This study has aimed to provide a model for predicting the severity of accidents in road and rail crossings of Iran with a fresh look at the data of recent years' crashes in these areas. Although Iran has a considerably smaller number of level crossings in its transportation network, however, considering the number and severity of accidents occurring in these crossings, the importance of the safety in these points. In order to have a more comprehensive understanding of the issue of safety at the level crossings, this section looks at the statistics of traffic accidents. Currently, in many countries, including Iran, the safety of level crossing is evaluated based on the frequency of accidents occurring in them. Considering the severity of these accidents is a subject that has recently been considered by researchers. In addition to the frequency of accidents, cross-country crashes in severity can also be investigated. It is noteworthy that trains, pedestrians and pedestrians are usually associated with high severity. This method is one of the methods for identifying hazardous and risky crossings in the rail transport network. In the context of the severity of crashes in the level crossing of Iran, only one study has been done so far. The study is aimed at presenting an intensive prediction model with a fresh look at the crash data of recent years. In this study, the specifications of the 240 authorized passageways in Iran and the crash data used therein are used. In addition, the logit model is used to predict the severity of accidents. It should be noted that the data used in this study are for the years 2009 to 2013. The results of this study indicate the importance of factors such as type of vehicle, type of collision, number of carriages, street lighting and type of train and road drivers' perception of the severity of road accidents.

In this paper results of the information collection application regarding the occurrence of approaching a model that predicts the accidents intensity. The modeling method used in this research is based on the logistic regression or its substitutes like Probit and dual Logit. At the first stage, by using the public Probit model and defining a parameter with four grades that is illustrative of the intensity of accidents, the independent parameters to be considered have been selected using the results of statistical Wald test.At the second stage, the intensity parameter has been converted to a dual parameter and by using the various compositions of independent parameters, various models for accidents intensity have been approached by dual Logit method. In this research, the modeling principles by logistic regression method have been analyzed and the substitute methods have also been comparatively investigated, and the effect of various independent accident parameters on the accidents intensity has been studied. The study of the effect of parameters on the intensity of accidents showed that there are some reasons responsible for the accidents. It is shown in this paper that applications of the results of Logit and Probit models regarding prediction of motorcycles accidents are almost the same and both are statistically credible.Various parameters regarding the climatic conditions, driver's conditions, vehicles conditions etc… are the inputs of the system as independent variants and the effect of those variants that according to statistical test are credible, have been investigated. Results of this research not only have provided the possibility for prediction of motorcycles accidents intensity using Probit at 4 grade intensity, but also showed that some parameters are mostly responsible for the intensity of accidents.These factors include the vagueness of the driving licenses of the guilty drivers, occurrence of the accidents between 4-6 am, involvement of buses or mini buses in the accidents, occurrence of accidents in highways or ring roads, crashing of motorcycles with heavy vehicles and inefficiency of traffic signs. These are the major parameters responsible for the increased intensity of motorcycles accidents and should be considered in safety programmes regarding motorcycles drivers.

Identifying the factors that contribute to injury as a result of crashes will help policy makers and road designers implement countermeasures, which could reduce crash injury severity, and cost. In result, objective of this study is identifying factors are more likely to contribute to crashes severity. Today, Researchers have utilized mathematical and statistical modeling-schemes to solve this complex road-safety problem. For this, discrete choice modeling is widely used to model injury severity of the crash. From the models, factors contributing to the injury severity are identified. MNL is the most prominent discrete choice model for modeling crash severity. For modeling, the data of a 5-year period of crashes occurred at the rural roads of Ilam province has been used. The input variables of the model were selected after a significance evaluation test. These variables included Age, Speed, Alcohol, Head-on, Airbag, Ejection, Seatbelt, following too Close, Gender, and Curved. After selecting the variables, the accuracy of the model was also studied. To validate the model, the likelihood ratio and the percent correctly predicted by the model at each crash severity level were used. After evaluating the model accuracy in the prediction of accidents severity, it was found that the model provides acceptable results for evaluating crashes severity, and it was found that except curve and following too close variables, all selected variables contributing in crashes severity.