Study of Road Accident Prediction Model at Accident Blackspot Area: A Case Study at Selangor

This study is focusing in the accident prediction model by using Multiple Linear Regression and Artificial Neural Network, as well as investigating the effectiveness of both predictive analyses. To meet these objectives, the historical data of accident was analysed with the on-site data for the purpose of relating them with the accident occurrence. Also, the accident historical data and the on-site data were analysed using two predictive models to predict the number of accident in current year. After the analysis, it is revealed that the outcomes obtained from both models were different with greater predicted value from the regression analysis due to greater errors being produced. Less predicted value, greater correlation and less error have been shown by the Artificial Neural Network analysis, concluding that it is more suitable for accident prediction.

[1]  Ryszard Hejmanowski,et al.  Suitability assessment of artificial neural network to approximate surface subsidence due to rock mass drainage , 2015 .

[2]  Qiaojun Xiang,et al.  Research on Traffic Safety of Freeway Upgrade Section , 2013 .

[3]  Galal A. Ali,et al.  Characteristics and Prediction of Traffic Accident Casualties In Sudan Using Statistical Modeling and Artificial Neural Networks , 2012 .

[4]  Mohd Zakwan Ramli.  Development of accident prediction model by using artificial neural network (ANN) , 2011 .

[5]  Y G L Bastos,et al.  Seat belt and helmet use among victims of traffic accidents in a city of Southern Brazil, 1997-2000. , 2005, Public health.

[6]  Riza Atiq Abdullah O.K. Rahmat,et al.  Why Do People Use Their Cars: A Case Study In Malaysia , 2007 .

[7]  Sanjay Misra,et al.  An artificial neural network model for road accident prediction: a case study of a developing country , 2014 .

[8]  Mohamed Abdel-Aty,et al.  Development of Artificial Neural Network Models to Predict Driver Injury Severity in Traffic Accidents at Signalized Intersections , 2001 .

[9]  Oj Oyedepo,et al.  Accident Prediction Models for Akure – Ondo Carriageway, Ondo State Southwest Nigeria; Using Multiple Linear Regressions , 2010 .

[10]  Abimbola O Odumosu,et al.  Demeanour Transposition as Strategy for Traffic Accident Reduction in Nigeria:Case Study of Niger State, Nigeria , 2005 .

[11]  Fajaruddin Mustakim.  Treating hazardous locations at federal route 50 , 2005 .

[12]  Erdem Doan,et al.  An application of modified Smeed, adapted Andreassen and artificial neural network accident models to three metropolitan cities of Turkey , 2009 .