Advertisement

Accuracy of Classification Algorithms Applied to EEG Records from Emotiv EPOC+ Using Their Spectral and Asymmetry Features

  • Kevin Martín-ChineaEmail author
  • Jordan Ortega
  • José Francisco Gómez-GonzálezEmail author
  • Jonay Toledo
  • Ernesto Pereda
  • Leopoldo Acosta
Conference paper
Part of the Learning and Analytics in Intelligent Systems book series (LAIS, volume 7)

Abstract

To develop a good BCI, it is necessary to take into account what features can be extracted and what classification algorithm can be used. In this manuscript, a cross-validation method is used to compare different classification algorithms (SVM, KNN, discriminant analyses and decision trees) as applied to EEG records obtained by a non-invasive wireless electroencephalograph (Emotiv EPOC+). The features used in the classification algorithms are the power spectrum of the signal and the hemispheric asymmetry. The used experimental paradigms (e.g. motor imagery) are designed to be used with reduced mobility people, because the aim is to develop a BCI to control an external device such as a wheelchair or a prosthesis.

Keywords

EEG Machine learning BCI Virtual reality Classification 

Notes

Acknowledgments

This work was conducted under the auspices of the Research Project ProID2017010100, supported by Consejería de Economía, Industria, Comercio y Conocimiento from Canary Government (Spain) and FEDER (European regional development fund (ERDF)), the Researches Projects TEC2016-80063-C3-2-R and DPI2017-90002-R, supported by Spanish Ministerio de Economía, Industria y Competitividad. J. Ortega has a fellowship by Agencia Canaria de Investigación, Innovación y Sociedad de la Información (ACIISI) from Canary Government (Spain).

References

  1. 1.
    Martišius, I., Damaševičius, R.: A prototype SSVEP based real time BCI gaming system. Comput. Intell. Neurosci. 2016, 1–15 (2016).  https://doi.org/10.1155/2016/3861425CrossRefGoogle Scholar
  2. 2.
    Qin, Y., Zhan, Y., Wang, C., et al.: Classifying four-category visual objects using multiple ERP components in single-trial ERP. Cogn. Neurodyn. 10, 275–285 (2016).  https://doi.org/10.1007/s11571-016-9378-0CrossRefGoogle Scholar
  3. 3.
    Oostenveld, R., Fries, P., Maris, E., Schoffelen, J.M.: FieldTrip: open source software for advanced analysis of MEG, EEG, and invasive electrophysiological data. Comput. Intell. Neurosci. (2011).  https://doi.org/10.1155/2011/156869CrossRefGoogle Scholar
  4. 4.
    Based, P.: Multitaper spectrum estimation, pp. 1–7 (2004)Google Scholar
  5. 5.
    Lin, Y.P., Wang, C.H., Wu, T.L., et al.: Support vector machine for EEG signal classification during listening to emotional music. In: Proceedings of the 2008 IEEE 10th Work Multimedia Signal Processing, MMSP 2008, pp. 127–130 (2008).  https://doi.org/10.1109/MMSP.2008.4665061
  6. 6.
    Lin, Y.P., Wang, C.H., Wu, T.L., et al.: Multilayer perceptron for EEG signal classification during listening to emotional music. In: IEEE Region 10 Annual International Conference Proceedings/TENCON (2007).  https://doi.org/10.1109/TENCON.2007.4428831
  7. 7.
    Bai, O., Mari, Z., Vorbach, S., Hallett, M.: Asymmetric spatiotemporal patterns of event-related desynchronization preceding voluntary sequential finger movements: a high-resolution EEG study. Clin. Neurophysiol. 116, 1213–1221 (2005).  https://doi.org/10.1016/j.clinph.2005.01.006CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Kevin Martín-Chinea
    • 1
    Email author
  • Jordan Ortega
    • 1
  • José Francisco Gómez-González
    • 1
    Email author
  • Jonay Toledo
    • 2
  • Ernesto Pereda
    • 1
  • Leopoldo Acosta
    • 2
  1. 1.Department of Industrial EngineeringUniversity of La LagunaLa LagunaSpain
  2. 2.Department of Computer and Systems EngineeringUniversity of La LagunaLa LagunaSpain

Personalised recommendations