Kohonen Self-Organizing Maps as a New Method for Determination of Salt Composition of Multi-Component Solutions

Authors: Sergey A. Burikov, Tatiana A. Dolenko, Kirill A. Gushchin, Sergey A. Dolenko

Abstract:

The paper presents the results of clusterization by Kohonen self-organizing maps (SOM) applied for analysis of array of Raman spectra of multi-component solutions of inorganic salts, for determination of types of salts present in the solution. It is demonstrated that use of SOM is a promising method for solution of clusterization and classification problems in spectroscopy of multicomponent objects, as attributing a pattern to some cluster may be used for recognition of component composition of the object.

Keywords: Kohonen self-organizing maps, clusterization, multicomponent solutions, Raman spectroscopy.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1096483

References:

[1] T. R. Crompton, Determination of anions in natural and treated waters. Taylor&Francis, 2002, 828 p.
[2] R. Michalski, "Ion Chromatography as a Reference Method for the Determination of Inorganic Ions in Water and Wastewater,” Critical Reviews in Analytical Chemistry, vol. 36, pp. 107–127, 2006.
[3] M. Chaplin, Water Structure and Behavior. www.lsbu.ac.uk/water, 2008
[4] T. A. Gogolinskaia, S. V. Patsaeva, and V. V. Fadeev, "About regularities of change of band 3100-3700 cm-1 of water Raman spectrum of water solutions of salts,” DAN USSR (Russian), vol. 290, no. 5, pp. 1099-1103, 1986.
[5] W. W. Rudolph, and G. Irmer, "Raman and infrared spectroscopic investigation on aqueous alkali metal phosphate solutions and density functional theory calculations of phosphate-water clusters,” Applied Spectroscopy, vol. 61, no. 12, pp. 274A-292A, Dec. 2007.
[6] A. N. Gorban, V. L. Dunin-Barkovsky et.al., "Neural-network informational models of complex engineering systems” in Neuroinformatica, ch. 4, S.A. Terechov, Ed. Novosibirsk: Nauka. Sibirskoe predpriyatie RAN, 1998.
[7] S. A. Dolenko, T. A. Dolenko, I. G. Persiantsev, V. V. Fadeev, and S. A. Burikov, "Solution of inverse problems of optical spectroscopy using neural networks,” Neurocomputers: Development, Application, no. 1-2, pp. 89-97, 2005. (Russian)
[8] S. A. Burikov, T. A. Dolenko, and V. V. Fadeev, "Identification of Inorganic Salts and Determination of Their Concentrations in Water Solutions from the Raman Valence Band Using Artificial Neural Networks,” Pattern Recognition and Image Analysis, vol. 17, no. 4, pp. 554-559, 2007.
[9] S. A. Burikov, S. A. Dolenko et al., "Application of Artificial Neural Networks to Solve Problems of Identification and Determination of Concentration of Salts in Multi-Component Water Solutions by Raman spectra,” Optical Memory and Neural Networks (Information Optics), vol. 19, no. 2, pp. 140-148, 2010.
[10] S. A. Dolenko, S. A. Burikov, T. A. Dolenko and I.G. Persiantsev, "Adaptive Methods for Solving Inverse Problems in Laser Raman Spectroscopy of Multi-Component Solutions,” Pattern Recognition and Image Analysis, vol. 22, no. 4, pp. 551-558, 2012.
[11] T. Kohonen, Self-Organizing Maps. 3d Edition. Berlin: Springer, 2001.
[12] U. Seiffert, and L.C. Jain, Self-Organizing neural networks: recent advances and applications, Heidelberg, New York: Physica-Verlag, 2002.
[13] "Self-Organizing Maps - Applications and Novel Algorithm Design,” 2011. http://www.intechopen.com/books/self-organizing-mapsapplications- and-novel-algorithm-design
[14] Loginom – analytical platform. http://loginom.basegroup.ru/
[15] S. A. Dolenko, S. A. Burikov, T. A. Dolenko, A. O. Efitorov, and I. G. Persiantsev, "Input data compression at neural-network solution of inverse problems of spectroscopy of multicomponent solutions,” in Proc. XV Russian Scientific-Technical Conf. Neuroinformatica (Russian). Moscow, 2013, vol. 2, pp. 205-215.
[16] B. Desgraupes. Clustring Indices. Supplement for Package clusterCrit for R. http://cran.r-project.org/web/packages/clusterCrit/vignettes/ clusterCrit.pdf