternative risk models for ranking locations for safety improvement, Transp. Res. Rec., 2005, 1 Mirza, M., Osindero, S., 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784. National Research Council (US) Transportation Research Board, 2010. Highway Safety Manual, vol. 1. AASHTO. Pan, 2017, Development of a global road safety performance function using deep neural networks, Int. J. Transp. Sci. Technol., 6, 159, 10.1016/j.ijtst.2017.07.004 Pan, 2020, Road safety performance function analysis with visual feature importance of deep neural nets, IEEE/CAA J. Automat. Sin., 7, 735, 10.1109/JAS.2020.1003108 Pedamonti, D., 2018. Comparison of non-linear activation functions for deep neural networks on mnist classification task. arXiv preprint arXiv:1804.02763. Persaud, 2010, Comparison of empirical Bayes and full Bayes approaches for before–after road safety evaluations, Acc. Anal. Prevent., 42, 38, 10.1016/j.aap.2009.06.028 Qu, 2014, A note on hotspot identification for urban expressways, Saf. Sci., 66, 87, 10.1016/j.ssci.2014.02.006 Rezapour, 2020, Application of deep learning techniques in predicting motorcycle crash severity, Eng. Rep., 2, e12175, 10.1002/eng2.12175 Seabold, S., Perktold, J., 2010. statsmodels: Econometric and statistical modeling with python. In: 9th Python in Science Conference. Sharma, 2017, Activation functions in neural networks, Towards Data Sci., 6 Singh, 2020, Deep neural network-based predictive modeling of road accidents, Neural Comput. Appl., 1 Theofilatos, 2019, Comparing machine learning and deep learning methods for real-time crash prediction, Transp. Res. Rec., 2673, 169, 10.1177/0361198119841571 Wang, 2019, Functional forms of the negative binomial models in safety performance functions for rural two-lane intersections, Acc. Anal. Prevent., 124, 193, 10.1016/j.aap.2019.01.015 Yang, 2021, Copula-based joint modeling of crash count and conflict risk measures with accommodation of mixed count-continuous margins, Analyt. Methods Acc. Res., 31, 100162 Ye, 2018, A semi-nonparametric poisson regression model for analyzing motor vehicle crash data, PloS One, 13, e0197338, 10.1371/journal.pone.0197338 Ye, 2018, A semi-nonparametric poisson regression model for analyzing motor vehicle crash data, PloS One, 13, e0197338, 10.1371/journal.pone.0197338 Zarei, 2022, Benefit–cost-based method to determine when safety performance functions should be redeveloped for use in intersection network screening, Transp. Res. Rec., 10.1177/03611981221092403 Zeng, 2016, Modeling nonlinear relationship between crash frequency by severity and contributing factors by neural networks, Analyt. Methods Acc. Res., 10, 12 Zhang, 2019, Trafficgan: Network-scale deep traffic prediction with generative adversarial nets, IEEE Trans. Intell. Transp. Syst. Zhang, 2020, Modeling pedestrians’ near-accident events at signalized intersections using gated recurrent unit (gru), Acc. Anal. Prevent., 148, 105844, 10.1016/j.aap.2020.105844 Zheng, 2019, Traffic accident’s severity prediction: A deep-learning approach-based cnn network, IEEE Access, 7, 39897, 10.1109/ACCESS.2019.2903319 Zou, 2013, Comparison of sichel and negative binomial models in estimating empirical bayes estimates, Transp. Res. Rec., 2392, 11, 10.3141/2392-02 Zou, 2015, Modeling over-dispersed crash data with a long tail: examining the accuracy of the dispersion parameter in negative binomial models, Analyt. Methods Acc. Res., 5, 1 Zou, 2018, Empirical bayes estimates of finite mixture of negative binomial regression models and its application to highway safety, J. Appl. Stat., 45, 1652, 10.1080/02664763.2017.1389863