Medical & Biological Engineering & Computing

, 45:403

A comparison approach toward finding the best feature and classifier in cue-based BCI

Authors

    • Department of Computer Science and Engineering, School of EngineeringShiraz University
  • B. Graimann
    • Laboratory of Brain–Computer Interfaces, Institute for Knowledge Discovery at the GrazUniversity of Technology
  • M. H. Moradi
    • Department of Biomedical EngineeringAmirkabir University of Technology (Tehran Polytechnic)
  • G. Pfurtscheller
    • Laboratory of Brain–Computer Interfaces, Institute for Knowledge Discovery at the GrazUniversity of Technology
Original Article

DOI: 10.1007/s11517-007-0169-y

Cite this article as:
Boostani, R., Graimann, B., Moradi, M.H. et al. Med Bio Eng Comput (2007) 45: 403. doi:10.1007/s11517-007-0169-y

Abstract

In this paper, a comparative evaluation of state-of-the art feature extraction and classification methods is presented for five subjects in order to increase the performance of a cue-based Brain–Computer interface (BCI) system for imagery tasks (left and right hand movements). To select an informative feature with a reliable classifier features containing standard bandpower, AAR coefficients, and fractal dimension along with support vector machine (SVM), Adaboost and Fisher linear discriminant analysis (FLDA) classifiers have been assessed. In the single feature-classifier combinations, bandpower with FLDA gave the best results for three subjects, and fractal dimension and FLDA and SVM classifiers lead to the best results for two other subjects. A genetic algorithm has been used to find the best combination of the features with the aforementioned classifiers and led to dramatic reduction of the classification error and also best results in the four subjects. Genetic feature combination results have been compared with the simple feature combination to show the performance of the Genetic algorithm.

Keywords

Brain–Computer interface (BCI)AdaboostSupport vector machine (SVM)Adaptive auto regressive (AAR)Fisher linear discriminate analysis (FLDA)Fractal dimension (FD)Bandpower (BP)Genetic algorithm

Copyright information

© International Federation for Medical and Biological Engineering 2007