The quantification of pollutants in drinking water by use of artificial neural networks

Authors:
Michael Cauchi;Luca Bianco;Conrad Bessant
Affiliations:
Cranfield Health, Cranfield University, Bedfordshire, UK MK43 0AL;Cranfield Health, Cranfield University, Bedfordshire, UK MK43 0AL;Cranfield Health, Cranfield University, Bedfordshire, UK MK43 0AL
Venue:
Natural Computing: an international journal
Year:
2011

Citing 7
Cited 0

Neural network design

Neural network design
Computing with membranes

Journal of Computer and System Sciences
Chemometrics: Statistics and Computer Application in Analytical Chemistry

Chemometrics: Statistics and Computer Application in Analytical Chemistry
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Learning regulation functions of metabolic systems by artificial neural networks

Proceedings of the 11th Annual conference on Genetic and evolutionary computation
MP systems approaches to biochemical dynamics: biological rhythms and oscillations

WMC'06 Proceedings of the 7th international conference on Membrane Computing
Metabolic p system flux regulation by artificial neural networks

WMC'09 Proceedings of the 10th international conference on Membrane Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Drinking water attained from aquifers (ground water) is susceptible to contamination from a wide variety of sources. The importance of ensuring that the water is of high quality is paramount. Multivariate calibration in conjunction with analytical techniques can assist in qualifying and quantifying a wide range of pollutants. These can be divided into two types: inorganic and organic. The former typically includes heavy metals such as cadmium and lead; the latter includes a range of compounds such as pesticides and by-products of industrial processes such as oil refining. This article presents the application of the well known nature-inspired paradigm of artificial neural networks (ANNs) for the quantitative determination of inorganic pollutants (namely cadmium, lead and copper) and organic pollutants (namely anthracene, phenanthrene and naphthalene) from multivariate analytical data acquired from the samples. The success of the determination of the pollutants via ANNs is reported in terms of the overall root mean square error of prediction (RMSEP) which is an accepted measure of the difference between the predicted concentrations and the actual concentrations. The work represents a good example of nature-inspired methods being used to solve a genuine environmental problem.