چكيده به لاتين
Growing population growth and rising economic growth and the growing transport industry have increased the demand for off-shore routes. This has increased the incidence of road accidents and the resulting casualties, including injuries and deaths. Road accidents are recognized as the eighth factor in human mortality in the world, and road safety crashes will be recognized as the third most common cause of death for humans by 2020 unless appropriate solutions are made to counter this phenomenon.
In this study, six of the extracted urban bipedal axes were selected as the study area and crash data was collected in the axes for 92-95 years. In this study, multi-layered perceptron model was used for modeling crashes for different axes. The purpose of the multi-layered perceptron model training is to find the optimal value of weights and biases in such a way as to minimize network error. With this view, multi-layered perceptron modeling is an optimization issue with a number of specific parameters. In another section of the work, the Interactive Safety Design Model is introduced.
Based on the collected data, the studied axes included Hamedan to Avaj, Hamedan to Ghorveh, Hamedan to Malayer and Hamedan to Bijar in the area of the protection of Hamedan province, as well as Abhar to Kaidar in the area of protection of Zanjan province and the old road to Abak to Qazvin, in Qazvin province. An appropriate model for the axis of Qazvin, Zanjan and Hamadan was architecture. Also, PNN and RBF networks were implemented and compared for the studied areas. Approximately good results were obtained from the network. The value of the r2 statistic that was calculated was 0.83. The value of the MSE parameter equals to 0.59, which indicates the accuracy of the results in the training phase. For the axis of the Qazvin region, the value of r2 was 0.94. The value of the MSE parameter was also 0.33, which was very good, and showed the accuracy of the results in the training phase.
