Loading...

Prediction of roadway accident frequencies: Count regressions versus machine learning models

Nassiri, H ; Sharif University of Technology

1429 Viewed
  1. Type of Document: Article
  2. Abstract:
  3. Prediction of accident frequency based on traffic and roadway characteristics has been a very significant tool in the field of traffic management. The accident frequencies on 185 roadway segments of the city of Mashhad, Iran, for the year 2007, were used to develop accident prediction models. Negative Binomial Regression, Zero Inated Negative Binomial Regression, Support Vector Machine and Back-Propagation Neural Network models were used to fit the accident data. Both fitting and predicting abilities of the models were evaluated through computing error values. Results show that the NBR model is the most effective model for predicting the number of accidents because of its low prediction and fitting error values. Although the BPNN model has high fitting capability, it does not have the prediction ability of the NBR model. Furthermore, the NBR is easily able to develop and interpret the role of effective variables, in comparison with machine learning models which have a black-box form. Marginal effect values for the NBR and ZINBR models, and sensitivity analysis of the SVM and BPNN models, reveal that Volume to Capacity ratio (V=C), Vehicle- Kilometers Travelled (VKT) and roadway width are the most significant variables. An increase in V=C and roadway width will decrease the number of accidents, however, an increase in VKT and permission to park on the right lane of the roadway can increase the crash frequency
  4. Keywords:
  5. Accident frequency prediction ; Support vector machine ; Zero inated negative binomial regression ; Forecasting ; Neural networks ; Traffic control ; Accident frequency ; Accident prediction model ; Back propagation neural networks ; Effective variables ; Machine learning models ; Negative binomialregression ; Roadway characteristics ; Significant variables ; Accident ; Prediction ; Regression analysis ; Sensitivity analysis ; Traffic management ; Iran ; Mashhad ; Razavi Khorasan
  6. Source: Scientia Iranica ; Vol. 21, issue. 2 , 2014 , p. 263-275 ; 10263098
  7. URL: http://www.scientiairanica.com/en/ManuscriptDetail?mid=279