An Evaluation Method for Water Quality Based on the Improved SOM Neural Network

Abstract:

In recent years, people have been paying increasingly attention on monitoring the quality of drinking water, which becomes rather necessary after natural disasters such as the Beijing 7.21 rainstorm, considering that the drinking water is one of the main medium for epidemic spreading. Most of the existing evaluation methods have their bases on concise mathematical models, which often fail to describe the complex essential nonlinear relations between the water quality and the chemical material in it. In this paper, we propose the evaluation method by using the SOM neural network, a unsupervised method that is able to classify, and therefore evaluate, given water samples. In order to promote the convergence rate and the precision of SOM neural network when dealing with high dimensional and highly correlated samples, we add a PCA preprocessing procedure. Experiment results demonstrate that the improved SOM neural network could evaluate the water quality with high precision.

• Periodical: Applied Mechanics and Materials (Volumes 373-375)
• Pages: 1220-1223
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.373-375.1220
• Online since: August 2013
• Authors: Hong Yi Li, Ze Xi Li, Chao Jie Wang, Yuan Feng Han, Di Zhao, Jing Cheng He
• Keywords: Correlation Matrix, Principal Component Analysis (PCA), SOM Neural Network, Water Quality Evaluation

References

[1] M. Varsta, J. Heikkonen, J. Lampinen and J. Del R. Millán. Temporal Kohonen Map and the Recurrent Self-Organizing Map: Analytical and Experimental Comparison. Neural Processing Letters,  Vol. 13, No. 3 (2001).

DOI: 10.1007/978-1-4471-1599-1_105

[2] J. Gippert and W. Rosentiel. The Continuous Interpolating Self-organizing Map. Neural Processing Letters,  Vol. 5, No. 3 (2004), pp.185-192.

[3] K. Sharma , S. Kim and M. Singh. An improved feature matching technique for stereo vision applications with the use of self-organizing map. International Journal of Precision Engineering and Manufacturing, Vol. 13, No. 8 (2012), pp.1359-1368.

DOI: 10.1007/s12541-012-0179-z

[4] M. Mitsumori, S. Nakagawa , H. Matsui , T. Shinkai and A Takenaka . Phylogenetic diversity of gene sequences isolated from the rumen as analysed using a self-organizing map (SOM) . Journal of applied microbiology ,  Vol. 109, No. 3 (2010).

DOI: 10.1111/j.1365-2672.2010.04703.x

[5] M. Lützow , I. Kögel-Knabner , K. Ekschmitt , H. Flessa , G. Guggenberger , E. Matzner  and B. Marschner. SOM fractionation methods: Relevance to functional pools and to stabilization mechanisms. Soil Biology and Biochemistry, Vol. 39, No. 9 (2007).

DOI: 10.1016/j.soilbio.2007.03.007

[6] J. Gillabel , B. Lopez , J. SIX , R. Merckx. Experimental evidence for the attenuating effect of SOM protection on temperature sensitivity of SOM decomposition. Global Change Biology, Vol. 16, No. 10 (2010), pp.2789-2798.

DOI: 10.1111/j.1365-2486.2009.02132.x