Neural Network Self-Learning Model for Complex Assessment of Drinking Water Safety for Consumers

Abstract

© 2017, Springer Science+Business Media, LLC, part of Springer Nature. We need to take into complex assessment a set of influencing factors of drinking water safety. This raises the task of developing an integrated methodology assessing the safety of drinking water that reaches the consumers. For the integrated assessment of the safety of drinking water, the method of clustering was chosen, namely, the neural network method of Kohonen self-organizing maps. Zones were separated by the method of cluster neural network analysis. The zones are characterized by different content of metal cations in drinking water, levels of carcinogenic and non-carcinogenic risk to the health of the child population, and the probability of the receipt of metal cations with potable water to consumers.