Missing Data Imputation Through SGTM Neural-Like Structure for Environmental Monitoring Tasks

  • Oleksandra MishchukEmail author
  • Roman Tkachenko
  • Ivan Izonin
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 938)


The article describes a new missing data imputation method. It is based on the use of a high-speed neural-like structure of the Successive Geometric Transformations Model. The importance of the research is based on the analysis of disadvantages of the known methods for missing data processing. Various simple and complex algorithms are analyzed, among which are the arithmetic mean algorithm, regression modeling, etc. It is shown that the above-mentioned imputation methods in data monitoring of air pollution do not allow to obtain reliable results due to the low prediction accuracy. An effective method for processing data imputation through SGTM neural-like structure is proposed. An example of filling data by forecasting CO, NO and NO2 missed parameters in data monitoring of air pollution is given. A comparison of the proposed method with the arithmetic mean algorithm is carried out. Accuracies of the data imputation by developed method and by arithmetic mean algorithm are based on calculated evaluation criteria: Root mean squared errors. Experimentally established that the data imputation method through SGTM neural-like structure has a three times higher accuracy of the data imputation than the arithmetic mean algorithm. The proposed approach can be used in various areas such as medicine, materials science, economics, science services, etc.


Imputation methods Missing data Neural-like structure Environmental monitoring Successive Geometric Transformations Model 


  1. 1.
    Brauer, M., et al.: Exposure assessment for estimation of the global burden of disease attributable to outdoor air pollution. Environ. Sci. Technol. 42(2), 652–660 (2012). Scholar
  2. 2.
    Shakovska, N., Shamuratov, O.: The structure of information systems for environmental monitoring. In: XIth International Scientific and Technical Conference “Computer Science and Information Technologies”, Lviv, Ukraine, 6–10 September, pp. 102–107 (2016)Google Scholar
  3. 3.
    Zagnieva, I., Timonina, E.: Comparison of efficiency of missing data imputation algorithms, depending on the analysis method used. Public Opin. Monit. 1(119), 41–55 (2014). (in Russian)Google Scholar
  4. 4.
    Skrynyk, O.: Recovery missing data in time series of meteorological parameters. Sci. Work. Ukr. Res. Hydro Meteorol. Inst. 260, 46–53 (2011). (in Ukrainian)Google Scholar
  5. 5.
    Zloba, E., Yatskiv, I.: Statistical methods for recovering missing data. Comput. Model. New Technol. 6(1), 51–61 (2002). (in Ukrainian)Google Scholar
  6. 6.
    Baraldi, A., Enders, C.: An introduction to modern missing data analyses. J. Sch. Psychol. 48(1), 5–37 (2010). Scholar
  7. 7.
    Andridge, R., Little, R.: A review of hot deck imputation for survey non-response. Int. Stat. Rev. 78(1), 40–64 (2010)CrossRefGoogle Scholar
  8. 8.
    Engelberg, S.: Digital Signal Processing: An Experimental Approach, chap. 7, p. 56. Springer, New York (2008)Google Scholar
  9. 9.
    Snytiuk, V.: Evolutionary method of filling missing data. In: Collection of works VI MK “Intelligent Analysis of Information”, Kyiv, pp. 262–271 (2006). (in Russian)Google Scholar
  10. 10.
    Kuznietsova, N.: Identification and processing of uncertainties in the form of incomplete data by methods of intellectual analysis. Syst. Res. Inf. Technol. 2, 104–115 (2016). (in Ukrainian)Google Scholar
  11. 11.
    Kaminskyi, R., Kunanets, N., et al.: Recovery gaps in experimental data. In: Proceedings of the 2nd International Conference on Computational Linguistics and Intelligent Systems, Volume I: Main Conference Lviv, Ukraine, 25–27 June, pp. 110–118. (2018)Google Scholar
  12. 12.
    Bodyanskiy, Ye., Tyshchenko, O., Kopaliani, D.: An evolving connectionist system for data stream fuzzy clustering and its online learning. Neurocomputing 262, 41–56 (2017).
  13. 13.
    Babichev, S., Škvor, J., Fišer, J., Lytvynenko, V.: Technology of gene expression profiles filtering based on wavelet analysis. Int. J. Intell. Syst. Appl. (IJISA) 10(4), 1–7 (2018). Scholar
  14. 14.
    Lytvyn, V., Vysotska, V., Peleshchak, I., Rishnyak, I., Peleshchak, R.: Time dependence of the output signal morphology for nonlinear oscillator neuron based on Van der Pol model. Int. J. Intell. Syst. Appl. (IJISA) 10(4), 8–17 (2018). Scholar
  15. 15.
    Hu, Zh., Bodyanskiy, Ye., Tyshchenko, O.: A deep cascade neural network based on extended neo-fuzzy neurons and its adaptive learning algorithm. In: IEEE First Ukraine Conference on Electrical and Computer Engineering (UKRCON), Kyiv, Ukraine, 29 May–2 June, pp. 801–805 (2017)Google Scholar
  16. 16.
    Babichev, S., Korobchynskyi, M., Lahodynskyi, O., Basanets, V., Borynskyi, V.: Development of a technique for the reconstruction and validation of gene network models based on gene expression profiles. East.-Eur. J. Enterp. Technol. 114(91), 19–32 (2018). Scholar
  17. 17.
    Hu, Zh., Bodyanskiy, Ye., Tyshchenko, O.: A cascade deep neuro-fuzzy system for high-dimensional online possibilistic fuzzy clustering. In: XIth International Scientific and Technical Conference “Computer Science and Information Technologies” (CSIT 2016), Lviv, Ukraine, 6–10 September, pp. 119–122 (2016)Google Scholar
  18. 18.
    Hu, Zh., Bodyanskiy, Ye., Tyshchenko, O., Boiko, O.: A neuro-fuzzy Kohonen network for data stream possibilistic clustering and its online self learning procedure. Appl. Soft Comput. 68, 710–718 (2018).
  19. 19.
    Bodyanskiy, Y., Vynokurova, O., Savvo, V., Tverdokhlib, T., Mulesa, P.: Hybrid clustering-classification neural network in the medical diagnostics of the reactive arthritis. Int. J. Intell. Syst. Appl. (IJISA) 8(8), 1–9 (2016). Scholar
  20. 20.
    Tkachenko, R., Yurchak, I., Polishchuk, U.: Neurolike networks on the basis of geometrical transformation machine. In: 2008 International Conference on Perspective Technologies and Methods in MEMS Design, Polyana, 21–24 May, pp. 77–80 (2008)Google Scholar
  21. 21.
    Tkachenko, R., Izonin, I.: Model and principles for the implementation of neural-like structures based on geometric data transformations. In: Hu, Zh., Petoukhov, S., Dychka, I., He, M. (eds.) Advances in Computer Science for Engineering and Education. Advances in Intelligent Systems and Computing, vol. 754, pp. 578–587. Springer, Cham, (2018)Google Scholar
  22. 22.
    Teslyuk, V., Beregovskyi, V., Denysyuk, P., Teslyuk, T., Lozynskyi, A.: Development and implementation of the technical accident prevention subsystem for the smart home system. Int. J. Intell. Syst. Appl. (IJISA) 10(1), 1–8 (2018). Scholar
  23. 23.
    De Vito, S., Piga, M., Martinotto, L., Di Francia, G.: CO, NO2 and NOx urban pollution monitoring with on-field calibrated electronic nose by automatic Bayesian regularization. Sens. Actuators B: Chem. 143(1), 182–191 (2009)CrossRefGoogle Scholar
  24. 24.
    Kaczor, S., Kryvinska, N.: It is all about services - fundamentals, drivers, and business models: the society of service science. J. Serv. Sci. Res. 5(2), 125–154 (2013)CrossRefGoogle Scholar
  25. 25.
    Rzheuskiy, A., Veretennikova, N., Kunanets, N., Kut, V.: The information support of virtual research teams by means of cloud managers. Int. J. Intell. Syst. Appl. (IJISA) 10(2), 37–46 (2018). Scholar
  26. 26.
    Dronyuk, I., Fedevych, O., Lipinski, P.: Ateb-prediction simulation of traffic using OMNeT++ modeling tools. In: 2016 XIth International Scientific and Technical Conference Computer Sciences and Information Technologies (CSIT), Lviv, pp. 96–98 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Lviv Polytechnic National UniversityLvivUkraine

Personalised recommendations