Development of Models for Crash Prediction and Collision Estimation- A Case Study for Hyderabad City

Document Type : Research Paper


1 PG Student, Department of Civil Engineering, VNR Vignana Jyothi Institute of Engineering and Technology, Hyderabad, Telangana, India.

2 Associate Professor, Department of Civil Engineering, VNR Vignana Jyothi Institute of Engineering and Technology, Hyderabad, Telangana, India

3 Professor, Department of Civil Engineering, University College of Engineering Osmania University, Hyderabad, Telangana, India


Road traffic crash is a cause of unnatural death and occupies fifth position in the world as per WHO records. Road crashes in India are alarming in situation while road safety is professionally lacking and politically missing. Hyderabad city, the capital of newly formed Telangana State occupies sixth position in occurrence of road crashes. An attempt is made to understand which model is suitable for road crash prediction and estimation of collision type which is influencing road crashes in the city. A retrospective observational study was conducted in the city of considering factors as roadway geometrics, traffic data and type of collision. Regression models like Multiple Linear Regression, Poisson Regression, Logit Model and Multinomial Logistic Model are considered for arriving crash prediction models. The suitability of model is based on R2 and chi-square test. It is observed from the analysis through comparison of above model; Logit model has an R2 of 0.7 and is significant for chi-square test. Shoulder condition is an affecting factor for non-fatal crashes in the city which is ascertained by Logit model. Further analysis is also carried for arriving on type of collision influencing on road crashes. It is observed from the results that sideswipe is more significant for road crashes.


-Ackaah, William and Salifu, Mohammed (2011) “Crash prediction model for two-lane rural highways in the Ashanti region of Ghana”, Science direct, Vol. 35, No.1, pp.34-40.
-Anitha Jacob and Anjaneyalu, M.V.L.R. (2013) “Development of crash prediction models for two-lane rural highways using regression analysis”, Highway Research Journal, Vol. 6, pp.59-70.
-Garber, N. and Erhard, A. (2000) “Effect of speed, flow and geometric characteristics on crash frequency for two-lane highways”, Transportation Research Record, Vol.1717, pp.76-83.
-Hanley, K.E., Gibby, A.R. and Ferrara, T.C. (2000) “Analysis of accident reduction factors on California state highways”, Transportation Research Record, Vol.1717, pp.37-45.
-Hauer, E. (1986), “On the estimation of expected number of crashes”, Accident Analysis and Prevention, Vol.18, pp.1-12.
-Haynes, Robert, Lake, Lain, Kingham, Simon, Sabb, Clive E., Pearce, Jamie and Barett, Ross (2008) “The influence of road curvature on fatal crashes in New Zealand”, Accident Analysis and Prevention, Vol. 37, pp.843-850.
-Hong, Dahee (2005) “Development of traffic accident prediction models by traffic and road characteristics in urban areas”, Proceedings of  the Eastern Asia Society for Transportation Studies, Vol. 5, pp.2046 – 2061
-Kumar, M. and Ramesh, A. (2014) “Estimation of influence on type of collision for road accidents using logit models in Cyberabad – Hyderabad -India”, International Journal of Civil and Structural Engineering, Vol.1, No.2, pp.61-65.
-Manisha Minesh Desai, Manisha Minesh, and Patel, A.K. (2010) “Road accidents study based on regression model: a case study of Ahmedabad City”, National Conference on Recent Trends in Engineering & Technology. 
-Ministry of Road Transport Highways (2013), MORTH, New Delhi.
-Murthy, NSSR, and Srinivasa, Rao R. (2015) “Development of model for road accidents based on intersection parameters using regression models”, International Journal of Scientific and Research Publications, Vol.5, No.1.
-National Crime Records Bureau (2013), NCRB, New Delhi.
-Ogden, K.W. (1997) “The effects of paved shoulders on crashes on rural highways”, Accident Analysis and Prevention, Vol. 29, pp.353-362.
-Olawale, Awe Olushina and Idowu Adarabioyo, Mummini (2011) “Multivariate regression techniques for analyzing auto-crash variables in Nigeria”, Journal of Natural Sciences Research, Vol. 1, pp.2224-3186.
-Oyedepo Olugbenga J and Makinde, Oluyemisi (2010) “Accident prediction models for AkureOndo carriageway Ondo state southwest Nigeria: using multiple linear regression”, African Research Review, Vol. 4, No.2, pp.30- 49.