(46-3) 18 * << * >> * Russian * English * Content * All Issues

A method for analyzing complex structured data with elements of machine learning
B.S. Mandrikova 1

1 Institute of Cosmophysical Research and Radio Wave Propagation,
Far Eastern Branch of the Russian Academy of Sciences, 684034, Kamchatskiy Kray, Paratunka, Russia, Mirnaya st, 7

 PDF, 1303 kB

DOI: 10.18287/2412-6179-CO-1088

Pages: 506-512.

Full text of article: Russian language.

Abstract:
A method for analyzing data of complex structure based on combining a wavelet transform and neural networks Autoencoder is proposed. The method allows you to research the data structure, detect abnormal changes of various shapes and durations, and suppress noise. The efficiency of the method is shown on the example of data from a network of neutron monitor stations. Neutron monitor data determine the intensity of secondary cosmic rays and are one of the key factors in space weather. The numerical implementation of the method allows it to be applied on-line, which is of interest in problems of analyzing environmental data and detecting catastrophic events.

Keywords:
data analysis, data of complex structure, wavelet transform, neural networks, neutron monitors.

Citation:
Mandrikova BS. A method for analyzing complex structured data with elements of machine learning. Computer Optics 2022; 46(3): 506-512. DOI: 10.18287/2412-6179-CO-1088.

Acknowledgements:
The work was funded under the government project AAAA-A21-121011290003-0 “Physical processes in the system of near space and geospheres under solar and lithospheric influences” IKIR FEB RAS.

References:
  1. Vorobiev AV, Vorobieva GR. Geographic information system for amplitude-frequency analysis of observation data of geomagnetic variations and space weather. Computer optics 2017; 41(6): 963-972. DOI: 10.18287/2412-6179-2017-41-6-963-972.
  2. Mandrikova OV, Zhizhikina EA. An automatic method for assessing the state of the geomagnetic field. Computer optics 2015; 39(3): 420-428. DOI: 10.18287/0134-2452-2015-39-3-420-428.
  3. Mandrikova OV, Stepanenko AA. An automated method for calculating the dst-index based on the wavelet model of the geomagnetic field variations field. Computer optics 2020; 44(5): 797-808. DOI: 10.18287/2412-6179-CO-709.
  4. Mandrikova OV, Fetisova NV, Polozov YA. Hybrid Model for Time Series of Complex Structure with ARIMA Components. Mathematics 2021; 9: 1122. DOI: 10.3390/math9101122.
  5. Abunin AA, Abunina MA, Belov AV, Eroshenko EA, Oleneva VA, Jahnke V. Forbush effects with sudden and gradual onset [In Russian]. Geomagn Aeron 2012; 52(3): 313-320.
  6. Kuznetsov VD. Space weather and risks of space activity [In Russian]. Space Engineering and technology 2014; 3(6): 3-13.
  7. Murzin BC. Astrophysics of cosmic rays: Textbook for universities [In Russian]. Moscow: “Logos” Publisher; 2007. ISBN: 978-5-98704-171-6.
  8. Real-time database of high-resolution neutron monitors. Source: <www.nmdb.eu>.
  9. Belov AV, Eroshenko EA, Yanke VG, Oleneva VA, Abunina MA, Abunin AA. Method of global survey for the world network of neutron monitors [In Russian]. Geomagnetism and Aeronomy 2018; 58(3): 374-389. DOI: 10.7868/S0016794018030082.
  10. Mavromichalaki H, Souvatzoglou G, Sarlanis C, et al. Using real time neutron monitor database to establish an alert signal. Proc 31st Int Cosmic Ray Conference (ICRC) 2009. Source: <https://galprop.stanford.edu/elibrary/icrc/2009/preliminary/pdf/icrc1381.pdf>.
  11. Veselovsky IS, Yakovchuk OS. On the forecast of solar proton events according to the data of ground-based neutron monitors [In Russian]. Astronomical Herald: Solar System Exploration 2011; 45(4): 365-375.
  12. Wawrzynczak A, Kopka P. Approximate Bayesian computation for estimating parameters of data-consistent forbush decrease model. Entropy 2018; 20: 622. DOI: 10.3390/e20080622.
  13. Chui CK. Introduction to wavelets [In Russian]. Moscow: "Mir" Publisher; 2001. ISBN: 5-03-003397-1.
  14. Astafieva NM. Wavelet analysis: basic theory and some applications. Physics–Uspekhi 1996; 39(11): 1085-1108. DOI: 10.1070/PU1996v039n11ABEH000177.
  15. Vizilter YuV, Gorbatsevich VS, Zheltov SYu. Structural and functional analysis and synthesis of deep convolutional neural networks. Computer optics 2019; 43(5): 886-900. DOI: 10.18287/2412-6179-2019-43-5-886-900.
  16. Soldatova OP, Lezin IA, Lezina IV, Kupriyanov AV, Kirsh DV. Application of fuzzy neural networks to determine the type of crystal lattices observed in nanoscale images. Computer optics 2015; 39(5): 787-794. DOI: 10.18287/0134-2452-2015-39-5-787-794.
  17. Rodin IA, Khonina SN, Serafimovich PG, Popov SB. Recognition of the types of wavefront aberrations corresponding to individual Zernike functions from the pattern of the point scattering function in the focal plane using neural networks. Computer optics 2020; 44(6): 923-930. DOI: 10.18287/2412-6179-CO-810.
  18. Goodfellow Y, Benjio I, Courville A. Deep learning. Adaptive computation and machine learning series. Cambridge, London: The MIT Press; 2016.
  19. Geppener VV, Mandrikova BS. An automated method for analyzing cosmic ray data and isolating sporadic effects [In Russian]. Computational Mathematics and Mathematical Physics 2021; 61(7): 1137-1148. DOI: 10.31857/S0044466921070061.
  20. Mandrikova O, Mandrikova B, Rodomanskay A. Method of constructing a nonlinear approximating scheme of a complex signal: Application pattern recognition. Mathematics 2021; 9(7): 737. DOI: 10.3390/math9070737.
  21. Geppener VV, Mandrikova B. Detecting and identifying anomalous effects in complex signals. Autom Remote Control 2021; 82(10), 1668-1678. DOI: 10.1134/S0005117921100052.
  22. Wald A. Statistical decision functions. London: Chapman & Hall; 1950.
  23. Bansal AK. Bayesian parametric inference. Oxford, UK: Alpha Science International Ltd; 2007.
  24. Abunina MA. Anisotropy of cosmic rays in various structures of the solar wind [In Russian]. The thesis for the Candidate’s degree in Technical Sciences. Moscow; 2016.
  25. Daubechies I. Ten lectures on wavelets [In Russian]. Moscow: "RKhD"Publisher; 2001.
  26. IZMIRAN catalog of Forbush effects and interplanetary disturbances [In Russian]. Source: <http://spaceweather.izmiran.ru/rus/fds2019.html>.
  27. Institute of Applied Geophysics [In Russian]. Source: <http://ipg.geospace.ru/>.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20