HISTOGRAM FILTER BASED ON FUZZY DATA ACCESSIBILITY TO GROUP INTERVAL

UDC 519.2

  • Ausiannikov Andrei Vitalievich − PhD (Engineering), Associate Professor, Assistant Professor, the Department of Information Technology. Belarusian State University (4, Nezavisimosti Ave., 220030, Minsk, Republic of Belarus). E-mail: andovs@mail.ru

  • Barashko Oleg Georgievich − PhD (Engineering), Associate Professor, Assistant Professor, the Department of Automation of Production Processes and Electrical Engineering. Belarusian State Technological University (13a, Sverdlova str., 220006, Minsk, Republic of Belarus). E-mail: barashko@belstu.by

DOI: https://doi.org/10.52065/2520-6141-2022-254-1-58-63

Key words: probability density, fuzzy belonging, histogram estimate, histogram filter.

For citation: Ausiannikov A. V., Barashko O. G. Histogram filter based on fuzzy data accessibility to group interval. Proceedings of BSTU, issue 3, Physics and Mathematics. Informatics, 2021, no. 1 (254), pp. 58–63 (In Russian).DOI: https://doi.org/10.52065/2520-6141-2022-254-1-58-63.

Abstract

The paper proposes a histogram estimate of the probability density based on fuzzy data belonging to the grouping interval. A methodology for constructing a histogram estimate using a histogram smoothing filter is presented. The technique of constructing such a filter is described. The main filter parameter is established - the coefficient of the statistical relationship between the amount of data falling into the grouping interval for a single inclusion function and when approaching using the membership function. The use of an iterative procedure for a histogram filter allows for a greater “smoothness” of the histogram. The simulation results show the effectiveness of using a histogram filter for different data volumes. At the same time, the choice of the number of grouping intervals for the “correct” recognition of probability density becomes not critical. The histogram filter is a simple tool that can easily be built into any algorithm for constructing histogram estimates.

Download

References

  1. Orlov Y. N. Optimal histogram partitioning for estimating the sample density of the distribution function of an unsteady time series. Preprinty IPM im. M. V. Keldysha [Preprints of the Institute of Applied Mathematics M. V. Keldysh], 2013, no. 14, рр. 26–52. Available at: http://library.keldysh.ru /preprint.asp?id=2013-14. (accessed 10.02.2021) (In Russian).
  2. Chong G., Yongho J., Yi L. Nonparametric density estimation in high-dimensions. Computer Science, 2013, no. 23, рр. 1131–1153.
  3. Orlov A. I. The new paradigm of applied statistics. Zavodskaya laboratoriya. Diagnostika materialov [Industrial Laboratory. Diagnostics of Materials], 2012, vol. 78, no. 11, pp. 87–93 (In Russian).
  4. Devroye L., Gyorfi L. Nonparametric Density Estimation: The L1 View. New York, John Wiley Sons Publ., 1985. 356 p.
  5. Gonzalez R. Digital Image Processing. Pearson Hall Publ., 2008. 976 p.
  6. Solomon C. J., Breckon T. P. Fundamentals of Digital Image Processing: A Practical Approach with Examples in Matlab. Wiley-Blackwell Publ., 2010. 344 p. DOI: 10.1002/9780470689776.
  7. Gonzalez R. Digital image processing. New York, NY, Pearson Publ., 2018. 512 p.
  8. Ovsyannikov A. V. The use of stochastic shaping filters. Izdatel'skiy Dom LAP LAMBERT Academic Publishing, OmniScriptum GmbH & Co. KG Publ., Saarbrücken, Germany, 2017. 64 p. (In Russian).
  9. Bernd J. Digital Image Processing. Springer Publ., Berlin, Heidelberg, New York, 2005, 658 p.
  10. Chakravorty P. What is a Signal [Lecture Notes]. IEEE Signal Processing Magazine, 2018, no. 35 (5), pp. 175–177. DOI: 10.1109/MSP.2018.2832195.
15.10.2021