IMPLEMENTATION OF DIGITAL FILTERS USING NEURAL NETWORKS WHEN THE OBJECT MOVEMENT DYNAMICS ARE NOT KNOWN

Zinovii Liubun, V. Nesterenko, V. Mandziy, O. Karpin

Abstract


Considered: Neural network-based algorithms to obtain an optimal digital filter. Recurrent neural networks can be used to implement an adaptive digital filter considering the characteristics of both interference and useful signal. The developed program trains recurrent neural networks and as a result obtains the coefficients of recursive digital filters. The efficiency of the proposed algorithm is confirmed with numerical experiments results.

Keywords: digital filter, recursive filters, recurrent neural networks


Full Text:

PDF

References


  1. Z. Liubun, V. Mandziy, O. Karpin, V. Rabyk, "Neural-network-based Gesture Detection for Capacitive Sensing," 2022 IEEE 16th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET), 2022, pp. 362-365, doi: 10.1109/TCSET55632.2022.9767083.
  2. Grewal M.S., Andrews A.P. Kalman Filtering: theory and practice. Prentice-Hall, Englewood Cliffs (1993)
  3. S. Haykin. Adaptive Filter Theory, 5th Edition, Prentice Hall, 2013.
  4. S. Haykin. Kalman Filtering and Neural Networks. First published:1 October 2001.Print ISBN:9780471369981 Online ISBN:9780471221548 DOI:10.1002/0471221546
  5. Recurrent Neural Filters: Learning Independent Bayesian Filtering Steps for Time Series Prediction Bryan Lim, Stefan Zohren and Stephen Roberts Oxford-Man Institute of Quantitative Finance Department of Engineering Science University of Oxford Oxford, UK {blim,zohren,sjrob}@robots.ox.ac.u.
  6. Oxford-Man. Recurrent Neural Filters: Learning Independent Bayesian Filtering Steps for Time Series Prediction. Retrieved from https://www.oxford-man.ox.ac.uk/wp-content/uploads/2020/03/Recurrent-Neural-Filters-Learning-Independent-Bayesian-Filtering-Steps-for-Time-Series-Prediction.pdf
  7. IOPSCIENCE. Recurrent neural networks as approximators of non-linear filters operators. Retrieved from https://iopscience.iop.org/article/10.1088/1742-6596/1141/1/012115/pdf
  8. STOWERS INSTITUTE RESEARCH WEBSITES. A fast noise filtering algorithm for time series prediction using recurrent neural networks. Retrieved from https://research.stowers.org/bru/RNN_Filter2_V3.pdf
  9. S. Haykin. Kalman filtering and neural networks, John Wiley, 2001.
  10. Parlos A. G., Menon S. K. and Atiya A. F. (2001). An algorithmic approach to adaptive state filtering using recurrent neural networks. “IEEE Transactions on Neural Networks”, 12-6:1411--1432.
  11. AN64846, Getting Started with CapSense®, Document No. 001-64846 Rev. *T, Retrieved from https://www.mouser.com/pdfdocs/AN64846.pdf




DOI: http://dx.doi.org/10.30970/eli.19.4

Refbacks

  • There are currently no refbacks.