eduzhai > Applied Sciences > Engineering >

A Computationally Efficient Multiclass Time-Frequency Common Spatial Pattern Analysis on EEG Motor Imagery

  • king
  • (0) Download
  • 20210507
  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: Common spatial pattern (CSP) is a popular feature extraction method forelectroencephalogram (EEG) motor imagery (MI). This study modifies theconventional CSP algorithm to improve the multi-class MI classificationaccuracy and ensure the computation process is efficient. The EEG MI data isgathered from the Brain-Computer Interface (BCI) Competition IV. At first, abandpass filter and a time-frequency analysis are performed for each experimenttrial. Then, the optimal EEG signals for every experiment trials are selectedbased on the signal energy for CSP feature extraction. In the end, theextracted features are classified by three classifiers, linear discriminantanalysis (LDA), naïve Bayes (NVB), and support vector machine (SVM), inparallel for classification accuracy comparison. The experiment results showthe proposed algorithm average computation time is 37.22 less than the FBCSP(1st winner in the BCI Competition IV) and 4.98 longer than the conventionalCSP method. For the classification rate, the proposed algorithm kappa valueachieved 2nd highest compared with the top 3 winners in BCI Competition IV.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×