Abstract
Mössbauer spectroscopy is a useful technique for characterizing the valencies, electronic and magnetic states, coordination symmetries and site occupancies of the cation. The Mössbauer parameters of isomer shift and quadrupole splitting are useful to distinguish paramagnetic ferrous and ferric iron in several substances, while the internal magnetic field provides information on the crystallinity. In recent years artificial neural networks have shown to be a powerful technique to solve problems of pattern recognition of a mineral from its Mössbauer spectrum, Mössbauer parameters data bank, crystalline structure and magnetic phases of soil from Mössbauer parameters. A computer software named Mössbauer Effect Assistant has been developed. It uses learning vector quantization neural network linked to a Mössbauer data bank that contains Mössbauer parameters of isomer shift, quadrupole spliting, internal magnetic field and the references of the substances. The program identifies the substance under study and/or its crystalline structure when fed with experimental Mössbauer parameters. It can also list the references from the literature by feeding the name of the substance or the author of the publication. Typical application of Mössbauer Effect Assistant in iron-bearing materials Mössbauer spectroscopy is present in user friendly Microsoft Windows environment.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Fabris J.D., Coey J.M.D., Qinian Qi, and Mussel W.N.: American Mineralogist8 (1995) 664.
Fabris J.D., Coey J.M.D., de Jesus Filho M.F., Santana D.P., Goulart A.T., Fontes M.F., and Curi N.: Hyper. Int.91 (1994) 751.
Souza M.N., Figueira M.A., and Da Costa M.S.: Nucl. Instr. and Methods in Phys. Res. B73 (1993) 95.
Salles E.O.T., De Souza Júnior P.A., and Garg V.K.:in Proc. First Simpósio Brasileiro de Automação Inteligente, UNESP, Rio Claro (SP, Brazil), September 1993, Sociedade Brasileira de Automática, São Paulo, 1993, p. 27.
Salles E.O.T., DeSouza P.A. Jr., and Garg V.K.: Nucl. Instr. and Methods in Phys. Res. B94 (1994) 499.
De Souza Júnior P.A., Salles E.O.T., and Garg V.K.:in Proc. 38th Midwest Symposium on Circuits and Systems, Rio de Janeiro (Brazil), August 18–21, 558 (1995).
Salles E.O.T., DeSouza P.A. Jr., and Garg V.K.: J. Radioanal. Nucl. Chem.190 (1995) 439.
Simpson P.K., ed.: Neural Networks — Theory, technology, and applications, IEEE Press, New York (USA), 1996.
Simpson P.K., ed.: Neural Networks Applications, IEEE Press, New York, USA (1966).
Taylor J.G. and Mannion C.L.T., eds.: New Developments in Neural Compating, Institute of Physics (U.K.), 1989, 264 pp.
Beale R. and Jackson T.: Neural Computing — An Introduction, Institute of Physics (U.K.), 1990.
Wassermann P.D.: Neural Computing Theory and Process, Van Nostrand Reinhold, New York (USA), 1989.
Fausett L.V.: Fundamentals of Neural Networks, Prentice Hall, Englewood Cliffs (New Jersey), 1994, 461 pp.
Aubin J.-P.: Neural Networks and Qualitative Physics — A Viability Approach, Cambridge University Press, 1994.
Sánches-Sinencio E. and Lau C.G.Y., eds.: Artificial Neural Networks — Paradigms, applications, and hardware implementation, IEEE Press, New York (USA), 1992.
Hecht-Nielsen R.: Applied Optics26 (1987) 4979.
Kohonen T.: IEEE Computer Mag. (1988), March, p. 11.
Kohonen T.: Self-organization and Assiciative Memory (3rd. ed.), Springer Verlag, Berlin, 1988.
Yasuo Matsuyama: IEEE Trans. Neural Networks 7 (1996) 652.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Júnior, P.A.D.S., Garg, V.K. Artificial neural networks in Mössbauer material science. Czech J Phys 47, 513–516 (1997). https://doi.org/10.1023/A:1021299104733
Received:
Issue Date:
DOI: https://doi.org/10.1023/A:1021299104733