A BCI motor imagery experiment based on parametric feature extraction and Fisher Criterion

David D'Croz-Baron, Juan Manuel Ramirez, Mary Baker, Vicente Alarcon-Aquino, Obed Carrera

Research output: Contribution to conferencePaper

13 Scopus citations

Abstract

An EEG-based classification method in the time domain is proposed to identify left and right hand motor imagery as part of a brain-computer interface (BCI) experiment. The feature vector is formed by sixth order autoregressive coefficients (AR) or sixth order adaptive autoregressive coefficients (AAR) representing EEG signals obtained from C3 and C4 channels, according to the EEG 10-20 standard. The signal is analyzed considering 1 second windows with a 50% overlapping. A feature selection process based on the Fisher Criterion (FC) removes irrelevant or noisy information. A Linear Discriminant Analysis (LDA) is applied to both cases: feature vectors formed with the total number of coefficients, and feature vectors formed with coefficients corresponding to larger Fisher Ratio. Classification results obtained using two AR methods, Burg and Levinson-Durbin, and one AAR LMS are presented.

Original languageEnglish
Pages257-261
Number of pages5
DOIs
StatePublished - 2012
Event22nd Annual International Conference on Electronics, Communications and Computers, CONIELECOMP 2012 - Cholula, Mexico
Duration: Feb 27 2012Feb 29 2012

Conference

Conference22nd Annual International Conference on Electronics, Communications and Computers, CONIELECOMP 2012
CountryMexico
CityCholula
Period02/27/1202/29/12

Keywords

  • Adaptive Autoregressive Coefficients (AAR)
  • Autoregressive coefficients (AR)
  • Brain Computer Interfaces (BCI)
  • EEG
  • Fisher Criterion (FC)

Fingerprint Dive into the research topics of 'A BCI motor imagery experiment based on parametric feature extraction and Fisher Criterion'. Together they form a unique fingerprint.

  • Cite this

    D'Croz-Baron, D., Ramirez, J. M., Baker, M., Alarcon-Aquino, V., & Carrera, O. (2012). A BCI motor imagery experiment based on parametric feature extraction and Fisher Criterion. 257-261. Paper presented at 22nd Annual International Conference on Electronics, Communications and Computers, CONIELECOMP 2012, Cholula, Mexico. https://doi.org/10.1109/CONIELECOMP.2012.6189920