WIT Press


Practical Application Of Neural Networks To Predict DO Concentration

Price

Free (open access)

Paper DOI

10.2495/WP990321

Volume

33

Pages

10

Published

1999

Size

933 kb

Author(s)

J.A. Garcia, V. Arroyo, L. Sanchez & J.A. Pino

Abstract

Practical application of neural networks to predict DO concentration J.A. Garcia, V. Arroyo, L. Sanchez, J.A. Pino Information Technologies Group (GTI) Departament of Applied Mathematics and Computational Sciences University ofCantabria Email:jgarcia @ mace, unican.es Abstract This paper presents a different alternative based on neural networks to predict dissolved oxygen concentration (DO) in water masses. This method allows the solution to mathematical models to be obtained more quickly, thus avoiding excessive computing times. With neural networks, non-linear systems can be modelled quite effectively, and time series prediction tasks can be carried out without the need for any excessively complicated calculations. In this paper, the first step has been to look for a suitable neural network model, the solution being found in feedforward backpropagation multilayer perceptron networks. Subsequently, the NevProp network simulator has been used to train and valida

Keywords