The classification of vehicular crashes based on their severity is crucial since not all of them have the same financial and injury values. In addition, avoiding crashes by identifying their influential factors is possible via accurate prediction modeling. In crash severity analysis, accurate and time-saving prediction models are necessary for classifying crashes based on their severity. Moreover, statistical models are incapable of identifying the potential severity of crashes regarding influencing factors incorporated in models. Unlike previous research efforts, which focused on the limited class of crash severity, including property damage only (PDO), fatality, and injury by applying data mining models, the present study sought to predict crash frequency according to five severity levels of PDO, fatality, severe injury, other visible injuries, and complaint of pain. The multinomial logistic regression (MLR) model and data mining approaches, including artificial neural network-multilayer perceptron (ANN-MLP) and two decision tree techniques, (i.e., Chi-square automatic interaction detector (CHAID) and C5.0) are utilized based on traffic crash records for State Highways in California, USA. The comparison of the findings of the relative importance of ten qualitative and ten quantitative independent variables incorporated in CHAID and C5.0 indicated that the cause of the crash (X1) and the number of vehicles (X5) were known as the most influential variables involved in the crash. However, the cause of the crash (X1) and weather (X2) were identified as the most contributing variables by the ANN-MLP model. In addition, the MLR model showed that the driver’s age (X11) accounts for a larger proportion of traffic crash severity. Therefore, the sensitivity analysis demonstrated that C5.0 had the best performance for predicting road crash severity. Not only did C5.0 take a shorter time (0.05 s) compared to CHAID, MLP, and MLR, it also represented the highest accuracy rate for the training set. The overall prediction accuracy based on the training data was approximately 88.09% compared to 77.21 and 70.21% for CHAID and MLP models. In general, the findings of this study revealed that C5.0 can be a promising tool for predicting road crash severity.

Objective The role of pupils liaisons education on social discipline promotion and road traffi c injury prevention was the main objective of this study. Methods It was a before-after interventional study on 2800 pupils randomly selected from six different districts of Tehran. Data was collected by a questionnaire for children's performances and other demographic information. Validity and reliability of questionnaire was determined by content validity and test re test. Results Subjects were 2800 pupils 8-15 years (Mean and median of ages: 11 years). Overall, 47.7% of pupils were boys and others girls. In general, 85.9% of parents had positive reaction to point out of their fi lial, 11% with no reaction and only 3% were protested to fi lial pointing out. lack of seat belt use 39.1%, speaking with mobile and driving 31.8% and speeding 29.8% as major offences. Recorded offences by traffi c police before the intervention was 2789 cases (SD = 2.6). A significant differences with 17.9 percent reduction in offences were observed after intervention (2290 cases, SD = 2.6, p < 0.001). In 9 part of education which was focused by pupils liaisons there was a range of (9.9-55.6%) with signifi cant reduction (p < 0.001) except of sleepy or fatigue and mobile speaking during driving. The most offences reduction were eating and drinking during driving (92.7%). Conclusion Pupils' liaison program was effective on reduction of driving offences. The most causes of offences were eating or drinking during driving. All affairs which were educated by pupils liaisons were effective on offences reduction except mobile speaking and driving.

ARTICLE INFO ABSTRACTLead and cadmium are heavy metals and are regarded as traffic generated pollutants scattered in the urban environment through vehicular traffic flow. A total of 13 roads in the city of Isfahan were used for studying the roadside soil pollution amount and determination of effective traffic parameters on soil lead and cadmium amounts. Soil samples were collected and analyzed from 13 sites. An empirical statistical approach was employed for the analysis and modeling purposes. Results suggest that Lead and Cadmium mean concentrations within the distance of 50 m from road curbside are more than background values. These values are well-above the maximum acceptable concentration of heavy metal contents of agricultural soil. Regression analysis of metal concentrations in gutter soil showed that the most effective traffic parameter which affects soil metal concentrations is total traffic volume. It was also observed that Lead and Cadmium concentrations (as independent variables) decreased logarithmically as distance increased from road curbs (as dependent variable), but they decreased exponentially with increment of total traffic volume (as another dependent variable). The regression models developed in this research are used for estimation of Lead and Cadmium concentrations in urban roadside soils on the basis of the distance from road and total traffic volume. The outcomes of this research can be used for mitigation of environmental impacts of roads by using them in urban land use planning, urban design, urban transportation and road traffic management and control.

The first effect of the any natural, artificial and social crises is on the traffic flow and the cutoff of the vital transport arteries. In this effect, various sectors involving in rescue, safety, and evacuation of the wounded and injured people, as well as many decisions made by crisis managers, face a lot of challenges. Therefore, the aim of this study is to investigate the readiness of traffic-related organizations in preventing crisis and traffic damages in metropolitan areas. Materials and Methods: This was an applied study, and the Delphi method was used for collecting the data from respondents. The statistical population consists of 40 Iranian traffic experts. A researcher-made questionnaire was designed for collecting the data, and its validity and reliability were confirmed using Face validity criteria and Cochran's formula (α=0.891). Friedman test was used for statistical analysis, and the goodness of the research model was measured using multiple linear regression analysis. Results: The readiness to continuously monitor traffic crises (beta coefficients=0.864) and readiness for timely notification of traffic crises (beta coefficients=0.399) were reported as the highest effective variables in preventing crisis damages by traffic-related organizations. Conclusion: To deal with the traffic crises, traffic-related organizations should be ready for continuously monitoring and timely notification of traffic crises, inter-organizational interactions, and mobilization of facilities.