The usage of Artificial Neural Networks (ANN) for the prediction of water pollution has been investigated more extensively over the past few years, and the reason is due to the ANNs efficiency at approximating complex functions. One particular way of designing an ANN used for treatment of water is to use the characteristics of the waste and pollution sources as inputs (water parameters) and to use the appearance of pollutants as ANN outputs. This way, the designed ANNs are able to determine the waste load from different sources of water environments. This paper presents the design and testing of a feedforward neural network for the prediction of photo-degradation in suspension of manganese doped zinc-oxide nanoparticles under visiblelight irradiation. The developed ANN was trained and validated using 210 samples by means of the Levenberg– Marquardt algorithm. The accuracy of true predictions, based on the testing dataset, was 93.78%. The developed system proved to be robust and simple for the prediction of photo-degradation, and can be implemented for the development of systems used for educational purposes.
CITATION STYLE
Avdihodzic, H., Redzovic, Z., & Halilovic, S. (2017). Application of artificial neural network in modelling of photo-degradation suspension of manganese doped zinc oxide nanoparticles under visible-light irradiation. In IFMBE Proceedings (Vol. 62, pp. 137–141). Springer Verlag. https://doi.org/10.1007/978-981-10-4166-2_21
Mendeley helps you to discover research relevant for your work.