Advertisement

Non-supervised Feature Selection: Evaluation in a BCI for Single-Trial Recognition of Gait Preparation/Stop

  • Denis Delisle-RodriguezEmail author
  • Ana Cecilia Villa-Parra
  • Alberto López-Delis
  • Anselmo Frizera-Neto
  • Eduardo Rocon
  • Teodiano Freire-Bastos
Conference paper
  • 94 Downloads
Part of the Biosystems & Biorobotics book series (BIOSYSROB, volume 15)

Abstract

Is presented a non-supervised method for feature selection based on similarity index, which is applied in a brain-computer interface (BCI) to recognize gait preparation/stops. Maximal information compression index is here used to obtain redundancies, while representation entropy value is employed to find the feature vectors with high entropy. EEG signals of six subjects were acquired on the primary cortex during walking, in order to evaluate this approach in a BCI. The maximum accuracy was 55 and 85 % to recognize gait preparation/stops, respectively. Thus, this method can be used in a BCI to improve the time delay during dimensionality reduction.

Keywords

Predictive Positive Value Dimensionality Reduction Motor Imagery True Positive Rate Band Power 
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.

Notes

Acknowledgments

Authors would like to thank CNPq, CAPES, FAPES and SENESCYT for supporting this research.

References

  1. 1.
    B. Graimann, J.E. Huggins, S.P. Levine, G. Pfurtscheller, Towards a direct brain interface based on human subdural recording and wavelet-packet analysis. IEEE Trans. Biomed. Eng. 51(6) (2004)Google Scholar
  2. 2.
    P. Mitra, C.A. Murthy, S.K. Pal, Unsupervised feature selection using feature similarity. IEEE Trans. Pattern Anal. Mach. Intell. 24(4), 1–13 (2002)Google Scholar
  3. 3.
    M. Seeber, R. Scherer, J. Wagner, T. Solis-Escalante, G.R. Müller-Putz, High and low gamma EEG oscillations in central sensorimotor areas are conversely modulated during the human gait cycle. Neuroimage 112, 318–326 (2015)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Denis Delisle-Rodriguez
    • 1
    • 3
    Email author
  • Ana Cecilia Villa-Parra
    • 1
    • 2
  • Alberto López-Delis
    • 3
  • Anselmo Frizera-Neto
    • 1
  • Eduardo Rocon
    • 4
  • Teodiano Freire-Bastos
    • 1
  1. 1.Electrical EngineeringFederal University of Espirito SantoVitoriaBrazil
  2. 2.GIIBUniversidad Politécnica SalesianaCuencaEcuador
  3. 3.Biophysics Medical CenterUniversity of OrienteSantiago de CubaCuba
  4. 4.Group of Neural and Cognitive EngineeringCSICMadridSpain

Personalised recommendations