Advertisement

Study of Algorithms Classifiers for an Offline BMI Based on Motor Imagery of Pedaling

  • Mario Ortiz
  • Marisol Rodríguez-Ugarte
  • Eduardo Iáñez
  • José M. Azorín
Conference paper
Part of the Biosystems & Biorobotics book series (BIOSYSROB, volume 22)

Abstract

The paper compares different signal processing algorithms and classifiers to evaluate the accuracy of a BMI based on lower-limb motor imagery. The methods were based on the analysis of the peaks of the different processing epochs for the alpha, beta and gamma EEG bands through the Marginal Hilbert Spectrum, Power Spectral Density and Fourier harmonic components. Data were classified and analyzed by three classifiers: Support Vector Machine, Self-Organizing Maps and Linear Discriminator analysis. Results show accuracy is dependent on the subject, but there is not dependency between the subjects and the methods, and classifiers. Best accuracy results were achieved by using the value of the peak of the Hilbert Marginal Spectrum, obtaining the analytical signal with the Stockwell transform. Regarding the classifiers SOM presented lower accuracy values than SVM and LDA.

References

  1. 1.
    Gharabaghi, A.: What turns assistive into restorative brain-machine interfaces? Front. Neurosci. 10, 456 (2016)Google Scholar
  2. 2.
    Pfurtscheller, G., Brunner, C., Schlögl, A., Lopes da Silva, F.H.: Mu rhythm (de)synchronization and EEG single-trial classification of different motor imagery tasks. Neuroimage 31(1), 153–159 (2006)CrossRefGoogle Scholar
  3. 3.
    Rao, R.P.N.: Brain-Computer Interfacing: An Introduction. Cambridge University Press, Cambridge (2013)CrossRefGoogle Scholar
  4. 4.
    Costa, Á., et al.: Attention level measurement during exoskeleton rehabilitation through a BMI system. In: González-Vargas, J., Ibáñez, J., Contreras-Vidal, J.L., van der Kooij, H., Pons, J.L. (eds.) Wearable Robotics: Challenges and Trends, vol. 16, pp. 243–247. Springer, Cham (2016)CrossRefGoogle Scholar
  5. 5.
    Huang, N.E., et al.: The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. R. Soc. London. Ser. A Math. Phys. Eng. Sci. 454(1971), 903LP–995 (1998)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Stockwell, R.G., Mansinha, L., Lowe, R.P.: Localization of the complex spectrum: the S transform. IEEE Trans. Signal Process. 44(4), 998–1001 (1996)CrossRefGoogle Scholar
  7. 7.
    Steinwart, I., Christmann, A.: Support Vector Machines. Springer, New York (2008)Google Scholar
  8. 8.
    Izenman, A.J.: Linear Discriminant Analysis, pp. 237–280. Springer, New York (2013)Google Scholar
  9. 9.
    Kohonen, T.: The self-organizing map. Proc. IEEE 78(9), 1464–1480 (1990)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Mario Ortiz
    • 1
  • Marisol Rodríguez-Ugarte
    • 1
  • Eduardo Iáñez
    • 1
  • José M. Azorín
    • 1
  1. 1.Brain-Machine Interface Systems LabMiguel Hernández University of ElcheElcheSpain

Personalised recommendations