Forecasting the Number of Injured in Traffic Accidents Referred to Forensic Medicine in Hamadan Province using Multi-layered Artificial Neural Network

Road traffic accidents are a new public health problem around the world, and "roadblocks" are one of the main causes.

In this study, using the statistics of traffic injured people referred to forensic medicine in Hamadan province between April 1989 and March 2017, using an artificial neural network, the number of injured for the 12 months leading to 1399 has been predicted. In this study, the appropriate neural network was designed with the data of the injured and then, using the best designed network, the network began to be trained and the network was validated with the absolute percentage of mean error. The authors observe all the ethical considerations of the research in this research and the present research has the code of ethics with the number IR.MEDILAM.REC.1398.213.

The artificial neural network with 12 inputs of one output and 5 hidden layers is suitable for predicting the injured referred to Hamedan forensic medicine. Predict well.

The predicted values showed that the number of traffic injured in Hamadan province is decreasing. Due to the high accuracy of the artificial neural network in this research, this method can be used as a basis for future research in accidents. The downward trend in the number of traffic injured in Hamadan province shows the effectiveness of accident reduction programs in this province