Abstract
This study presents forecast of highway casualties in Turkey using nonlinear multiple regression (NLMR) and artificial neural network (ANN) approaches. Also, the effect of railway development on highway safety using ANN models was evaluated. Two separate NLMR and ANN models for forecasting the number of accidents (A) and injuries (I) were developed using 27 years of historical data (1980–2006). The first 23 years data were used for training, while the remaining data were utilized for testing. The model parameters include gross national product per capita (GNP-C), numbers of vehicles per thousand people (V-TP), and percentage of highways, railways, and airways usages (TSUP-H, TSUP-R, and TSUP-A, respectively). In the ANN models development, the sigmoid and linear activation functions were employed with feed-forward back propagation algorithm. The performances of the developed NLMR and ANN models were evaluated by means of error measurements including mean absolute percentage error (MAPE), mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R 2). ANN models were used for future estimates because NLMR models produced unreasonably decreasing projections. The number of road accidents and as well as injuries was forecasted until 2020 via different possible scenarios based on (1) taking TSUPs at their current trends with no change in the national transport policy at present, and (2) shifting passenger traffic from highway to railway at given percentages but leaving airway traffic with its current trend. The model results indicate that shifting passenger traffic from the highway system to railway system resulted in a significant decrease on highway casualties in Turkey.
Similar content being viewed by others
References
Akgungor AP, Demirel A (2004) Analysis of transportation systems and transportation policies in Turkey. J Eng Sci 10(3):423–430
Szyliowicz JS (2004) Turkey’s surface transportation policy and sustainable development. Middle East Stud 40(1):23–44. doi:10.1080/00263200412331301877
Babalik-Sutcliffe E (2007) Pro-rail policies in Turkey: a policy shift? Transp Rev 27(4):485–498. doi:10.1080/01441640601151564
Turkish Statistical Institute (2006) http://www.tuik.gov.tr. Accessed 10 Sept 2009
Bozkurt E (2002) A model study on road traffic accidents in Turkey. Expertness thesis, the State Institute of Statistics Prime Ministry Republic of Turkey, Turkey
Isik A, Erdem M (2004) Investigation of effective parameters on traffic accidents in Turkey with regression analysis paper presented at 2nd Traffic Forum, ATO, Ankara
Mirasyedi F (2006) Research concerning the effect of weathers on traffic accidents in Turkey and prediction models of traffic accidents. M.Sc. thesis, Kırıkkale University, Turkey
Chang L (2005) Analysis of freeway accident frequencies: negative binomial regression versus artificial neural. Saf Sci 43(8):541–557. doi:10.1016/j.ssci.2005.04.004
Kalyoncuoglu SF, Tigdemir M (2004) An alternative approach for modeling and simulation of traffic data: artificial neural networks. Simul Model Pract Theory 12(5):351–362. doi:10.1016/j.simpat.2004.04.002
Akgungor AP, Dogan E (2008) Estimating road accidents of Turkey based on regression analysis and artificial neural network approach. Adv Transp Stud Int J Sect A 16:11–22
Akgungor AP, Dogan E (2009) An artificial intelligent approach to traffic accident estimation: model development and application. Transport 24(2):135–142. doi:10.3846/1648-4142.2009.24.135-142
Akgungor AP, Dogan E (2009) An application of modified Smeed, adapted Andreassen and artificial neural network accident models to three metropolitan cities of Turkey. Sci Res Essay 4(9):906–913
Cansız ÖF (2011) Improvements in estimating a fatal accidents model formed by an artificial neural network. Simulation 87(6):512–522. doi:10.1177/0037549710370842
Bates DM, Watts DG (2007) Nonlinear regression analysis and its applications. A Wiley-Interscience Publication, New York
Kalogirou S, Bojic M (2000) Artificial neural networks for the prediction of the energy consumption of a passive solar building. Energy 25(5):479–491. doi:10.1016/S0360-5442(99)00086-9
Gonzalez PA, Zamarreno JM (2005) Prediction of hourly energy consumption in buildings based on a feedback artificial neural network. Energy Build 37(6):595–601. doi:10.1016/j.enbuild.2004.09.006
Pao HT (2007) Forecasting electricity market pricing using artificial neural networks. Energy Convers Manag 48(3):907–912. doi:10.1016/j.enconman.2006.08.016
Murat YS (2006) Comparison of fuzzy logic and artificial neural networks approaches in vehicle delay modeling. Transp Res Part C Emerg Technol 14(5):316–334. doi:10.1016/j.trc.2006.08.003
Murat YS, Ceylan H (2006) Use of artificial neural networks for transport energy modeling. Energy Policy 34(17):3165–3172. doi:10.1016/j.enpol.2005.02.010
Murat YS, Baskan O (2006) Modeling vehicle delays at signalized junctions: artificial neural networks approach. J Sci Ind Res 65(7):558–564
Turkish Statistical Institute (2007) http://www.tuik.gov.tr. Accessed 10 Sept 2009
General Directorate of Security Affairs (2007) http://www.egm.gov.tr. Accessed 21 May 2009
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Doğan, E., Akgüngör, A.P. Forecasting highway casualties under the effect of railway development policy in Turkey using artificial neural networks. Neural Comput & Applic 22, 869–877 (2013). https://doi.org/10.1007/s00521-011-0778-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-011-0778-0