Medical & Biological Engineering & Computing

, 45:61

Study of discriminant analysis applied to motor imagery bipolar data

Authors

    • Dp IEE, Edificio Los TejosPublic University of Navarre
  • Reinhold Scherer
    • Institute for Knowledge DiscoveryTUG
  • Rafael Cabeza
    • Dp IEE, Edificio Los TejosPublic University of Navarre
  • Alois Schlögl
    • Institute for Human–Computer InterfacesTUG
  • Gert Pfurtscheller
    • Institute for Knowledge DiscoveryTUG
Original Article

DOI: 10.1007/s11517-006-0122-5

Cite this article as:
Vidaurre, C., Scherer, R., Cabeza, R. et al. Med Bio Eng Comput (2007) 45: 61. doi:10.1007/s11517-006-0122-5

Abstract

We present a study of linear, quadratic and regularized discriminant analysis (RDA) applied to motor imagery data of three subjects. The aim of the work was to find out which classifier can separate better these two-class motor imagery data: linear, quadratic or some function in between the linear and quadratic solutions. Discriminant analysis methods were tested with two different feature extraction techniques, adaptive autoregressive parameters and logarithmic band power estimates, which are commonly used in brain–computer interface research. Differences in classification accuracy of the classifiers were found when using different amounts of data; if a small amount was available, the best classifier was linear discriminant analysis (LDA) and if enough data were available all three classifiers performed very similar. This suggests that the effort needed to find regularizing parameters for RDA can be avoided by using LDA.

Keywords

Brain–computer interfaceDiscriminant analysisRegularizationAdaptive autoregressive parametersLogarithmic band power estimates

Copyright information

© International Federation for Medical and Biological Engineering 2006