@article{article_346052, title={Prediction of Occupational Accidents for Turkey Until the Year 2025 Using Artificial Neural Networks}, journal={International Journal of Engineering Research and Development}, volume={5}, pages={10–16}, year={2013}, url={https://izlik.org/JA25GA36RA}, author={Ceylan, Hüseyin and Avan, Murat}, keywords={Occupational Accident,Accident Prediction Models,Artificial Neural Networks,Turkey}, abstract={<p align="justify">In this study, occupational accident prediction models were developed by using artificial neural networks (ANNs) for Turkey. Using these models in Turkey until the year 2025 occupational accident, permanent incapacity and the number of dead was estimated by the three different scenarios. In the development of the models, insured workers, work place, occupational accident, dead and incapacity for work values were used as model parameters with data between 1970 and 2010. 2-5-1 neural network architecture was selected as the best network architecture. Sigmoid and pureline function were used for secret layer and output layer respectively. The sigmoid and pureline functions were used as activation functions with feed forward back propagation algorithm. Order to obtain a useful model, the network was trained between 1970 and 2004 to forecast values 2005 to 2010.The model was compared to the real values and it was seen that it is applicable for this aim. The performances of all developed models were evaluated by the use of Mean Absolute Percent Errors (MAPE), Mean Absolute Errors (MAE) and Root Mean Square Errors (RMSE). <br> </p>}, number={1}