Advertisement

Application of Artificial Neural Networks for Modelling of Nicolsky-Eisenman Equation and Determination of Ion Activities in Mixtures

  • Józef Wiora
  • Dariusz Grabowski
  • Alicja Wiora
  • Andrzej Kozyra
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 322)

Abstract

The paper deals with the problem of ion activity determination for a mixture by means of ion-selective electrodes. Mathematical model of the analysed phenomenon is described by the Nicolsky-Eisenman equation, which relates activities of ions and ion-selective electrode potentials. The equation is strongly nonlinear and, especially in the case of multi-compound assays, the calculation of ion activities becomes a complex task. Application of multilayer perceptron artificial neural networks, which are known as universal approximators, can help to solve this problem. A new proposition of such network has been presented in the paper. The main difference in comparison with the previously proposed networks consists in the input set, which includes not only electrode potentials but also electrode parameters. The good network performance obtained during training has been confirmed by additional tests using measurement results and finally compared with the original as well as the simplified analytical model.

Keywords

Artificial neural network Potentiometry Ion-selective electrode 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Baret, M., Massart, D.L., Fabry, P., Conesa, F., Eichner, C., Menardo, C.: Application of neural network calibrations to an halide ISE array. Talanta 51, 863–877 (2000)CrossRefGoogle Scholar
  2. 2.
    Mimendia, A., Legin, A., Merkoçi, A., del Valle, M.: Use of sequential injection analysis to construct a potentiometric electronic tongue: Application to the multidetermination of heavy metals. Sensors and Actuators B: Chemical 146, 420–426 (2010)CrossRefGoogle Scholar
  3. 3.
    Gutiérrez, M., Alegret, S., del Valle, M.: Bioelectronic tongue for the simultaneous determination of urea, creatinine and alkaline ions in clinical samples. Biosensors and Bioelectronics 23, 795–802 (2008)CrossRefGoogle Scholar
  4. 4.
    Midgley, D., Torrance, K.: Potentiometric Water Analysis, 2nd edn. John Wiley & Sons, Inc., Chichester (1991)Google Scholar
  5. 5.
    Kane, P., Diamond, D.: Determination of ion-selective electrode characteristics by non-linear curve fitting. Talanta 44(4), 1847–1858 (1997)CrossRefGoogle Scholar
  6. 6.
    Amman, D.: Ion-Selective Microelectrodes. Springer, Heidelberg (1986)CrossRefGoogle Scholar
  7. 7.
    IUPAC: Potentiometric selectivity coefficients of ion-selective electrodes. Part I. Inorganic cations (technical report). Pure Appl. Chem. 72(10), 1851–2082 (2000)Google Scholar
  8. 8.
    Simon, W., Ammann, D., Oehme, M., Morf, W.E.: Calcium-selective electrodes. Annals of the New York Academy of Sciences 307(1), 52–70 (1978)CrossRefGoogle Scholar
  9. 9.
    Martnez-Barrachina, S., Alonso, J., Matia, L., Prats, R., del Valle, M.: Determination of trace levels of anionic surfactants in river water and wastewater by a flow injection analysis system with on-line preconcentration and potentiometric detection. Analytical Chemistry 71(17), 3684–3691 (1999)CrossRefGoogle Scholar
  10. 10.
    Inczédy, J., Lengyel, T., Ure, A.M.: The Orange Book: Compendium of Analytical Nomenclature. Definitive rules 1997, 3rd edn. IUPAC. Blackwell Science Ltd., Oxford (1998)Google Scholar
  11. 11.
    Kozyra, A., Wiora, J., Wiora, A.: Calibration of potentiometric sensor arrays with a reduced number of standards. Talanta 98, 28–33 (2012)CrossRefGoogle Scholar
  12. 12.
    Wiora, J., Wiora, A.: A system allowing for the automatic determination of the characteristic shapes of ion-selective electrodes. In: Pisarkiewicz, T. (ed.) Optoelectronic and Electronic Sensors VI. Proceedings of SPIE, vol. 6348 (2006)Google Scholar
  13. 13.
    Pitzer, K.S.: Activity Coefficients in Electrolyte Solution, 2nd edn. CRC Press, Boca Raton (1991)Google Scholar
  14. 14.
    Bastkowski, F., et al.: Pitzer ion activities in mixed electrolytes for calibration of ion-selective electrodes used in clinical chemistry. Accred. Qual. Assur. 18, 469–479 (2013)CrossRefGoogle Scholar
  15. 15.
    Wiora, A., Wiora, J., Kozyra, A.: Dynamic models of ion-selective electrodes and their interface electronics. Metrology and Measurement Systems 13(4), 421–432 (2006)Google Scholar
  16. 16.
    Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2(5), 359–366 (1989)CrossRefGoogle Scholar
  17. 17.
    Malinowski, A., Cholewo, T.J., Zurada, J.M., Aronhime, P.B.: Inverse mapping with neural network for control of nonlinear systems, vol. 3, pp. 453–456 (1996)Google Scholar
  18. 18.
    Kim, T., Adali, T.: Approximation by fully complex multilayer perceptrons. Neural Computation 15(7), 1641–1666 (2003)CrossRefzbMATHGoogle Scholar
  19. 19.
    Pei, J.S., Wright, J., Smyth, A.: Mapping polynomial fitting into feedforward neural networks for modeling nonlinear dynamic systems and beyond. Computer Methods in Applied Mechanics and Engineering 194(42-44), 4481–4505 (2005)CrossRefzbMATHMathSciNetGoogle Scholar
  20. 20.
    Grabowski, D., Walczak, J.: Generalized spectrum analysis by means of neural networks. In: Rutkowski, L., Kacprzyk, J. (eds.) Neural Networks and Soft Computing. Advances in Soft Computing, pp. 704–709 (2003)Google Scholar
  21. 21.
    Oh, S.K., Pedrycz, W.: Self-organizing polynomial neural networks based on polynomial and fuzzy polynomial neurons: Analysis and design. Fuzzy Sets and Systems 142(2), 163–198 (2004)CrossRefzbMATHMathSciNetGoogle Scholar
  22. 22.
    Ilin, R., Kozma, R., Werbos, P.: Beyond feedforward models trained by backpropagation: A practical training tool for a more efficient universal approximator. IEEE Transactions on Neural Networks 19(6), 929–937 (2008)CrossRefGoogle Scholar
  23. 23.
    Cimino, M., Pedrycz, W., Lazzerini, B., Marcelloni, F.: Using multilayer perceptrons as receptive fields in the design of neural networks. Neurocomputing 72(10-12), 2536–2548 (2009)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Józef Wiora
    • 1
  • Dariusz Grabowski
    • 2
  • Alicja Wiora
    • 1
  • Andrzej Kozyra
    • 1
  1. 1.Institute of Automatic ControlSilesian University of TechnologyGliwicePoland
  2. 2.Institute of Electrical Engineering and Computer ScienceSilesian University of TechnologyGliwicePoland

Personalised recommendations