Efficient Error Based Metrics for Fuzzy-Neural Network Performance Evaluation

Part of the Studies in Computational Intelligence book series (SCI, volume 728)


In this paper the effectiveness of different error metrics for assessment of the capabilities of an advanced fuzzy-neural architecture are studied. The proposed structure combines the potentials of the Intuitionistic Fuzzy Logic with the simplicity of the Neo-Fuzzy Neuron theory for implementation of robust modeling mechanisms, able to capture uncertain variations in the data space. A major concern when evaluating the performance of such kind of models is the selection of appropriate error metrics in order to assess their potential to capture a wide range of system behaviours. Therefore, different error metrics to evaluate the functional properties of a proposed Intuitionistic Neo-fuzzy network are studied and a comparative analysis in modeling of chaotic time series is made.


  1. 1.
    Abiyev, R.H., Kaynak, O.: Type 2 fuzzy neural structure for identification and control of time-varying plants. IEEE Trans. Ind. Electron. 57(12) (2010)Google Scholar
  2. 2.
    Aliev, R.A., Guirimov, B.G.: Type-2 Fuzzy Neural Networks and Their Applications. Springer International Publishing (2014)Google Scholar
  3. 3.
    Atanassov, K.: Intuitionistic Fuzzy Sets. Springr, Hielderberg (1999)CrossRefzbMATHGoogle Scholar
  4. 4.
    Baceiar, A., De Souza Filho, E., Neves, F., Landim, R.: On-line linear system parameter estimation using the neo-fuzzy-neuron algorithm. In: Proceedings of the 2nd IEEE International Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, pp. 115–118 (2003)Google Scholar
  5. 5.
    Bodyanskiy, Y., Kokshenevane, I., Kolodyazhniy, V.: An adaptive learning algorithm for a neo-fuzzy neuron. In: Proceedings of the 3rd Conference of the European Society for Fuzzy Logic and Technology, pp. 375–379 (2005)Google Scholar
  6. 6.
    Bodyanskiy, Y., Viktorov, Y.: The cascade neo-fuzzy architecture and its online learning algorithm. Int. Book Series Inf. Sci. Comput. 17(1), 110–116 (2010)Google Scholar
  7. 7.
    Bodyanskiy, Y., Pliss, I., Vynokurova, O.: Flexible neo-fuzzy neuron and neuro-fuzzy network for monitoring time series properties. Inf. Technol. Manag. Sci. 16, 47–52 (2013)Google Scholar
  8. 8.
    Bodyanskiy, Y., Tyshchenko, O., Kopaliani, D.: An extended neo-fuzzy neuron and its adaptive learning algorithm. Int. J. Intell. Syst. Appl. 2, 21–26 (2015)Google Scholar
  9. 9.
    Castillo, O., Melin, P., Tsvetkov, R., Atanassov, K.T.: Short remark on fuzzy sets, interval type-2 fuzzy sets, general type-2 fuzzy sets and intuitionistic fuzzy sets. In: Intelligent Systems’ 2014, Advances in Intelligent Systems and Computing, vol. 322, pp. 183–190 (2015)Google Scholar
  10. 10.
    Chai, T., Draxler, R.R.: Root mean square error (RMSE) or mean absolute error (MAE)?–Arguments against avoiding RMSE in the literature. Geosci. Model Dev. 7, 1247–1250 (2014)CrossRefGoogle Scholar
  11. 11.
    Collopy, F., Armstrong, J.S.: Another Error Measure for Selection of the Best Forecasting Method: The Unbiased Absolute Percentage Error (2000)Google Scholar
  12. 12.
    Jang, J.-S.R.: ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans. Syst. Man Cybern. 23(5), 665–685 (1993)CrossRefGoogle Scholar
  13. 13.
    Juang, C.-F., Jang, W.-S.: A type-2 neural fuzzy system learned through type-1 fuzzy rules andits FPGA-based hardware implementation. Appl. Soft Comput. 18, 302–313 (2014)CrossRefGoogle Scholar
  14. 14.
    Kasabov, N.K., Song, Q.: DENFIS: dynamic evolving neural-fuzzy inference system and its application for time-series prediction. IEEE Trans. Fuzzy Syst. 10(2), (2002)Google Scholar
  15. 15.
    Kim, H.D.: Optimal learning of neo-fuzzy structure using bacteria foraging optimization. In: Proceedings of the ICCA (2005)Google Scholar
  16. 16.
    Landim, R., Rodriguez, B., Silva, S., Caminhas, W.: A neo-fuzzy-neuron with real time training applied to flux observer for an induction motor. In: Proceedings of 5th IEEE Brazilian Symposium of Neural Networks, pp. 67–72 (1998)Google Scholar
  17. 17.
    Moreno, J.J.M., Pol, A.P., Abad, A.S., Blasco, B.C.: Using the RMAPE index as a resistant measure of forecast accuracy. Psicothema 25(4), 500–506 (2013)Google Scholar
  18. 18.
    Pandit, M., Srivastava, L., Singh, V.: On-line voltage security assessment using modified neo fuzzy neuron based classifier. IEEE Int. Conf. Ind. Technol. 899–904 (2006)Google Scholar
  19. 19.
    Shcherbakov, M., Brebels, A.: A survey of forecast error measures. World Appl. Sci. J. 24(4), 171–176 (2013)Google Scholar
  20. 20.
    Silva, A.M., Caminhas, W., Lemos, A., Gomide, F.: A fast learning algorithm for evolving neo-fuzzy neuron. Appl. Soft Comput. 14, 194–209 (2014)CrossRefGoogle Scholar
  21. 21.
    Silva, A.M., Caminhas, W., Lemos, A., Gomide, F.: Evolving neo-fuzzy neural network with adaptive feature selection. In: Proceedings of 2013 BRICS IEEE Congress on Computational Intelligence, 11th Brazilian Congress on Computational Intelligence, pp. 341–349 (2014)Google Scholar
  22. 22.
    Soualhi, A., Clerc, G., Razik, H., Rivas, F.: Long-term prediction of bearing condition by the neo-fuzzy neuron. In: Proceedings of 9th International IEEE Symposium of Diagnostic of Electric Machines, Power Electronics and Drives, pp. 586–591 (2013)Google Scholar
  23. 23.
    Terziyska, M., Todorov, Y.: Modeling of chaotic time series by interval type-2 neo-fuzzy neural network. In: International Conference on Artificial Neural Networks (ICANN’ 2014). Springer Lecture Notes on Computer Science, vol. 8681, pp. 643–650. Hamburg, Germany (2014)Google Scholar
  24. 24.
    Tung, S.W., Quek, C., Guan, C.: T2FIS: an evolving type-2 neural fuzzy inference system. Inf. Sci. 220, 124–148 (2013)CrossRefGoogle Scholar
  25. 25.
    Uchino, E., Yamakawa, T.: High speed fuzzy learning machine with guarantee of global minimum and its applications to chaotic system identification and medical image processing. In: Proceedings of 7th International IEEE Conference on Tools with Artificial Intelligence, pp. 242–249 (1995)Google Scholar
  26. 26.
    Uchino, E., Yamakawa, T.: Neo-fuzzy-neuron based new approach to system modeling, with application to actual system. In: Proceedings of 6th International IEEE Conference on Tools with Artificial Intelligence, pp. 564–570 (1994)Google Scholar
  27. 27.
    Willmott, C., Matsuura, K.: Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim. Res. 30, 79–82 (2005)CrossRefGoogle Scholar
  28. 28.
    Zadeh, L.A.: The concept of a linguistic variable and its applications to approximate reasoning-1. Inf. Sci. 8, 199–249 (1975)CrossRefzbMATHMathSciNetGoogle Scholar
  29. 29.
    Zaychenko, Y., Gasanov, A.: Investigations of cascade neo-fuzzy neural networks in the problem of forecasting at the stock exchange. In: Proceedings of the IVth IEEE International Conference Problems of Cybernetics and Informatics (PCI’ 2012), pp. 227–229 (2012)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Department of Informatics and StatisticsUniversity of Food TechnologiesPlovdivBulgaria
  2. 2.Department of Chemical and Metallurgical EngineeringLaboratory of Automation and Process Control, Aalto UniversityEspooFinland

Personalised recommendations