Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks

Accident Analysis and Prevention

Volumn 38, Issue 3, 2006, Pages 434-444

  Delen, Dursun ^a   Sharda, Ramesh ^a   Bessonov, Max ^a  

^a OKLAHOMA STATE UNIVERSITY   (United States)

Author keywords

Artificial neural networks; Classification; Injury severity; Problem decomposition; Sensitivity analysis

Indexed keywords

ACCIDENT PREVENTION; BEHAVIORAL RESEARCH; CLASSIFICATION (OF INFORMATION); ENVIRONMENTAL IMPACT; NEURAL NETWORKS; SENSITIVITY ANALYSIS;

CLASSIFICATION; INJURY SEVERITY; PROBLEM DECOMPOSITION;

HIGHWAY ACCIDENTS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; CAR DRIVING; DEMOGRAPHY; ENVIRONMENTAL PLANNING; HOSPITALIZATION; HUMAN; NONLINEAR SYSTEM; PSYCHOLOGICAL ASPECT; RISK ASSESSMENT; RISK FACTOR; SAFETY; STATISTICS; TRAFFIC ACCIDENT; UNITED STATES;

ACCIDENTS, TRAFFIC; AUTOMOBILE DRIVING; DEMOGRAPHY; ENVIRONMENT DESIGN; HUMANS; NEURAL NETWORKS (COMPUTER); NONLINEAR DYNAMICS; RISK ASSESSMENT; RISK FACTORS; SAFETY; SEVERITY OF ILLNESS INDEX; UNITED STATES;

EID: 33644889643     PISSN: 00014575     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.aap.2005.06.024     Document Type: Article

References (26)

1. M.A. Abdel-aty, C. Chen, and J.R. Schott An assessment of the effect of driver age on traffic accident involvement using log-linear models Acc. Anal. Prev. 30 6 1998 851 861
2. Abdelwahab, H.T., Abdel-Aty, M.A., 2001. Development of Artificial Neural Network Models to Predict Driver Injury Severity in Traffic Accidents at Signalizes Intersection. Transportation Research Record 1746, Paper No. 01-2234, pp. 6-13.
3. A.S. Al-Ghamdi Using logistic regression to estimate the influence of accident factors on accident severity Acc. Anal. Prev. 34 6 2002 729 741
4. E.L. Allwein, R.E. Schapire, and Y. Singer Reducing multiclass to binary: a unifying approach for margin classifiers J. Mach. Learn. Res. 1 2000 113 141
5. R. Anand, K. Mehrotra, C.K. Mohan, and S. Ranka Efficient classification for multiclass problems using modular neural networks IEEE Trans. Neural Networks 6 1 1995 117 124
6. L. Breiman, J.H. Friedman, R.A. Olshen, and C.J. Stone Classification and Regression Trees 1984 Wadsworth & Brooks/Cole Advanced Books & Software Monterey, CA
7. S. Dissanayake, and J.J. Lu Factors influential in making an injury severity difference to older drivers involved in highway crashes Acc. Anal. Prev. 34 5 2002 609 618
8. J. Edwards The relationship between road accident severity and recorded weather J. Safety Res. 29 4 1998 249 262
9. C.M. Farmer, E.R. Braver, and E.L. Mitter Two-vehicle side impact crashes: the relationship of vehicle and crash characteristics to injury severity Acc. Anal. Prev. 29 3 1997 399 406
10. K.E. Fish, and J.G. Blodgett 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
11. K.E. Fish, and R.S. Segall A visual analysis of learning rule effects and variable importance for neural networks employed in data mining operations Kybernetes: Int. J. Syst. Cybernet. 33 5/6 2004 1127 1142
12. J. Fürnkranz Round robin classification J. Mach. Learn. Res. 2 2002 721 747
13. GES, 2005. National Automotive Sampling System General Estimates System, National Center for Statistics and Analysis of the National Highway Traffic Safety Administration.
14. S. Haykin Neural Networks: A Comprehensive Foundation 1998 Prentice-Hall New Jersey
15. K. Hornik, M. Stinchcombe, and H. White Universal approximation of an unknown mapping and its derivatives using multilayer feedforward network Neural Networks 3 1990 359 366
16. K.M. Kockelman, and Y.J. Kweon Driver injury severity: an application of ordered probit models Acc. Anal. Prev. 34 3 2002 313 321
17. R. Kohavi A study of cross-validation and bootstrap for accuracy estimation and model selection S. Wermter E. Riloff G. Scheler The Fourteenth International Joint Conference on Artificial Intelligence (IJCAI) Montreal, Quebec, Canada 1995 Morgan Kaufman Publishing San Francisco, CA 1137 1145
18. K.J. Lui, and D. McGee An application of conditional logistic regression to study the effects of safety belts, the principal impact points, and car weights on drivers' fatalities J. Safety Res. 19 4 1988 197 203
19. L. Mussone, A. Ferrari, and M. Oneta An analysis of urban collisions using an artificial intelligence model Acc. Anal. Prev. 31 1999 705 718
20. C.J. O'Donnell, and D.H. Connor Predicting the severity of motor vehicle accident injuries using models of ordered multiple choice Acc. Anal. Prev. 28 6 1996 739 753
21. J.C. Principe, N.R. Euliano, and W.C. Lefebre Neural and Adaptive Systems: Fundamentals Through Simulations 2000 John Wiley and Sons New York
22. R. Rifkin, and A. Klautau In defense of one-vs-all classification J. Mach. Learn. Res. 5 2004 101 141
23. SPSS SPSS Clementine for Windows 2005 SPSS Inc. Chicago, IL
24. D.M.J. Tax, and R.P.W. Duin Using two-class classifiers for multiclass classification Proceedings of the 16th International Conference on Pattern Recognitions, vol. 2 August 11-15 2002 IEEE Press 124 127
25. R. Wilson, and R. Sharda Bankruptcy prediction using neural networks Decis. Support Syst. 11 1994 545 557
26. D.P. Wood, and C.K. Simms Car size and injury risk: a model for injury risk in frontal collisions Acc. Anal. Prev. 34 2002 93 99