Predicting motor vehicle collisions using Bayesian neural network models: An empirical analysis

Accident Analysis and Prevention

Volumn 39, Issue 5, 2007, Pages 922-933

  Xie, Yuanchang ^a   Lord, Dominique ^a   Zhang, Yunlong ^a  

^a Texas AandM University   (United States)

Author keywords

Artificial neural networks; Bayesian methods; Frontage roads; Negative binomial; Statistical model

Indexed keywords

BAYESIAN NETWORKS; MATHEMATICAL MODELS; NEURAL NETWORKS; STATISTICAL METHODS;

BAYESIAN METHODS; FRONTAGE ROADS; NEGATIVE BINOMIAL; STATISTICAL MODEL;

HIGHWAY ACCIDENTS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; BAYES THEOREM; BINOMIAL DISTRIBUTION; EMPIRICISM; HUMAN; MONTE CARLO METHOD; SENSITIVITY AND SPECIFICITY; STATISTICAL MODEL; STATISTICS; TRAFFIC ACCIDENT;

ACCIDENTS, TRAFFIC; ALGORITHMS; BAYES THEOREM; BINOMIAL DISTRIBUTION; EMPIRICISM; HUMANS; MODELS, STATISTICAL; MONTE CARLO METHOD; NEURAL NETWORKS (COMPUTER); SENSITIVITY AND SPECIFICITY;

EID: 34548502433     PISSN: 00014575     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.aap.2006.12.014     Document Type: Article

References (59)

1. Abdelwahab H.T., and Abdel-Aty M.A. Artificial neural networks and logit models for traffic safety analysis of toll plazas. Transport. Res. Rec. 1784 (2002) 115-125
2. Bonneson, J.A., Zimmerman, K., Fitzpatrick, K., 2006. Road safety design synthesis. TTI Report 0-4703-P1. Texas Transportation Institute, College Station, TX.
3. Cameron A.C., and Trivedi P.K. Regression Analysis of Count Data (1998), Cambridge University Press, Cambridge, UK
4. Chin H.C., and Quddus M.A. Applying the random effect negative binomial model to examine traffic accident occurrence at signalized intersections. Accid. Anal. Prev. 35 2 (2003) 253-259
5. Delen D., Sharda R., and Bessonov M. Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks. Accid. Anal. Prev. 38 3 (2006) 434-444
6. Donnell E.T., and Mason J.M. Predicting the frequency of median barrier crashes on Pennsylvania interstate highways. Accid. Anal. Prev. 38 3 (2006) 590-599
7. El-Basyouny K., and Sayed T. Comparison of two negative binomial regression techniques in developing accident prediction models. Proceedings of the Transportation Research Board 85th Annual Meeting. Washington, DC (2006) (CD-ROM)
8. Fish K.E., and Blodgett J.G. A visual method for determining variable importance in an artificial neural network model: an empirical benchmark study. J. Target. Meas. Anal. Market. 11 3 (2003) 244-254
9. Hauer E. Identification of sites with promise. Transport. Res. Rec. 1542 (1996) 54-60
10. Hauer E. Observational Before-After Studies in Road Safety: Estimating the Effect of Highway and Traffic Engineering Measures on Road Safety (1997), Elsevier Science Ltd., Oxford
11. Hauer, E., 2000. Lane width and safety. Draft document. Review of Literature for the Interactive Highway Safety Design Model, Toronto, Ont. (http://www.roadsafetyresearch.com/, accessed on December 14, 2006).
12. Hauer E., Allery B.K., Kononov J., and Griffith M.S. How to best rank site with promise. Transport. Res. Rec. 1897 (2004) 48-54
13. Hauer E., Council F.M., and Mohammedshah Y. Safety models for urban four-lane undivided urban segments. Transport. Res. Rec. 1897 (2004) 96-105
14. Hiselius L.W. Estimating the relationship between accident frequency and homogeneous and inhomogeneous traffic flows. Accid. Anal. Prev. 36 6 (2004) 985-992
15. Hornik K., Stinchcombe M., and White H. Multilayer feed-forward networks are universal approximators. Neural Netw. 2 5 (1989) 359-366
16. Hughes, W., Eccles, K., Harwood, D., Potts, I., Hauer, E., 2004. Development of a Highway Safety Manual. Appendix C: Highway Safety Manual Prototype Chapter: Two-Lane Highways. NCHRP Web Document 62 (Project 17-18(4)). Washington, DC (available at http://www.highwaysafetymanual.org/, accessed June 2006).
17. Kumara S.S.P., and Chin H.C. Modeling accident occurrence at signalized tee intersections with special emphasis on excess zeros. Traffic Inj. Prev. 3 4 (2003) 53-57
18. Lee J., and Mannering F. Impact of roadside features on the frequency and severity of run-off-roadway accidents: an empirical analysis. Accid. Anal. Prev. 34 2 (2002) 149-161
19. Liang F. An effective Bayesian neural network classifier with a comparison study to support vector machine. Neural Comput. 15 8 (2003) 1959-1989
20. Liang F. Bayesian neural networks for nonlinear time series forecasting. Stat. Comput. 15 1 (2005) 13-29
21. Liang F., and Wong W.H. Real-parameter evolutionary Monte Carlo with applications to Bayesian mixture models. J. Am. Stat. Assoc. 96 454 (2001) 653-666
22. Lord D. Modeling motor vehicle crashes using Poisson-gamma models: examining the effects of low sample mean values and small sample size on the estimation of the fixed dispersion parameter. Accid. Anal. Prev. 38 4 (2006) 751-766
23. Lord D., and Bonneson J.A. Estimating accident modification factors for rural frontage roads in Texas. Paper presented at the 86th Annual Meeting of the Transportation Research Board. Washington, DC (2006)
24. Lord, D., Miranda-Moreno, L.F., 2006. Effects of low sample mean values and small sample size on the estimation of the fixed dispersion parameter of Poisson-gamma models for modeling motor vehicle crashes: a Bayesian perspective. Working Paper. Zachry Department of Civil Engineering, Texas A&M University, College Station, TX.
25. Lord D., Manar A., and Vizioli A. Modeling crash-flow-density and crash-flow-V/C ratio for rural and urban freeway segments. Accid. Anal. Prev. 37 1 (2005) 185-199
26. Lord D., Washington S.P., and Ivan J.N. Poisson, Poisson-gamma and zero-inflated regression models of motor vehicle crashes: balancing statistical fit and theory. Accid. Anal. Prev. 37 1 (2005) 35-46
27. Lord D., Washington S.P., and Ivan J.N. Further notes on the application of zero inflated models in highway safety. Accid. Anal. Prev. 39 1 (2007) 53-57
28. Ma J., and Kockelman K.M. Bayesian multivariate Poisson regression for models of injury count by severity. Proceedings of the Transportation Research Board 85th Annual Meeting. Washington, DC (2006) (CD-ROM)
29. Mackay, D.J.C., 1992. Bayesian methods for adaptive models. Ph.D. Dissertation. California Institute of Technology, Pasadena, California.
30. Maher M.J., and Summersgill I. A comprehensive methodology for the fitting of predictive accident models. Accid. Anal. Prev. 28 3 (1996) 281-296
31. Marzban C., and Witt A. A Bayesian neural network for severe-hail size prediction. Weather Forecast. 16 5 (2001) 600-610
32. MATLAB Neural Network Toolbox 5 (2006), The MathWorks Inc., Natick, MA
33. Miaou S.P. The relationship between truck accidents and geometric design of road sections: Poisson versus negative binomial regressions. Accid. Anal. Prev. 26 4 (1994) 471-482
34. Miaou S.-P., and Lord D. Modeling traffic crash-flow relationships for intersections: dispersion parameter, functional form, and Bayes versus empirical Bayes. Transport. Res. Rec. 1840 (2003) 31-40
35. Miaou S.P., and Lum H. Modeling vehicle accidents and highway geometric design relationships. Accid. Anal. Prev. 25 6 (1993) 689-709
36. Miaou S.P., and Song J.J. Bayesian ranking of sites for engineering safety improvements: decision parameter, treatability concept, statistical criterion, and spatial dependence. Accid. Anal. Prev. 37 4 (2005) 699-720
37. 2 to evaluate the goodness-of-fit of predictive models. Transport. Res. Rec. 1542 (1996) 6-13
38. Milton J., and Mannering F. The relationship among highway geometrics, traffic-related elements and motor-vehicle accident frequencies. Transportation 25 4 (1998) 395-413
39. Mitra S., and Washington S. On the nature of over-dispersion in motor vehicle crash prediction models. Accid. Anal. Prev. 39 (2007) 459-468
40. Mussone L., Ferrari A., and Oneta M. An analysis of urban collisions using an artificial intelligence model. Accid. Anal. Prev. 31 6 (1999) 705-718
41. Neal, R.M., 1995. Bayesian learning for neural networks. Ph.D. Dissertation. University of Toronto, Toronto, Ontario.
42. Oh J., Lyon C., Washington S., Persaud B., and Bared J. Validation of FHWA crash models for rural intersections: lessons learned. Transport. Res. Rec. 1840 (2003) 41-49
43. Oh J., Washington S.P., and Choi K. Development of accident prediction models for rural highway intersections. Transport. Res. Rec. 1897 (2004) 18-27
44. Oh J., Washington S.P., and Nam D. Accident prediction model for railway-highway interfaces. Accid. Anal. Prev. 38 2 (2006) 346-356
45. Okamoto H., and Koshi M. A method to cope with the random errors of observed accident rates in regression analysis. Accid. Anal. Prev. 21 4 (1989) 317-332
46. Park E.S., and Lord D. Multivariate Poisson-lognormal models for jointly modeling crash frequency by severity. Paper presented at the 86th Annual Meeting of the Transportation Research Board. Washington, DC (2006)
47. In: Payne R.W. (Ed). The Guide to Genstat (2000), Lawes Agricultural Trust, Rothamsted Experimental Station, Oxford, UK
48. Persaud B.N., Lord D., and Palminaso J. Issues of calibration and transferability in developing accident prediction models for urban intersections. Transport. Res. Rec. 1784 (2002) 57-64
49. Qin X., Ivan J.N., Ravishanker N., and Liu J. Hierarchical Bayesian estimation of safety performance functions for two-lane highways using Markov Chain Monte Carlo modeling. J. Transport. Eng. 131 5 (2005) 345-351
50. Riviere C., Lauret P., Ramsamy J.F.M., and Page Y. A Bayesian neural network approach to estimating the energy equivalent speed. Accid. Anal. Prev. 38 2 (2006) 248-259
51. SAS Institute Inc. Version 9 of the SAS System for Windows (2002), SAS Institute Inc., Cary, NC
52. Schluter P.J., Deely J.J., and Nicholson A.J. Ranking and selecting motor vehicle accident sites by using a hierarchical Bayesian model. Statistician 46 3 (1997) 293-316
53. Shankar V., Mannering F., and Barfield W. Effect of roadway geometrics and environmental factors on rural freeway accident frequencies. Accid. Anal. Prev. 27 3 (1995) 371-389
54. Shankar V., Milton J., and Mannering F. Modeling accident frequencies as zero-altered probability processes: an empirical inquiry. Accid. Anal. Prev. 29 6 (1997) 829-837
55. Song J.J., Gosh M., Miaou S.-P., and Malik B. Bayesian multivariate spatial models for roadway traffic crash mapping. J. Multivar. Anal. 97 1 (2006) 246-273
56. Tunaru R. Hierarchical Bayesian models for multiple count data. Aust. J. Stat. 31 2/3 (2002) 221-229
57. Vogt, A., Bared, J.G., 1998. Accident Models for Two-Lane Rural Roads: Segments and Intersections. Report No. FHWA-RD-98-133. Federal Highway Administration, Mclean, Virginia.
58. Warton D.I. Many zeros does not mean zero inflation: comparing the goodness-of-fit of parametric models to multivariate abundance data. Environmetrics 16 2 (2005) 275-289
59. Zhang Y., Ye Z., and Lord D. Estimating the dispersion parameter of the negative binomial distribution for analyzing crash data using a Bootstrapped maximum likelihood method. Paper presented at the 86th Annual Meeting of the Transportation Research Board. Washington, DC (2006)