---

   Introduction: It is of prime importance to consider the pattern and geographical changes of a disease, in each community independently, to determine high and low risk areas. Mapping diseases is a set of statistical methods which attempt to provide precise maps by which the geographical distribution of a disease is estimated. In this study, Bayesian methods were applied to estimate the relative death rate of work-related accidents in Iran.

  Methods: For the purpose of this study, the data of work-related accidents of Iran in 2009 were analyzed. To estimate the parameters of the map, empirical Bayes method (Poisson-Gamma method) was applied using Winbugs 1.4 software. Moreover, the Arc GIs 9.2 software was used to set relative incidence of death and accident related maps.

  Results: Regarding the estimates achieved by empirical Bayes method and applying Poisson-Gamma for the incidence of work related accidents in 2009, the maximum and minimum prevalence risk rate among men was 2.991 in Markazi province and 0.457 in Khorasan Razavi province, while they were 3.848 in Semnan province and 0.243 in Hormozgan province for women.

Conclusion: Overall, the incidence of work-related accidents follows no specific geographical distribution pattern and in most provinces the pattern was different for men and women in Iran. By and large, the incidence of these events in the neighboring provinces of Tehran is more than the other parts of the country.

---

Introduction: Road traffic accidents are one of the leading causes of death worldwide, including Iran. There are several factors involved in the occurrence of them; using different models, these factors can be identified and the occurrence of road traffic accidents can be predicted. The purpose of this study was to predict road traffic accidents based on weather conditions using artificial neural network model.
Methods: In the present study, traffic data during the years 2014 to 2017, were examined using a multilayer perceptron network. Network input variables included minimum temperature, average temperature, average rainfall, maximum wind speed, glaciation, air pressure, fog concentration and output variable was the number of accidents.
Results: The designed network with seven neurons in the input layer, four neurons in the middle layer, and one neuron in the output layer with Lunberg-Marquardt optimization function and sigmoid tangent transfer function in the middle layer and linear transmission function in the output layer was selected as the optimal network. The results showed that the designed network with the correlation coefficient of 0.90 and mean square error of 0.01 has a high ability to predict road traffic accidents.
Conclusion: The results showed that the artificial neural network has a good performance for predicting road traffic accidents. Given the importance of predicting road traffic accidents and its role in promoting the health of people in such accidents, the results of this study can be used to expand more effective preventive measures for policy makers and researchers.