Using Fuzzy Multilayer Perceptrons for the Classification of Time Series

  • Toni Pimentel
  • Fernando M. Ramos
  • Sandra Sandri
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8256)


In the last decades, rainforests all over the world have been subjected to high rates of land use change due to deforestation. Tracking and understanding the trends and patterns of these changes is crucial for the creation and implementation of effective policies for sustainable development and environment protection. Here we propose the use of Fuzzy Multilayer Perceptrons (Fuzzy MLP) for classification of land use and land cover patterns in the Brazilian Amazon, using time series of vegetation index, taken from NASA’s MODIS (Moderate Resolution Imaging Spectroradiometer) sensor. Results show that the combination of degree of ambiguity and fuzzy desired output, two of the Fuzzy MLP techniques implemented here, provides an overall accuracy ranging from 89% to 96%.


Membership Function Vegetation Index Fuzzy Inference System Input Pattern Moderate Resolution Image Spectroradiometer 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    de Freitas, R.M.: Laboratório virtual para visualizão e caracterização do uso e cobertura da terra utilizando imagens de sensoriamento remoto. PhD Thesis, INPE, Brazil (2012)Google Scholar
  2. 2.
    Gershenfeld, N.A., Weigend, A.S.: The future of time series: Learning and understanding, Working Papers, Santa Fe Inst (1993)Google Scholar
  3. 3.
    Haykin, S.S.: Neural Networks and Learning Machines. Prentice Hall (2009)Google Scholar
  4. 4.
    Jang, J.S.R.: ANFIS: Adaptive-network-based fuzzy inference system. IEEE Trans. on SMC 23(3), 665–685 (1993)Google Scholar
  5. 5.
    Keller, J.M., Hunt, D.J.: Incorporating fuzzy membership functions into the perceptron algorithm. IEEE Trans. on PAMI 6, 693–699 (1985)CrossRefGoogle Scholar
  6. 6.
    Mehrotra, K., Mohan, C.K., Ranka, S.: Elements of artificial neural networks. MIT Press (1996)Google Scholar
  7. 7.
    Moorthy, M., Cellier, F.E., LaFrance, J.T.: Predicting US food demand in the 20th century: A new look at system dynamics. In: Proc. SPIE, vol. 3369, p. 343 (1998)Google Scholar
  8. 8.
    Pal, S.K., Mitra, S.: Multilayer perceptron, fuzzy sets, and classification. IEEE Trans. on Neural Networks 3(5), 683–697 (1992)CrossRefGoogle Scholar
  9. 9.
    de Paula Canuto, A.M.: Combining neural networks and fuzzy logic for applications in character recognition. PhD Thesis Electronic Engineering, Un. of Kent at Canterbury (2001)Google Scholar
  10. 10.
    Pimentel, T., Ramos, F., Sandri, S.: Uso de Perceptrons Multicamadas Difusos para a Classificação de Padrões em Séries Temporais (submitted, 2013) (in Portuguese)Google Scholar
  11. 11.
    Popoola, A.O.: Fuzzy-Wavelet Method for Time Series Analysis. PhD Thesis, University of Surrey, UK (2007)Google Scholar
  12. 12.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Cognitive Modeling 1, 213 (2002)Google Scholar
  13. 13.
    Stoeva, S., Nikov, A.: A fuzzy backpropagation algorithm. Fuzzy Sets and Systems 112(1), 27–39 (2000)MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Takagi, T., Sugeno, M.: Fuzzy identification of system and its applications to modeling and control. IEEE Trans. SMC 1(5) (1985)Google Scholar
  15. 15.
    Wang, L.X., Mendel, J.M.: Generating fuzzy rules by learning from examples. IEEE Trans. on SMC 22(6), 1414–1427 (1992)MathSciNetGoogle Scholar
  16. 16.
    Ying, H.: General SISO Takagi-Sugeno fuzzy systems with linear rule consequent are universal approximators. IEEE Trans. on Fuzzy Systems 6(4), 582–587 (1998)CrossRefGoogle Scholar
  17. 17.
    Zadeh, L.A.: Fuzzy sets. Information and Control 8(3), 338–353 (1965)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Toni Pimentel
    • 1
  • Fernando M. Ramos
    • 1
  • Sandra Sandri
    • 1
  1. 1.Instituto Nacional de Pesquisas EspaciaisSão José dos CamposBrazil

Personalised recommendations