2D-Neo-Fuzzy Neuron and Its Adaptive Learning

Yevgeniy Bodyanskiy, Olena Vynokurova, Valentyna Volkova, Olena Boiko

Abstract


In the paper 2D-neo-fuzzy neuron is presented. It is a generalization of the traditional NFN for data in matrix form. 2D-NFN is based on the matrix adaptive bilinear model with an additional fuzzification layer. It reduces the number of adjustable synaptic weights in comparison with traditional systems. For its learning, optimized adaptive procedures with filtering and tracking properties are proposed. 2D-NFN can be effectively used for image processing, data reduction, and restoration of non-stationary signals, presented as 2D-sequences.

Keywords:
2D network; data mining; hybrid systems; neo-fuzzy neuron

Full Text:

 PDF

References


T. Yamakawa, E. Uchino, T. Miki and H. Kusanagi, “A neo-fuzzy neuron and its applications to system identification and prediction of the system behavior,” in Proc. 2nd Int. Conf. on Fuzzy Logic and Neural Networks “IIZUKA-92”, Iizuka, Japan, 1992, pp. 477–483.

E. Uchino and T. Yamakawa, “Neo-fuzzy-neuron based new approach to system modeling, with application to actual system,” in Proc. Sixth International Conference on Tools with Artificial Intelligence, New Orleans, LA, USA, 1994, pp. 564–570. https://doi.org/10.1109/TAI.1994.346442

E. Uchino and T. Yamakawa, “Soft computing based signal prediction, restoration and filtering,” in Intelligent Hybrid Systems: Fuzzy Logic, Neural Networks and Genetic Algorithms, Boston: Kluwer Academic Publisher, 1997, pp. 331–349. https://doi.org/10.1007/978-1-4615-6191-0_14

T. Miki and T. Yamakawa, “Analog implementation of neo-fuzzy neuron and its on-board learning,” in Computational Intelligence and Applications, Piraeus: WSES Press, 1999, pp. 144–149.

T. Yamakawa, E. Uchino and T. Samatsu, “Wavelet neural networks employing over-complete number of compactly supported non-orthogonal wavelets and their applications,” in Proc. of 1994 IEEE International Conference on Neural Networks, Orlando, FL, USA, 1994, pp. 1391–1396. https://doi.org/10.1109/ICNN.1994.374489

T. Yamakawa, “A novel nonlinear synapse neuron model guaranteeing a global minimum – wavelet neuron,” in Proc. 28th IEEE International Symposium on Multiple-Valued Logic, 1998, pp. 335–337. https://doi.org/10.1109/ISMVL.1998.679510

R. P. Landim, B. Rodrigues, S. R. Silva and W. M. Caminhas, “A neo-fuzzy-neuron with real time training applied to flux observer for an induction motor,” in Proc. IEEE 5th Brazilian Symposium on Neural Networks, Belo Horizonte, Brazil, 1998, pp. 67–72. https://doi.org/10.1109/SBRN.1998.730996

W. M. Caminhas and F. A. Gomide, “A fast learning algorithm for neofuzzy networks,” in Proc. Conf. Information Processing and Management of Uncertainty in Knowledge-Based Systems “IPMU’2000”, Madrid, Spain, 2000, pp. 1784–1790.

R. P. Landim, B. R. de Menezes, S. R. Silva and W. M. Caminhas, “On-line neo-fuzzy-neuron state observer,” in Proc. Sixth Brazilian Symposium on Neural Networks, vol.1, Rio de Janeiro, Brazil, 2000, pp. 196–201. https://doi.org/10.1109/SBRN.2000.889738

A. M. Silva, W. M. Caminhas, A. P. Lemos and F. Gomide, “Evolving neo-fuzzy neural network with adaptive feature selection,” in Proc. 11th Brazilian Congress on Computational Intelligence, BRICS 2013, Ipojuca, Brazil, 2013, pp. 341–349. https://doi.org/10.1109/BRICS-CCI-CBIC.2013.64

A. M. Silva, W. Caminhas, A. Lemos and F. Gomide, “A fast learning algorithm for evolving neo-fuzzy neuron,” in Applied Soft Computing, vol. 14, 2014, pp. 194–209. https://doi.org/10.1016/j.asoc.2013.03.022

Y. Bodyanskiy, V. Kolodyazhniy and A. Stephan, “An adaptive learning algorithm for a neuro-fuzzy network,” ed. by B. Reusch “Computational Intelligence: Theory and Applications,” Berlin-Heidelberg-New York, Springer, 2001, pp. 68–75. https://doi.org/10.1007/3-540-45493-4_11

Y. Bodyanskiy, I. Kokshenev and V. Kolodyazhniy, “An adaptive learning algorithm for a neo-fuzzy neuron,” in Proc. 3rd Int. Conf. of European Union Soc. For Fuzzy Logic and Technology (EUSFLAT 2003), Zittau, Germany, 2003, pp. 375–379.

P. Otto, Y. Bodyanskiy and V. Kolodyazhniy, “A new learning algorithm for a forecasting neuro-fuzzy network,” in Integrated Computer-Aided Engineering, vol. 10, no. 4, 2003, pp. 399–409. https://doi.org/10.3233/ica-2003-10409

Y. Bodyanskiy, V. Kolodyazhniy, I. Pliss and O. Vynokurova, “Learning wavelet neuron based on the RASP-function,” in Radioelectronics. Informatics. Control, vol. 68, no. 1, 2004, pp. 118–122.

V. Kolodyazhniy and Y. Bodyanskiy, “Fuzzy Kolmogorov’s network,” Lecture Notes in Computer Science, LNCS, vol. 3214, Heidelberg, Springer Verlag, 2004, pp. 764–771. https://doi.org/10.1007/978-3-540-30133-2_100

Y. Bodyanskiy, N. Lamonova, I. Pliss and O. Vynokurova, “An adaptive learning algorithm for a wavelet neural network,” in Expert Systems, vol. 22, no. 5, 2005, pp. 235–240. https://doi.org/10.1111/j.1468-0394.2005.00314.x

V. Kolodyazhniy, Y. Bodyanskiy, V. Poyedyntseva and A. Stephan, “Neuro-fuzzy Kolmogorov’s network with a modified perceptron learning rule for classification problems,” in Computational Intelligence: Theory and Applications, B. Reusch, Ed., Berlin-Heidelberg, Springer-Verlag, 2006, pp. 41–49. https://doi.org/10.1007/3-540-34783-6_6

Y. Bodyanskiy, O. Kharchenko and O. Vynokurova, “Hybrid cascade neural network based on wavelet-neuron,” in Int. J. Information Theories & Applications, vol. 18, no. 4, 2011, pp. 335–343.

Y. Bodyanskiy, O. Tyshchenko and W. Woicik, “Multivariate non-stationary time series predictor based on an adaptive neuro-fuzzy approach,” Elektronika, no. 8, 2013, pp. 10–13.

I. Pliss, Y. Bodyanskiy and O. Vynokurova, “Flexible neo-fuzzy neuron and its adaptive learning algorithms,” Proc. 20th East West Zittau Fuzzy Colloquium, Zittau-Görlitz, Germany, 2013, pp. 47–54.

Y. Bodyanskiy, I. Pliss and O. Vynokurova, “Flexible neo-fuzzy neuron and neuro-fuzzy network for monitoring time series properties,” Sci. J. of Riga Technical University: Information Technology and Management Science, vol. 16, no. 1, 2014, pp. 47–52. https://doi.org/10.2478/itms-2013-0007

Y. V. Bodyanskiy, O. K. Tyshchenko and D. S. Kopaliani, “An extended neo-fuzzy neuron and its adaptive learning algorithm,” in Int. J. Intelligent Systems and Applications, vol. 7, no. 2, 2015, pp. 21–26. https://doi.org/10.5815/ijisa.2015.02.03

Y. Bodyanskiy, O. Tyshchenko and D. Kopaliani, “A hybrid cascade neural network with an optimized pool in each cascade,” in Soft Computing, vol. 19, no. 12, 2015, pp. 3445–3454. https://doi.org/10.1007/s00500-014-1344-3

Y. Bodyanskiy, O. Vynokurova, G. Setlak and I. Pliss, “Hybrid neuro-neo-fuzzy system and its learning algorithm,” in Proc. X Int. Sci. Techn. Conf. Computer Science and Information Technologies “CSIT’2015”, Lviv, Ukraine, 2015, pp. 111–114. https://doi.org/10.1109/stc-csit.2015.7325445

Y. V. Bodyanskiy, O. K. Tyshchenko and D. S. Kopaliani, “Adaptive learning of an evolving cascade neo-fuzzy system in data stream mining tasks,” in Evolving Systems, vol. 7, no. 2, 2016, pp. 107–116. https://doi.org/10.1007/s12530-016-9149-5

Z. Hu, Y. V. Bodyanskiy, O. K. Tyshchenko and O. O. Boiko, “An evolving cascade system based on a set of neo-fuzzy nodes,” in Int. J. Intelligent Systems and Applications, vol. 8, no. 9, 2016, pp. 1–7. https://doi.org/10.5815/ijisa.2016.09.01

Z. Hu, Y. V. Bodyanskiy, O. K. Tyshchenko and O. O. Boiko, “Adaptive forecasting of non-stationary nonlinear time series based on the evolving weighted neuro-neo-fuzzy-ANARX-model,” in Int. J. Information Technology and Computer Science, vol. 8, no. 10, 2016, pp. 1–10. https://doi.org/10.5815/ijitcs.2016.10.01

Z. Hu, Y. V. Bodyanskiy and O. K. Tyshchenko, “A deep cascade neural network based on extended neo-fuzzy neurons and its adaptive learning algorithm,” in Proc. IEEE First Ukraine Conf. on Electrical and Computer Engineering “UKRCON’2017”, Kyiv, Ukraine, 2017, pp. 801–805. https://doi.org/10.1109/ukrcon.2017.8100357

Z. Hu, Y. V. Bodyanskiy, N. Ye. Kulishova and O. K. Tyshchenko, “A multidimensional extended neo-fuzzy neuron for facial expression recognition,” in Int. J. Intelligent Systems and Applications, vol. 9, no. 9, 2017, pp. 29–36. https://doi.org/10.5815/ijisa.2017.09.04

Z. Hu, Y. V. Bodyanskiy and O. K. Tyshchenko, “A hybrid growing ENFN-based neuro-fuzzy system and its rapid deep learning,” in Proc. XIIth Int. Sci. Techn. Conf. “CSIT’2017”, Lviv, Ukraine, 2017, pp. 514–519. https://doi.org/10.1109/stc-csit.2017.8098840

Y. Bodyanskiy, I. Pliss, O. Vynokurova, D. Peleshko and Y. Rashkevych, “Neo-fuzzy encoder and its adaptive learning for big data processing,” in Information Technology and Management Science, vol. 20, no. 1, 2018, pp. 6–11. https://doi.org/10.1515/itms-2017-0001

D. Zurita, M. Delgado, J. A. Carino, J. A. Ortega and G. Clerk, “Industrial time series modelling by means of the neo-fuzzy neuron,” in IEEE Access, vol. 4, 2016, pp. 6151–6160. https://doi.org/10.1109/access.2016.2611649

Y. V. Bodyanskiy and I. P. Pliss, “About matrix object control task in conditions of uncertainty,” in Avtomatika i Telemekhanika, no. 2, 1990, pp. 175–178. (in Russian)

Y. Bodyanskiy, I. Pliss and V. Timofeev, “Discrete adaptive identification and extrapolation of two-dimensional fields,” in Pattern Recognition and Image Analysis, vol. 5, no. 3, 1995, pp. 410–416.

Y. V. Bodyanskiy and M. D. Boryachok, Optimal control of stochastic objects under conditions on uncertainty, Kyiv, Ukraine: ISDO, 1993. (in Ukrainian)

Machine Learning Repository. [Online]. Available: http://archive.ics.uci.edu/ml/datasets/Optical+Recognition+of+Handwritten+Digits




DOI: 10.7250/itms-2018-0003

Refbacks

  • There are currently no refbacks.


Copyright (c) 2018 Yevgeniy Bodyanskiy, Olena Vynokurova, Valentyna Volkova, Olena Boiko

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.